diff --git "a/uqff_report.json" "b/uqff_report.json" new file mode 100644--- /dev/null +++ "b/uqff_report.json" @@ -0,0 +1,21826 @@ +{ + "schema": 1, + "generated_by": { + "tool": "mistralrs quantize", + "mistralrs_version": "0.9.0", + "git_revision": "unknown" + }, + "base_model": "Qwen/Qwen3-0.6B", + "repo_id": "mistralrs-community/Qwen3-0.6B-UQFF", + "uqff_version": "1.1.0", + "outputs": [ + { + "quant": "afq2", + "shards": [ + "afq2-0.uqff" + ], + "layers": 197, + "actual_counts": { + "afq2": 197 + }, + "fallback_count": 0, + "layer_details": [ + { + "module": "lm_head", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 151936, + 64 + ] + }, + { + "module": "model.layers.0.mlp.down_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.0.mlp.gate_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.0.mlp.up_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.0.self_attn.k_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.0.self_attn.o_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.0.self_attn.q_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 2048, + 64 + ] + }, + { + "module": "model.layers.0.self_attn.v_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.1.mlp.down_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.1.mlp.gate_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.1.mlp.up_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.1.self_attn.k_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.1.self_attn.o_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.1.self_attn.q_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 2048, + 64 + ] + }, + { + "module": "model.layers.1.self_attn.v_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.10.mlp.down_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.10.mlp.gate_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.10.mlp.up_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.10.self_attn.k_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.10.self_attn.o_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.10.self_attn.q_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 2048, + 64 + ] + }, + { + "module": "model.layers.10.self_attn.v_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.11.mlp.down_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.11.mlp.gate_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.11.mlp.up_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.11.self_attn.k_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.11.self_attn.o_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.11.self_attn.q_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 2048, + 64 + ] + }, + { + "module": "model.layers.11.self_attn.v_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.12.mlp.down_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.12.mlp.gate_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.12.mlp.up_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.12.self_attn.k_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.12.self_attn.o_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.12.self_attn.q_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 2048, + 64 + ] + }, + { + "module": "model.layers.12.self_attn.v_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.13.mlp.down_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.13.mlp.gate_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.13.mlp.up_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.13.self_attn.k_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.13.self_attn.o_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.13.self_attn.q_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 2048, + 64 + ] + }, + { + "module": "model.layers.13.self_attn.v_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.14.mlp.down_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.14.mlp.gate_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.14.mlp.up_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.14.self_attn.k_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.14.self_attn.o_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.14.self_attn.q_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 2048, + 64 + ] + }, + { + "module": "model.layers.14.self_attn.v_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.15.mlp.down_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.15.mlp.gate_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.15.mlp.up_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.15.self_attn.k_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.15.self_attn.o_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.15.self_attn.q_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 2048, + 64 + ] + }, + { + "module": "model.layers.15.self_attn.v_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.16.mlp.down_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.16.mlp.gate_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.16.mlp.up_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.16.self_attn.k_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.16.self_attn.o_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.16.self_attn.q_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 2048, + 64 + ] + }, + { + "module": "model.layers.16.self_attn.v_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.17.mlp.down_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.17.mlp.gate_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.17.mlp.up_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.17.self_attn.k_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.17.self_attn.o_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.17.self_attn.q_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 2048, + 64 + ] + }, + { + "module": "model.layers.17.self_attn.v_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.18.mlp.down_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.18.mlp.gate_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.18.mlp.up_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.18.self_attn.k_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.18.self_attn.o_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.18.self_attn.q_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 2048, + 64 + ] + }, + { + "module": "model.layers.18.self_attn.v_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.19.mlp.down_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.19.mlp.gate_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.19.mlp.up_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.19.self_attn.k_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.19.self_attn.o_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.19.self_attn.q_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 2048, + 64 + ] + }, + { + "module": "model.layers.19.self_attn.v_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.2.mlp.down_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.2.mlp.gate_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.2.mlp.up_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.2.self_attn.k_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.2.self_attn.o_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.2.self_attn.q_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 2048, + 64 + ] + }, + { + "module": "model.layers.2.self_attn.v_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.20.mlp.down_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.20.mlp.gate_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.20.mlp.up_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.20.self_attn.k_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.20.self_attn.o_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.20.self_attn.q_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 2048, + 64 + ] + }, + { + "module": "model.layers.20.self_attn.v_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.21.mlp.down_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.21.mlp.gate_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.21.mlp.up_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.21.self_attn.k_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.21.self_attn.o_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.21.self_attn.q_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 2048, + 64 + ] + }, + { + "module": "model.layers.21.self_attn.v_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.22.mlp.down_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.22.mlp.gate_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.22.mlp.up_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.22.self_attn.k_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.22.self_attn.o_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.22.self_attn.q_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 2048, + 64 + ] + }, + { + "module": "model.layers.22.self_attn.v_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.23.mlp.down_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.23.mlp.gate_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.23.mlp.up_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.23.self_attn.k_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.23.self_attn.o_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.23.self_attn.q_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 2048, + 64 + ] + }, + { + "module": "model.layers.23.self_attn.v_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.24.mlp.down_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.24.mlp.gate_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.24.mlp.up_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.24.self_attn.k_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.24.self_attn.o_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.24.self_attn.q_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 2048, + 64 + ] + }, + { + "module": "model.layers.24.self_attn.v_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.25.mlp.down_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.25.mlp.gate_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.25.mlp.up_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.25.self_attn.k_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.25.self_attn.o_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.25.self_attn.q_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 2048, + 64 + ] + }, + { + "module": "model.layers.25.self_attn.v_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.26.mlp.down_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.26.mlp.gate_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.26.mlp.up_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.26.self_attn.k_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.26.self_attn.o_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.26.self_attn.q_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 2048, + 64 + ] + }, + { + "module": "model.layers.26.self_attn.v_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.27.mlp.down_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.27.mlp.gate_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.27.mlp.up_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.27.self_attn.k_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.27.self_attn.o_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.27.self_attn.q_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 2048, + 64 + ] + }, + { + "module": "model.layers.27.self_attn.v_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.3.mlp.down_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.3.mlp.gate_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.3.mlp.up_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.3.self_attn.k_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.3.self_attn.o_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.3.self_attn.q_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 2048, + 64 + ] + }, + { + "module": "model.layers.3.self_attn.v_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.4.mlp.down_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.4.mlp.gate_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.4.mlp.up_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.4.self_attn.k_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.4.self_attn.o_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.4.self_attn.q_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 2048, + 64 + ] + }, + { + "module": "model.layers.4.self_attn.v_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.5.mlp.down_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.5.mlp.gate_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.5.mlp.up_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.5.self_attn.k_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.5.self_attn.o_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.5.self_attn.q_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 2048, + 64 + ] + }, + { + "module": "model.layers.5.self_attn.v_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.6.mlp.down_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.6.mlp.gate_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.6.mlp.up_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.6.self_attn.k_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.6.self_attn.o_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.6.self_attn.q_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 2048, + 64 + ] + }, + { + "module": "model.layers.6.self_attn.v_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.7.mlp.down_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.7.mlp.gate_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.7.mlp.up_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.7.self_attn.k_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.7.self_attn.o_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.7.self_attn.q_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 2048, + 64 + ] + }, + { + "module": "model.layers.7.self_attn.v_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.8.mlp.down_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.8.mlp.gate_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.8.mlp.up_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.8.self_attn.k_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.8.self_attn.o_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.8.self_attn.q_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 2048, + 64 + ] + }, + { + "module": "model.layers.8.self_attn.v_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.9.mlp.down_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.9.mlp.gate_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.9.mlp.up_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 3072, + 64 + ] + }, + { + "module": "model.layers.9.self_attn.k_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + }, + { + "module": "model.layers.9.self_attn.o_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.9.self_attn.q_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 2048, + 64 + ] + }, + { + "module": "model.layers.9.self_attn.v_proj", + "default_target": "afq2", + "resolved_target": "afq2", + "stored": "afq2", + "shape": [ + 1024, + 64 + ] + } + ] + }, + { + "quant": "q3k", + "shards": [ + "q3k-0.uqff" + ], + "layers": 197, + "actual_counts": { + "q3k": 197 + }, + "fallback_count": 0, + "layer_details": [ + { + "module": "lm_head", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 151936, + 1024 + ] + }, + { + "module": "model.layers.0.mlp.down_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.0.mlp.gate_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.0.mlp.up_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.0.self_attn.k_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.0.self_attn.o_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.0.self_attn.q_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.0.self_attn.v_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.1.mlp.down_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.1.mlp.gate_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.1.mlp.up_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.1.self_attn.k_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.1.self_attn.o_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.1.self_attn.q_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.1.self_attn.v_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.10.mlp.down_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.10.mlp.gate_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.10.mlp.up_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.10.self_attn.k_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.10.self_attn.o_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.10.self_attn.q_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.10.self_attn.v_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.11.mlp.down_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.11.mlp.gate_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.11.mlp.up_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.11.self_attn.k_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.11.self_attn.o_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.11.self_attn.q_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.11.self_attn.v_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.12.mlp.down_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.12.mlp.gate_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.12.mlp.up_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.12.self_attn.k_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.12.self_attn.o_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.12.self_attn.q_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.12.self_attn.v_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.13.mlp.down_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.13.mlp.gate_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.13.mlp.up_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.13.self_attn.k_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.13.self_attn.o_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.13.self_attn.q_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.13.self_attn.v_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.14.mlp.down_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.14.mlp.gate_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.14.mlp.up_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.14.self_attn.k_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.14.self_attn.o_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.14.self_attn.q_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.14.self_attn.v_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.15.mlp.down_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.15.mlp.gate_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.15.mlp.up_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.15.self_attn.k_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.15.self_attn.o_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.15.self_attn.q_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.15.self_attn.v_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.16.mlp.down_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.16.mlp.gate_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.16.mlp.up_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.16.self_attn.k_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.16.self_attn.o_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.16.self_attn.q_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.16.self_attn.v_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.17.mlp.down_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.17.mlp.gate_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.17.mlp.up_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.17.self_attn.k_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.17.self_attn.o_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.17.self_attn.q_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.17.self_attn.v_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.18.mlp.down_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.18.mlp.gate_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.18.mlp.up_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.18.self_attn.k_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.18.self_attn.o_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.18.self_attn.q_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.18.self_attn.v_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.19.mlp.down_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.19.mlp.gate_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.19.mlp.up_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.19.self_attn.k_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.19.self_attn.o_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.19.self_attn.q_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.19.self_attn.v_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.2.mlp.down_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.2.mlp.gate_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.2.mlp.up_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.2.self_attn.k_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.2.self_attn.o_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.2.self_attn.q_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.2.self_attn.v_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.20.mlp.down_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.20.mlp.gate_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.20.mlp.up_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.20.self_attn.k_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.20.self_attn.o_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.20.self_attn.q_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.20.self_attn.v_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.21.mlp.down_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.21.mlp.gate_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.21.mlp.up_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.21.self_attn.k_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.21.self_attn.o_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.21.self_attn.q_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.21.self_attn.v_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.22.mlp.down_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.22.mlp.gate_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.22.mlp.up_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.22.self_attn.k_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.22.self_attn.o_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.22.self_attn.q_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.22.self_attn.v_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.23.mlp.down_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.23.mlp.gate_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.23.mlp.up_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.23.self_attn.k_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.23.self_attn.o_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.23.self_attn.q_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.23.self_attn.v_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.24.mlp.down_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.24.mlp.gate_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.24.mlp.up_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.24.self_attn.k_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.24.self_attn.o_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.24.self_attn.q_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.24.self_attn.v_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.25.mlp.down_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.25.mlp.gate_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.25.mlp.up_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.25.self_attn.k_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.25.self_attn.o_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.25.self_attn.q_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.25.self_attn.v_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.26.mlp.down_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.26.mlp.gate_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.26.mlp.up_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.26.self_attn.k_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.26.self_attn.o_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.26.self_attn.q_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.26.self_attn.v_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.27.mlp.down_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.27.mlp.gate_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.27.mlp.up_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.27.self_attn.k_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.27.self_attn.o_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.27.self_attn.q_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.27.self_attn.v_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.3.mlp.down_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.3.mlp.gate_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.3.mlp.up_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.3.self_attn.k_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.3.self_attn.o_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.3.self_attn.q_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.3.self_attn.v_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.4.mlp.down_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.4.mlp.gate_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.4.mlp.up_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.4.self_attn.k_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.4.self_attn.o_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.4.self_attn.q_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.4.self_attn.v_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.5.mlp.down_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.5.mlp.gate_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.5.mlp.up_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.5.self_attn.k_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.5.self_attn.o_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.5.self_attn.q_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.5.self_attn.v_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.6.mlp.down_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.6.mlp.gate_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.6.mlp.up_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.6.self_attn.k_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.6.self_attn.o_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.6.self_attn.q_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.6.self_attn.v_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.7.mlp.down_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.7.mlp.gate_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.7.mlp.up_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.7.self_attn.k_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.7.self_attn.o_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.7.self_attn.q_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.7.self_attn.v_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.8.mlp.down_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.8.mlp.gate_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.8.mlp.up_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.8.self_attn.k_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.8.self_attn.o_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.8.self_attn.q_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.8.self_attn.v_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.9.mlp.down_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.9.mlp.gate_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.9.mlp.up_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.9.self_attn.k_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.9.self_attn.o_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.9.self_attn.q_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.9.self_attn.v_proj", + "default_target": "q3k", + "resolved_target": "q3k", + "stored": "q3k", + "shape": [ + 1024, + 1024 + ] + } + ] + }, + { + "quant": "afq3", + "shards": [ + "afq3-0.uqff" + ], + "layers": 197, + "actual_counts": { + "afq3": 197 + }, + "fallback_count": 0, + "layer_details": [ + { + "module": "lm_head", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 151936, + 96 + ] + }, + { + "module": "model.layers.0.mlp.down_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 288 + ] + }, + { + "module": "model.layers.0.mlp.gate_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.0.mlp.up_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.0.self_attn.k_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.0.self_attn.o_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.0.self_attn.q_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 2048, + 96 + ] + }, + { + "module": "model.layers.0.self_attn.v_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.1.mlp.down_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 288 + ] + }, + { + "module": "model.layers.1.mlp.gate_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.1.mlp.up_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.1.self_attn.k_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.1.self_attn.o_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.1.self_attn.q_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 2048, + 96 + ] + }, + { + "module": "model.layers.1.self_attn.v_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.10.mlp.down_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 288 + ] + }, + { + "module": "model.layers.10.mlp.gate_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.10.mlp.up_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.10.self_attn.k_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.10.self_attn.o_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.10.self_attn.q_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 2048, + 96 + ] + }, + { + "module": "model.layers.10.self_attn.v_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.11.mlp.down_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 288 + ] + }, + { + "module": "model.layers.11.mlp.gate_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.11.mlp.up_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.11.self_attn.k_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.11.self_attn.o_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.11.self_attn.q_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 2048, + 96 + ] + }, + { + "module": "model.layers.11.self_attn.v_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.12.mlp.down_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 288 + ] + }, + { + "module": "model.layers.12.mlp.gate_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.12.mlp.up_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.12.self_attn.k_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.12.self_attn.o_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.12.self_attn.q_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 2048, + 96 + ] + }, + { + "module": "model.layers.12.self_attn.v_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.13.mlp.down_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 288 + ] + }, + { + "module": "model.layers.13.mlp.gate_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.13.mlp.up_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.13.self_attn.k_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.13.self_attn.o_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.13.self_attn.q_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 2048, + 96 + ] + }, + { + "module": "model.layers.13.self_attn.v_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.14.mlp.down_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 288 + ] + }, + { + "module": "model.layers.14.mlp.gate_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.14.mlp.up_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.14.self_attn.k_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.14.self_attn.o_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.14.self_attn.q_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 2048, + 96 + ] + }, + { + "module": "model.layers.14.self_attn.v_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.15.mlp.down_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 288 + ] + }, + { + "module": "model.layers.15.mlp.gate_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.15.mlp.up_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.15.self_attn.k_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.15.self_attn.o_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.15.self_attn.q_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 2048, + 96 + ] + }, + { + "module": "model.layers.15.self_attn.v_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.16.mlp.down_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 288 + ] + }, + { + "module": "model.layers.16.mlp.gate_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.16.mlp.up_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.16.self_attn.k_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.16.self_attn.o_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.16.self_attn.q_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 2048, + 96 + ] + }, + { + "module": "model.layers.16.self_attn.v_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.17.mlp.down_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 288 + ] + }, + { + "module": "model.layers.17.mlp.gate_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.17.mlp.up_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.17.self_attn.k_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.17.self_attn.o_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.17.self_attn.q_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 2048, + 96 + ] + }, + { + "module": "model.layers.17.self_attn.v_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.18.mlp.down_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 288 + ] + }, + { + "module": "model.layers.18.mlp.gate_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.18.mlp.up_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.18.self_attn.k_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.18.self_attn.o_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.18.self_attn.q_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 2048, + 96 + ] + }, + { + "module": "model.layers.18.self_attn.v_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.19.mlp.down_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 288 + ] + }, + { + "module": "model.layers.19.mlp.gate_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.19.mlp.up_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.19.self_attn.k_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.19.self_attn.o_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.19.self_attn.q_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 2048, + 96 + ] + }, + { + "module": "model.layers.19.self_attn.v_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.2.mlp.down_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 288 + ] + }, + { + "module": "model.layers.2.mlp.gate_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.2.mlp.up_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.2.self_attn.k_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.2.self_attn.o_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.2.self_attn.q_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 2048, + 96 + ] + }, + { + "module": "model.layers.2.self_attn.v_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.20.mlp.down_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 288 + ] + }, + { + "module": "model.layers.20.mlp.gate_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.20.mlp.up_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.20.self_attn.k_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.20.self_attn.o_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.20.self_attn.q_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 2048, + 96 + ] + }, + { + "module": "model.layers.20.self_attn.v_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.21.mlp.down_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 288 + ] + }, + { + "module": "model.layers.21.mlp.gate_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.21.mlp.up_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.21.self_attn.k_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.21.self_attn.o_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.21.self_attn.q_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 2048, + 96 + ] + }, + { + "module": "model.layers.21.self_attn.v_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.22.mlp.down_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 288 + ] + }, + { + "module": "model.layers.22.mlp.gate_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.22.mlp.up_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.22.self_attn.k_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.22.self_attn.o_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.22.self_attn.q_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 2048, + 96 + ] + }, + { + "module": "model.layers.22.self_attn.v_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.23.mlp.down_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 288 + ] + }, + { + "module": "model.layers.23.mlp.gate_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.23.mlp.up_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.23.self_attn.k_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.23.self_attn.o_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.23.self_attn.q_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 2048, + 96 + ] + }, + { + "module": "model.layers.23.self_attn.v_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.24.mlp.down_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 288 + ] + }, + { + "module": "model.layers.24.mlp.gate_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.24.mlp.up_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.24.self_attn.k_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.24.self_attn.o_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.24.self_attn.q_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 2048, + 96 + ] + }, + { + "module": "model.layers.24.self_attn.v_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.25.mlp.down_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 288 + ] + }, + { + "module": "model.layers.25.mlp.gate_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.25.mlp.up_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.25.self_attn.k_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.25.self_attn.o_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.25.self_attn.q_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 2048, + 96 + ] + }, + { + "module": "model.layers.25.self_attn.v_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.26.mlp.down_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 288 + ] + }, + { + "module": "model.layers.26.mlp.gate_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.26.mlp.up_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.26.self_attn.k_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.26.self_attn.o_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.26.self_attn.q_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 2048, + 96 + ] + }, + { + "module": "model.layers.26.self_attn.v_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.27.mlp.down_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 288 + ] + }, + { + "module": "model.layers.27.mlp.gate_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.27.mlp.up_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.27.self_attn.k_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.27.self_attn.o_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.27.self_attn.q_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 2048, + 96 + ] + }, + { + "module": "model.layers.27.self_attn.v_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.3.mlp.down_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 288 + ] + }, + { + "module": "model.layers.3.mlp.gate_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.3.mlp.up_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.3.self_attn.k_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.3.self_attn.o_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.3.self_attn.q_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 2048, + 96 + ] + }, + { + "module": "model.layers.3.self_attn.v_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.4.mlp.down_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 288 + ] + }, + { + "module": "model.layers.4.mlp.gate_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.4.mlp.up_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.4.self_attn.k_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.4.self_attn.o_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.4.self_attn.q_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 2048, + 96 + ] + }, + { + "module": "model.layers.4.self_attn.v_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.5.mlp.down_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 288 + ] + }, + { + "module": "model.layers.5.mlp.gate_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.5.mlp.up_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.5.self_attn.k_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.5.self_attn.o_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.5.self_attn.q_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 2048, + 96 + ] + }, + { + "module": "model.layers.5.self_attn.v_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.6.mlp.down_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 288 + ] + }, + { + "module": "model.layers.6.mlp.gate_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.6.mlp.up_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.6.self_attn.k_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.6.self_attn.o_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.6.self_attn.q_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 2048, + 96 + ] + }, + { + "module": "model.layers.6.self_attn.v_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.7.mlp.down_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 288 + ] + }, + { + "module": "model.layers.7.mlp.gate_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.7.mlp.up_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.7.self_attn.k_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.7.self_attn.o_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.7.self_attn.q_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 2048, + 96 + ] + }, + { + "module": "model.layers.7.self_attn.v_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.8.mlp.down_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 288 + ] + }, + { + "module": "model.layers.8.mlp.gate_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.8.mlp.up_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.8.self_attn.k_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.8.self_attn.o_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.8.self_attn.q_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 2048, + 96 + ] + }, + { + "module": "model.layers.8.self_attn.v_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.9.mlp.down_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 288 + ] + }, + { + "module": "model.layers.9.mlp.gate_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.9.mlp.up_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 3072, + 96 + ] + }, + { + "module": "model.layers.9.self_attn.k_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + }, + { + "module": "model.layers.9.self_attn.o_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.9.self_attn.q_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 2048, + 96 + ] + }, + { + "module": "model.layers.9.self_attn.v_proj", + "default_target": "afq3", + "resolved_target": "afq3", + "stored": "afq3", + "shape": [ + 1024, + 96 + ] + } + ] + }, + { + "quant": "q4k", + "shards": [ + "q4k-0.uqff" + ], + "layers": 197, + "actual_counts": { + "q4k": 197 + }, + "fallback_count": 0, + "layer_details": [ + { + "module": "lm_head", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 151936, + 1024 + ] + }, + { + "module": "model.layers.0.mlp.down_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.0.mlp.gate_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.0.mlp.up_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.0.self_attn.k_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.0.self_attn.o_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.0.self_attn.q_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.0.self_attn.v_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.1.mlp.down_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.1.mlp.gate_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.1.mlp.up_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.1.self_attn.k_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.1.self_attn.o_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.1.self_attn.q_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.1.self_attn.v_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.10.mlp.down_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.10.mlp.gate_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.10.mlp.up_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.10.self_attn.k_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.10.self_attn.o_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.10.self_attn.q_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.10.self_attn.v_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.11.mlp.down_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.11.mlp.gate_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.11.mlp.up_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.11.self_attn.k_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.11.self_attn.o_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.11.self_attn.q_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.11.self_attn.v_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.12.mlp.down_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.12.mlp.gate_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.12.mlp.up_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.12.self_attn.k_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.12.self_attn.o_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.12.self_attn.q_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.12.self_attn.v_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.13.mlp.down_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.13.mlp.gate_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.13.mlp.up_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.13.self_attn.k_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.13.self_attn.o_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.13.self_attn.q_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.13.self_attn.v_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.14.mlp.down_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.14.mlp.gate_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.14.mlp.up_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.14.self_attn.k_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.14.self_attn.o_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.14.self_attn.q_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.14.self_attn.v_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.15.mlp.down_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.15.mlp.gate_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.15.mlp.up_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.15.self_attn.k_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.15.self_attn.o_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.15.self_attn.q_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.15.self_attn.v_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.16.mlp.down_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.16.mlp.gate_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.16.mlp.up_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.16.self_attn.k_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.16.self_attn.o_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.16.self_attn.q_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.16.self_attn.v_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.17.mlp.down_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.17.mlp.gate_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.17.mlp.up_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.17.self_attn.k_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.17.self_attn.o_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.17.self_attn.q_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.17.self_attn.v_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.18.mlp.down_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.18.mlp.gate_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.18.mlp.up_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.18.self_attn.k_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.18.self_attn.o_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.18.self_attn.q_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.18.self_attn.v_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.19.mlp.down_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.19.mlp.gate_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.19.mlp.up_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.19.self_attn.k_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.19.self_attn.o_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.19.self_attn.q_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.19.self_attn.v_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.2.mlp.down_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.2.mlp.gate_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.2.mlp.up_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.2.self_attn.k_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.2.self_attn.o_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.2.self_attn.q_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.2.self_attn.v_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.20.mlp.down_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.20.mlp.gate_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.20.mlp.up_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.20.self_attn.k_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.20.self_attn.o_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.20.self_attn.q_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.20.self_attn.v_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.21.mlp.down_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.21.mlp.gate_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.21.mlp.up_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.21.self_attn.k_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.21.self_attn.o_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.21.self_attn.q_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.21.self_attn.v_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.22.mlp.down_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.22.mlp.gate_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.22.mlp.up_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.22.self_attn.k_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.22.self_attn.o_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.22.self_attn.q_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.22.self_attn.v_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.23.mlp.down_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.23.mlp.gate_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.23.mlp.up_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.23.self_attn.k_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.23.self_attn.o_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.23.self_attn.q_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.23.self_attn.v_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.24.mlp.down_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.24.mlp.gate_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.24.mlp.up_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.24.self_attn.k_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.24.self_attn.o_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.24.self_attn.q_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.24.self_attn.v_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.25.mlp.down_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.25.mlp.gate_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.25.mlp.up_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.25.self_attn.k_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.25.self_attn.o_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.25.self_attn.q_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.25.self_attn.v_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.26.mlp.down_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.26.mlp.gate_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.26.mlp.up_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.26.self_attn.k_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.26.self_attn.o_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.26.self_attn.q_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.26.self_attn.v_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.27.mlp.down_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.27.mlp.gate_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.27.mlp.up_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.27.self_attn.k_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.27.self_attn.o_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.27.self_attn.q_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.27.self_attn.v_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.3.mlp.down_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.3.mlp.gate_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.3.mlp.up_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.3.self_attn.k_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.3.self_attn.o_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.3.self_attn.q_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.3.self_attn.v_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.4.mlp.down_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.4.mlp.gate_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.4.mlp.up_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.4.self_attn.k_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.4.self_attn.o_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.4.self_attn.q_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.4.self_attn.v_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.5.mlp.down_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.5.mlp.gate_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.5.mlp.up_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.5.self_attn.k_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.5.self_attn.o_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.5.self_attn.q_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.5.self_attn.v_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.6.mlp.down_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.6.mlp.gate_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.6.mlp.up_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.6.self_attn.k_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.6.self_attn.o_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.6.self_attn.q_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.6.self_attn.v_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.7.mlp.down_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.7.mlp.gate_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.7.mlp.up_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.7.self_attn.k_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.7.self_attn.o_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.7.self_attn.q_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.7.self_attn.v_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.8.mlp.down_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.8.mlp.gate_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.8.mlp.up_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.8.self_attn.k_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.8.self_attn.o_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.8.self_attn.q_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.8.self_attn.v_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.9.mlp.down_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.9.mlp.gate_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.9.mlp.up_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.9.self_attn.k_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.9.self_attn.o_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.9.self_attn.q_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.9.self_attn.v_proj", + "default_target": "q4k", + "resolved_target": "q4k", + "stored": "q4k", + "shape": [ + 1024, + 1024 + ] + } + ] + }, + { + "quant": "afq4", + "shards": [ + "afq4-0.uqff" + ], + "layers": 197, + "actual_counts": { + "afq4": 197 + }, + "fallback_count": 0, + "layer_details": [ + { + "module": "lm_head", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 151936, + 128 + ] + }, + { + "module": "model.layers.0.mlp.down_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.0.mlp.gate_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.0.mlp.up_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.0.self_attn.k_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.0.self_attn.o_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.0.self_attn.q_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 2048, + 128 + ] + }, + { + "module": "model.layers.0.self_attn.v_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.1.mlp.down_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.1.mlp.gate_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.1.mlp.up_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.1.self_attn.k_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.1.self_attn.o_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.1.self_attn.q_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 2048, + 128 + ] + }, + { + "module": "model.layers.1.self_attn.v_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.10.mlp.down_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.10.mlp.gate_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.10.mlp.up_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.10.self_attn.k_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.10.self_attn.o_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.10.self_attn.q_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 2048, + 128 + ] + }, + { + "module": "model.layers.10.self_attn.v_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.11.mlp.down_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.11.mlp.gate_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.11.mlp.up_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.11.self_attn.k_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.11.self_attn.o_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.11.self_attn.q_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 2048, + 128 + ] + }, + { + "module": "model.layers.11.self_attn.v_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.12.mlp.down_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.12.mlp.gate_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.12.mlp.up_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.12.self_attn.k_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.12.self_attn.o_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.12.self_attn.q_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 2048, + 128 + ] + }, + { + "module": "model.layers.12.self_attn.v_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.13.mlp.down_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.13.mlp.gate_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.13.mlp.up_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.13.self_attn.k_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.13.self_attn.o_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.13.self_attn.q_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 2048, + 128 + ] + }, + { + "module": "model.layers.13.self_attn.v_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.14.mlp.down_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.14.mlp.gate_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.14.mlp.up_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.14.self_attn.k_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.14.self_attn.o_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.14.self_attn.q_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 2048, + 128 + ] + }, + { + "module": "model.layers.14.self_attn.v_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.15.mlp.down_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.15.mlp.gate_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.15.mlp.up_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.15.self_attn.k_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.15.self_attn.o_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.15.self_attn.q_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 2048, + 128 + ] + }, + { + "module": "model.layers.15.self_attn.v_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.16.mlp.down_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.16.mlp.gate_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.16.mlp.up_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.16.self_attn.k_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.16.self_attn.o_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.16.self_attn.q_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 2048, + 128 + ] + }, + { + "module": "model.layers.16.self_attn.v_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.17.mlp.down_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.17.mlp.gate_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.17.mlp.up_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.17.self_attn.k_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.17.self_attn.o_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.17.self_attn.q_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 2048, + 128 + ] + }, + { + "module": "model.layers.17.self_attn.v_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.18.mlp.down_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.18.mlp.gate_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.18.mlp.up_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.18.self_attn.k_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.18.self_attn.o_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.18.self_attn.q_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 2048, + 128 + ] + }, + { + "module": "model.layers.18.self_attn.v_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.19.mlp.down_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.19.mlp.gate_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.19.mlp.up_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.19.self_attn.k_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.19.self_attn.o_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.19.self_attn.q_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 2048, + 128 + ] + }, + { + "module": "model.layers.19.self_attn.v_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.2.mlp.down_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.2.mlp.gate_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.2.mlp.up_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.2.self_attn.k_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.2.self_attn.o_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.2.self_attn.q_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 2048, + 128 + ] + }, + { + "module": "model.layers.2.self_attn.v_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.20.mlp.down_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.20.mlp.gate_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.20.mlp.up_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.20.self_attn.k_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.20.self_attn.o_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.20.self_attn.q_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 2048, + 128 + ] + }, + { + "module": "model.layers.20.self_attn.v_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.21.mlp.down_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.21.mlp.gate_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.21.mlp.up_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.21.self_attn.k_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.21.self_attn.o_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.21.self_attn.q_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 2048, + 128 + ] + }, + { + "module": "model.layers.21.self_attn.v_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.22.mlp.down_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.22.mlp.gate_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.22.mlp.up_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.22.self_attn.k_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.22.self_attn.o_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.22.self_attn.q_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 2048, + 128 + ] + }, + { + "module": "model.layers.22.self_attn.v_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.23.mlp.down_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.23.mlp.gate_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.23.mlp.up_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.23.self_attn.k_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.23.self_attn.o_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.23.self_attn.q_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 2048, + 128 + ] + }, + { + "module": "model.layers.23.self_attn.v_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.24.mlp.down_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.24.mlp.gate_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.24.mlp.up_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.24.self_attn.k_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.24.self_attn.o_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.24.self_attn.q_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 2048, + 128 + ] + }, + { + "module": "model.layers.24.self_attn.v_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.25.mlp.down_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.25.mlp.gate_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.25.mlp.up_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.25.self_attn.k_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.25.self_attn.o_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.25.self_attn.q_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 2048, + 128 + ] + }, + { + "module": "model.layers.25.self_attn.v_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.26.mlp.down_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.26.mlp.gate_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.26.mlp.up_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.26.self_attn.k_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.26.self_attn.o_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.26.self_attn.q_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 2048, + 128 + ] + }, + { + "module": "model.layers.26.self_attn.v_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.27.mlp.down_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.27.mlp.gate_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.27.mlp.up_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.27.self_attn.k_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.27.self_attn.o_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.27.self_attn.q_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 2048, + 128 + ] + }, + { + "module": "model.layers.27.self_attn.v_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.3.mlp.down_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.3.mlp.gate_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.3.mlp.up_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.3.self_attn.k_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.3.self_attn.o_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.3.self_attn.q_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 2048, + 128 + ] + }, + { + "module": "model.layers.3.self_attn.v_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.4.mlp.down_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.4.mlp.gate_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.4.mlp.up_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.4.self_attn.k_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.4.self_attn.o_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.4.self_attn.q_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 2048, + 128 + ] + }, + { + "module": "model.layers.4.self_attn.v_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.5.mlp.down_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.5.mlp.gate_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.5.mlp.up_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.5.self_attn.k_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.5.self_attn.o_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.5.self_attn.q_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 2048, + 128 + ] + }, + { + "module": "model.layers.5.self_attn.v_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.6.mlp.down_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.6.mlp.gate_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.6.mlp.up_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.6.self_attn.k_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.6.self_attn.o_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.6.self_attn.q_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 2048, + 128 + ] + }, + { + "module": "model.layers.6.self_attn.v_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.7.mlp.down_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.7.mlp.gate_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.7.mlp.up_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.7.self_attn.k_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.7.self_attn.o_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.7.self_attn.q_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 2048, + 128 + ] + }, + { + "module": "model.layers.7.self_attn.v_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.8.mlp.down_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.8.mlp.gate_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.8.mlp.up_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.8.self_attn.k_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.8.self_attn.o_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.8.self_attn.q_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 2048, + 128 + ] + }, + { + "module": "model.layers.8.self_attn.v_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.9.mlp.down_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.9.mlp.gate_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.9.mlp.up_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 3072, + 128 + ] + }, + { + "module": "model.layers.9.self_attn.k_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + }, + { + "module": "model.layers.9.self_attn.o_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.9.self_attn.q_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 2048, + 128 + ] + }, + { + "module": "model.layers.9.self_attn.v_proj", + "default_target": "afq4", + "resolved_target": "afq4", + "stored": "afq4", + "shape": [ + 1024, + 128 + ] + } + ] + }, + { + "quant": "q5k", + "shards": [ + "q5k-0.uqff" + ], + "layers": 197, + "actual_counts": { + "q5k": 197 + }, + "fallback_count": 0, + "layer_details": [ + { + "module": "lm_head", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 151936, + 1024 + ] + }, + { + "module": "model.layers.0.mlp.down_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.0.mlp.gate_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.0.mlp.up_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.0.self_attn.k_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.0.self_attn.o_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.0.self_attn.q_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.0.self_attn.v_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.1.mlp.down_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.1.mlp.gate_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.1.mlp.up_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.1.self_attn.k_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.1.self_attn.o_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.1.self_attn.q_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.1.self_attn.v_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.10.mlp.down_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.10.mlp.gate_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.10.mlp.up_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.10.self_attn.k_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.10.self_attn.o_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.10.self_attn.q_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.10.self_attn.v_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.11.mlp.down_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.11.mlp.gate_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.11.mlp.up_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.11.self_attn.k_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.11.self_attn.o_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.11.self_attn.q_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.11.self_attn.v_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.12.mlp.down_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.12.mlp.gate_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.12.mlp.up_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.12.self_attn.k_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.12.self_attn.o_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.12.self_attn.q_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.12.self_attn.v_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.13.mlp.down_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.13.mlp.gate_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.13.mlp.up_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.13.self_attn.k_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.13.self_attn.o_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.13.self_attn.q_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.13.self_attn.v_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.14.mlp.down_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.14.mlp.gate_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.14.mlp.up_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.14.self_attn.k_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.14.self_attn.o_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.14.self_attn.q_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.14.self_attn.v_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.15.mlp.down_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.15.mlp.gate_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.15.mlp.up_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.15.self_attn.k_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.15.self_attn.o_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.15.self_attn.q_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.15.self_attn.v_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.16.mlp.down_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.16.mlp.gate_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.16.mlp.up_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.16.self_attn.k_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.16.self_attn.o_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.16.self_attn.q_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.16.self_attn.v_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.17.mlp.down_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.17.mlp.gate_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.17.mlp.up_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.17.self_attn.k_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.17.self_attn.o_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.17.self_attn.q_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.17.self_attn.v_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.18.mlp.down_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.18.mlp.gate_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.18.mlp.up_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.18.self_attn.k_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.18.self_attn.o_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.18.self_attn.q_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.18.self_attn.v_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.19.mlp.down_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.19.mlp.gate_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.19.mlp.up_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.19.self_attn.k_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.19.self_attn.o_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.19.self_attn.q_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.19.self_attn.v_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.2.mlp.down_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.2.mlp.gate_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.2.mlp.up_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.2.self_attn.k_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.2.self_attn.o_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.2.self_attn.q_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.2.self_attn.v_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.20.mlp.down_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.20.mlp.gate_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.20.mlp.up_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.20.self_attn.k_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.20.self_attn.o_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.20.self_attn.q_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.20.self_attn.v_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.21.mlp.down_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.21.mlp.gate_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.21.mlp.up_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.21.self_attn.k_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.21.self_attn.o_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.21.self_attn.q_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.21.self_attn.v_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.22.mlp.down_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.22.mlp.gate_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.22.mlp.up_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.22.self_attn.k_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.22.self_attn.o_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.22.self_attn.q_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.22.self_attn.v_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.23.mlp.down_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.23.mlp.gate_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.23.mlp.up_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.23.self_attn.k_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.23.self_attn.o_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.23.self_attn.q_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.23.self_attn.v_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.24.mlp.down_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.24.mlp.gate_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.24.mlp.up_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.24.self_attn.k_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.24.self_attn.o_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.24.self_attn.q_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.24.self_attn.v_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.25.mlp.down_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.25.mlp.gate_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.25.mlp.up_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.25.self_attn.k_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.25.self_attn.o_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.25.self_attn.q_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.25.self_attn.v_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.26.mlp.down_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.26.mlp.gate_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.26.mlp.up_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.26.self_attn.k_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.26.self_attn.o_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.26.self_attn.q_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.26.self_attn.v_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.27.mlp.down_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.27.mlp.gate_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.27.mlp.up_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.27.self_attn.k_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.27.self_attn.o_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.27.self_attn.q_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.27.self_attn.v_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.3.mlp.down_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.3.mlp.gate_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.3.mlp.up_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.3.self_attn.k_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.3.self_attn.o_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.3.self_attn.q_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.3.self_attn.v_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.4.mlp.down_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.4.mlp.gate_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.4.mlp.up_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.4.self_attn.k_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.4.self_attn.o_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.4.self_attn.q_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.4.self_attn.v_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.5.mlp.down_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.5.mlp.gate_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.5.mlp.up_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.5.self_attn.k_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.5.self_attn.o_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.5.self_attn.q_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.5.self_attn.v_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.6.mlp.down_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.6.mlp.gate_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.6.mlp.up_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.6.self_attn.k_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.6.self_attn.o_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.6.self_attn.q_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.6.self_attn.v_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.7.mlp.down_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.7.mlp.gate_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.7.mlp.up_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.7.self_attn.k_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.7.self_attn.o_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.7.self_attn.q_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.7.self_attn.v_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.8.mlp.down_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.8.mlp.gate_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.8.mlp.up_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.8.self_attn.k_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.8.self_attn.o_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.8.self_attn.q_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.8.self_attn.v_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.9.mlp.down_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.9.mlp.gate_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.9.mlp.up_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.9.self_attn.k_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.9.self_attn.o_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.9.self_attn.q_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.9.self_attn.v_proj", + "default_target": "q5k", + "resolved_target": "q5k", + "stored": "q5k", + "shape": [ + 1024, + 1024 + ] + } + ] + }, + { + "quant": "q6k", + "shards": [ + "q6k-0.uqff" + ], + "layers": 197, + "actual_counts": { + "q6k": 197 + }, + "fallback_count": 0, + "layer_details": [ + { + "module": "lm_head", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 151936, + 1024 + ] + }, + { + "module": "model.layers.0.mlp.down_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.0.mlp.gate_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.0.mlp.up_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.0.self_attn.k_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.0.self_attn.o_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.0.self_attn.q_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.0.self_attn.v_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.1.mlp.down_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.1.mlp.gate_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.1.mlp.up_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.1.self_attn.k_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.1.self_attn.o_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.1.self_attn.q_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.1.self_attn.v_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.10.mlp.down_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.10.mlp.gate_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.10.mlp.up_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.10.self_attn.k_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.10.self_attn.o_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.10.self_attn.q_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.10.self_attn.v_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.11.mlp.down_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.11.mlp.gate_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.11.mlp.up_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.11.self_attn.k_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.11.self_attn.o_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.11.self_attn.q_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.11.self_attn.v_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.12.mlp.down_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.12.mlp.gate_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.12.mlp.up_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.12.self_attn.k_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.12.self_attn.o_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.12.self_attn.q_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.12.self_attn.v_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.13.mlp.down_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.13.mlp.gate_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.13.mlp.up_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.13.self_attn.k_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.13.self_attn.o_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.13.self_attn.q_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.13.self_attn.v_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.14.mlp.down_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.14.mlp.gate_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.14.mlp.up_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.14.self_attn.k_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.14.self_attn.o_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.14.self_attn.q_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.14.self_attn.v_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.15.mlp.down_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.15.mlp.gate_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.15.mlp.up_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.15.self_attn.k_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.15.self_attn.o_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.15.self_attn.q_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.15.self_attn.v_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.16.mlp.down_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.16.mlp.gate_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.16.mlp.up_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.16.self_attn.k_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.16.self_attn.o_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.16.self_attn.q_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.16.self_attn.v_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.17.mlp.down_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.17.mlp.gate_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.17.mlp.up_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.17.self_attn.k_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.17.self_attn.o_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.17.self_attn.q_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.17.self_attn.v_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.18.mlp.down_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.18.mlp.gate_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.18.mlp.up_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.18.self_attn.k_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.18.self_attn.o_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.18.self_attn.q_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.18.self_attn.v_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.19.mlp.down_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.19.mlp.gate_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.19.mlp.up_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.19.self_attn.k_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.19.self_attn.o_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.19.self_attn.q_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.19.self_attn.v_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.2.mlp.down_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.2.mlp.gate_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.2.mlp.up_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.2.self_attn.k_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.2.self_attn.o_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.2.self_attn.q_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.2.self_attn.v_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.20.mlp.down_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.20.mlp.gate_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.20.mlp.up_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.20.self_attn.k_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.20.self_attn.o_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.20.self_attn.q_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.20.self_attn.v_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.21.mlp.down_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.21.mlp.gate_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.21.mlp.up_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.21.self_attn.k_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.21.self_attn.o_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.21.self_attn.q_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.21.self_attn.v_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.22.mlp.down_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.22.mlp.gate_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.22.mlp.up_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.22.self_attn.k_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.22.self_attn.o_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.22.self_attn.q_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.22.self_attn.v_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.23.mlp.down_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.23.mlp.gate_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.23.mlp.up_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.23.self_attn.k_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.23.self_attn.o_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.23.self_attn.q_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.23.self_attn.v_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.24.mlp.down_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.24.mlp.gate_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.24.mlp.up_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.24.self_attn.k_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.24.self_attn.o_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.24.self_attn.q_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.24.self_attn.v_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.25.mlp.down_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.25.mlp.gate_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.25.mlp.up_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.25.self_attn.k_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.25.self_attn.o_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.25.self_attn.q_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.25.self_attn.v_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.26.mlp.down_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.26.mlp.gate_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.26.mlp.up_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.26.self_attn.k_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.26.self_attn.o_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.26.self_attn.q_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.26.self_attn.v_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.27.mlp.down_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.27.mlp.gate_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.27.mlp.up_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.27.self_attn.k_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.27.self_attn.o_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.27.self_attn.q_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.27.self_attn.v_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.3.mlp.down_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.3.mlp.gate_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.3.mlp.up_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.3.self_attn.k_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.3.self_attn.o_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.3.self_attn.q_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.3.self_attn.v_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.4.mlp.down_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.4.mlp.gate_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.4.mlp.up_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.4.self_attn.k_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.4.self_attn.o_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.4.self_attn.q_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.4.self_attn.v_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.5.mlp.down_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.5.mlp.gate_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.5.mlp.up_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.5.self_attn.k_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.5.self_attn.o_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.5.self_attn.q_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.5.self_attn.v_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.6.mlp.down_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.6.mlp.gate_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.6.mlp.up_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.6.self_attn.k_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.6.self_attn.o_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.6.self_attn.q_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.6.self_attn.v_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.7.mlp.down_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.7.mlp.gate_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.7.mlp.up_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.7.self_attn.k_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.7.self_attn.o_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.7.self_attn.q_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.7.self_attn.v_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.8.mlp.down_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.8.mlp.gate_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.8.mlp.up_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.8.self_attn.k_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.8.self_attn.o_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.8.self_attn.q_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.8.self_attn.v_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.9.mlp.down_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.9.mlp.gate_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.9.mlp.up_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.9.self_attn.k_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.9.self_attn.o_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.9.self_attn.q_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.9.self_attn.v_proj", + "default_target": "q6k", + "resolved_target": "q6k", + "stored": "q6k", + "shape": [ + 1024, + 1024 + ] + } + ] + }, + { + "quant": "afq6", + "shards": [ + "afq6-0.uqff" + ], + "layers": 197, + "actual_counts": { + "afq6": 197 + }, + "fallback_count": 0, + "layer_details": [ + { + "module": "lm_head", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 151936, + 192 + ] + }, + { + "module": "model.layers.0.mlp.down_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 576 + ] + }, + { + "module": "model.layers.0.mlp.gate_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.0.mlp.up_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.0.self_attn.k_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.0.self_attn.o_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.0.self_attn.q_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 2048, + 192 + ] + }, + { + "module": "model.layers.0.self_attn.v_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.1.mlp.down_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 576 + ] + }, + { + "module": "model.layers.1.mlp.gate_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.1.mlp.up_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.1.self_attn.k_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.1.self_attn.o_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.1.self_attn.q_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 2048, + 192 + ] + }, + { + "module": "model.layers.1.self_attn.v_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.10.mlp.down_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 576 + ] + }, + { + "module": "model.layers.10.mlp.gate_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.10.mlp.up_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.10.self_attn.k_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.10.self_attn.o_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.10.self_attn.q_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 2048, + 192 + ] + }, + { + "module": "model.layers.10.self_attn.v_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.11.mlp.down_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 576 + ] + }, + { + "module": "model.layers.11.mlp.gate_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.11.mlp.up_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.11.self_attn.k_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.11.self_attn.o_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.11.self_attn.q_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 2048, + 192 + ] + }, + { + "module": "model.layers.11.self_attn.v_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.12.mlp.down_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 576 + ] + }, + { + "module": "model.layers.12.mlp.gate_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.12.mlp.up_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.12.self_attn.k_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.12.self_attn.o_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.12.self_attn.q_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 2048, + 192 + ] + }, + { + "module": "model.layers.12.self_attn.v_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.13.mlp.down_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 576 + ] + }, + { + "module": "model.layers.13.mlp.gate_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.13.mlp.up_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.13.self_attn.k_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.13.self_attn.o_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.13.self_attn.q_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 2048, + 192 + ] + }, + { + "module": "model.layers.13.self_attn.v_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.14.mlp.down_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 576 + ] + }, + { + "module": "model.layers.14.mlp.gate_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.14.mlp.up_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.14.self_attn.k_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.14.self_attn.o_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.14.self_attn.q_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 2048, + 192 + ] + }, + { + "module": "model.layers.14.self_attn.v_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.15.mlp.down_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 576 + ] + }, + { + "module": "model.layers.15.mlp.gate_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.15.mlp.up_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.15.self_attn.k_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.15.self_attn.o_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.15.self_attn.q_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 2048, + 192 + ] + }, + { + "module": "model.layers.15.self_attn.v_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.16.mlp.down_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 576 + ] + }, + { + "module": "model.layers.16.mlp.gate_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.16.mlp.up_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.16.self_attn.k_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.16.self_attn.o_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.16.self_attn.q_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 2048, + 192 + ] + }, + { + "module": "model.layers.16.self_attn.v_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.17.mlp.down_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 576 + ] + }, + { + "module": "model.layers.17.mlp.gate_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.17.mlp.up_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.17.self_attn.k_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.17.self_attn.o_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.17.self_attn.q_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 2048, + 192 + ] + }, + { + "module": "model.layers.17.self_attn.v_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.18.mlp.down_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 576 + ] + }, + { + "module": "model.layers.18.mlp.gate_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.18.mlp.up_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.18.self_attn.k_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.18.self_attn.o_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.18.self_attn.q_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 2048, + 192 + ] + }, + { + "module": "model.layers.18.self_attn.v_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.19.mlp.down_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 576 + ] + }, + { + "module": "model.layers.19.mlp.gate_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.19.mlp.up_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.19.self_attn.k_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.19.self_attn.o_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.19.self_attn.q_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 2048, + 192 + ] + }, + { + "module": "model.layers.19.self_attn.v_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.2.mlp.down_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 576 + ] + }, + { + "module": "model.layers.2.mlp.gate_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.2.mlp.up_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.2.self_attn.k_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.2.self_attn.o_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.2.self_attn.q_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 2048, + 192 + ] + }, + { + "module": "model.layers.2.self_attn.v_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.20.mlp.down_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 576 + ] + }, + { + "module": "model.layers.20.mlp.gate_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.20.mlp.up_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.20.self_attn.k_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.20.self_attn.o_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.20.self_attn.q_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 2048, + 192 + ] + }, + { + "module": "model.layers.20.self_attn.v_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.21.mlp.down_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 576 + ] + }, + { + "module": "model.layers.21.mlp.gate_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.21.mlp.up_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.21.self_attn.k_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.21.self_attn.o_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.21.self_attn.q_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 2048, + 192 + ] + }, + { + "module": "model.layers.21.self_attn.v_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.22.mlp.down_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 576 + ] + }, + { + "module": "model.layers.22.mlp.gate_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.22.mlp.up_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.22.self_attn.k_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.22.self_attn.o_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.22.self_attn.q_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 2048, + 192 + ] + }, + { + "module": "model.layers.22.self_attn.v_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.23.mlp.down_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 576 + ] + }, + { + "module": "model.layers.23.mlp.gate_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.23.mlp.up_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.23.self_attn.k_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.23.self_attn.o_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.23.self_attn.q_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 2048, + 192 + ] + }, + { + "module": "model.layers.23.self_attn.v_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.24.mlp.down_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 576 + ] + }, + { + "module": "model.layers.24.mlp.gate_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.24.mlp.up_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.24.self_attn.k_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.24.self_attn.o_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.24.self_attn.q_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 2048, + 192 + ] + }, + { + "module": "model.layers.24.self_attn.v_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.25.mlp.down_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 576 + ] + }, + { + "module": "model.layers.25.mlp.gate_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.25.mlp.up_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.25.self_attn.k_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.25.self_attn.o_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.25.self_attn.q_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 2048, + 192 + ] + }, + { + "module": "model.layers.25.self_attn.v_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.26.mlp.down_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 576 + ] + }, + { + "module": "model.layers.26.mlp.gate_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.26.mlp.up_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.26.self_attn.k_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.26.self_attn.o_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.26.self_attn.q_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 2048, + 192 + ] + }, + { + "module": "model.layers.26.self_attn.v_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.27.mlp.down_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 576 + ] + }, + { + "module": "model.layers.27.mlp.gate_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.27.mlp.up_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.27.self_attn.k_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.27.self_attn.o_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.27.self_attn.q_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 2048, + 192 + ] + }, + { + "module": "model.layers.27.self_attn.v_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.3.mlp.down_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 576 + ] + }, + { + "module": "model.layers.3.mlp.gate_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.3.mlp.up_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.3.self_attn.k_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.3.self_attn.o_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.3.self_attn.q_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 2048, + 192 + ] + }, + { + "module": "model.layers.3.self_attn.v_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.4.mlp.down_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 576 + ] + }, + { + "module": "model.layers.4.mlp.gate_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.4.mlp.up_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.4.self_attn.k_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.4.self_attn.o_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.4.self_attn.q_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 2048, + 192 + ] + }, + { + "module": "model.layers.4.self_attn.v_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.5.mlp.down_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 576 + ] + }, + { + "module": "model.layers.5.mlp.gate_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.5.mlp.up_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.5.self_attn.k_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.5.self_attn.o_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.5.self_attn.q_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 2048, + 192 + ] + }, + { + "module": "model.layers.5.self_attn.v_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.6.mlp.down_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 576 + ] + }, + { + "module": "model.layers.6.mlp.gate_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.6.mlp.up_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.6.self_attn.k_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.6.self_attn.o_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.6.self_attn.q_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 2048, + 192 + ] + }, + { + "module": "model.layers.6.self_attn.v_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.7.mlp.down_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 576 + ] + }, + { + "module": "model.layers.7.mlp.gate_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.7.mlp.up_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.7.self_attn.k_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.7.self_attn.o_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.7.self_attn.q_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 2048, + 192 + ] + }, + { + "module": "model.layers.7.self_attn.v_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.8.mlp.down_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 576 + ] + }, + { + "module": "model.layers.8.mlp.gate_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.8.mlp.up_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.8.self_attn.k_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.8.self_attn.o_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.8.self_attn.q_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 2048, + 192 + ] + }, + { + "module": "model.layers.8.self_attn.v_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.9.mlp.down_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 576 + ] + }, + { + "module": "model.layers.9.mlp.gate_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.9.mlp.up_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 3072, + 192 + ] + }, + { + "module": "model.layers.9.self_attn.k_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + }, + { + "module": "model.layers.9.self_attn.o_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 384 + ] + }, + { + "module": "model.layers.9.self_attn.q_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 2048, + 192 + ] + }, + { + "module": "model.layers.9.self_attn.v_proj", + "default_target": "afq6", + "resolved_target": "afq6", + "stored": "afq6", + "shape": [ + 1024, + 192 + ] + } + ] + }, + { + "quant": "q8_0", + "shards": [ + "q8_0-0.uqff" + ], + "layers": 197, + "actual_counts": { + "q8_0": 197 + }, + "fallback_count": 0, + "layer_details": [ + { + "module": "lm_head", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 151936, + 1024 + ] + }, + { + "module": "model.layers.0.mlp.down_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.0.mlp.gate_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.0.mlp.up_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.0.self_attn.k_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.0.self_attn.o_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.0.self_attn.q_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.0.self_attn.v_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.1.mlp.down_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.1.mlp.gate_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.1.mlp.up_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.1.self_attn.k_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.1.self_attn.o_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.1.self_attn.q_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.1.self_attn.v_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.10.mlp.down_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.10.mlp.gate_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.10.mlp.up_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.10.self_attn.k_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.10.self_attn.o_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.10.self_attn.q_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.10.self_attn.v_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.11.mlp.down_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.11.mlp.gate_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.11.mlp.up_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.11.self_attn.k_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.11.self_attn.o_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.11.self_attn.q_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.11.self_attn.v_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.12.mlp.down_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.12.mlp.gate_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.12.mlp.up_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.12.self_attn.k_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.12.self_attn.o_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.12.self_attn.q_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.12.self_attn.v_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.13.mlp.down_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.13.mlp.gate_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.13.mlp.up_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.13.self_attn.k_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.13.self_attn.o_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.13.self_attn.q_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.13.self_attn.v_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.14.mlp.down_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.14.mlp.gate_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.14.mlp.up_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.14.self_attn.k_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.14.self_attn.o_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.14.self_attn.q_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.14.self_attn.v_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.15.mlp.down_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.15.mlp.gate_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.15.mlp.up_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.15.self_attn.k_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.15.self_attn.o_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.15.self_attn.q_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.15.self_attn.v_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.16.mlp.down_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.16.mlp.gate_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.16.mlp.up_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.16.self_attn.k_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.16.self_attn.o_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.16.self_attn.q_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.16.self_attn.v_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.17.mlp.down_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.17.mlp.gate_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.17.mlp.up_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.17.self_attn.k_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.17.self_attn.o_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.17.self_attn.q_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.17.self_attn.v_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.18.mlp.down_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.18.mlp.gate_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.18.mlp.up_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.18.self_attn.k_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.18.self_attn.o_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.18.self_attn.q_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.18.self_attn.v_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.19.mlp.down_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.19.mlp.gate_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.19.mlp.up_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.19.self_attn.k_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.19.self_attn.o_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.19.self_attn.q_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.19.self_attn.v_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.2.mlp.down_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.2.mlp.gate_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.2.mlp.up_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.2.self_attn.k_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.2.self_attn.o_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.2.self_attn.q_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.2.self_attn.v_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.20.mlp.down_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.20.mlp.gate_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.20.mlp.up_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.20.self_attn.k_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.20.self_attn.o_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.20.self_attn.q_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.20.self_attn.v_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.21.mlp.down_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.21.mlp.gate_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.21.mlp.up_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.21.self_attn.k_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.21.self_attn.o_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.21.self_attn.q_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.21.self_attn.v_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.22.mlp.down_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.22.mlp.gate_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.22.mlp.up_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.22.self_attn.k_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.22.self_attn.o_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.22.self_attn.q_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.22.self_attn.v_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.23.mlp.down_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.23.mlp.gate_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.23.mlp.up_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.23.self_attn.k_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.23.self_attn.o_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.23.self_attn.q_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.23.self_attn.v_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.24.mlp.down_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.24.mlp.gate_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.24.mlp.up_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.24.self_attn.k_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.24.self_attn.o_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.24.self_attn.q_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.24.self_attn.v_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.25.mlp.down_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.25.mlp.gate_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.25.mlp.up_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.25.self_attn.k_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.25.self_attn.o_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.25.self_attn.q_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.25.self_attn.v_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.26.mlp.down_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.26.mlp.gate_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.26.mlp.up_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.26.self_attn.k_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.26.self_attn.o_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.26.self_attn.q_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.26.self_attn.v_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.27.mlp.down_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.27.mlp.gate_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.27.mlp.up_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.27.self_attn.k_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.27.self_attn.o_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.27.self_attn.q_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.27.self_attn.v_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.3.mlp.down_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.3.mlp.gate_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.3.mlp.up_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.3.self_attn.k_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.3.self_attn.o_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.3.self_attn.q_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.3.self_attn.v_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.4.mlp.down_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.4.mlp.gate_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.4.mlp.up_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.4.self_attn.k_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.4.self_attn.o_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.4.self_attn.q_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.4.self_attn.v_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.5.mlp.down_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.5.mlp.gate_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.5.mlp.up_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.5.self_attn.k_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.5.self_attn.o_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.5.self_attn.q_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.5.self_attn.v_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.6.mlp.down_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.6.mlp.gate_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.6.mlp.up_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.6.self_attn.k_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.6.self_attn.o_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.6.self_attn.q_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.6.self_attn.v_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.7.mlp.down_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.7.mlp.gate_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.7.mlp.up_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.7.self_attn.k_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.7.self_attn.o_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.7.self_attn.q_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.7.self_attn.v_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.8.mlp.down_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.8.mlp.gate_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.8.mlp.up_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.8.self_attn.k_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.8.self_attn.o_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.8.self_attn.q_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.8.self_attn.v_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.9.mlp.down_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.9.mlp.gate_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.9.mlp.up_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.9.self_attn.k_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.9.self_attn.o_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.9.self_attn.q_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.9.self_attn.v_proj", + "default_target": "q8_0", + "resolved_target": "q8_0", + "stored": "q8_0", + "shape": [ + 1024, + 1024 + ] + } + ] + }, + { + "quant": "afq8", + "shards": [ + "afq8-0.uqff" + ], + "layers": 197, + "actual_counts": { + "afq8": 197 + }, + "fallback_count": 0, + "layer_details": [ + { + "module": "lm_head", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 151936, + 256 + ] + }, + { + "module": "model.layers.0.mlp.down_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 768 + ] + }, + { + "module": "model.layers.0.mlp.gate_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.0.mlp.up_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.0.self_attn.k_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.0.self_attn.o_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 512 + ] + }, + { + "module": "model.layers.0.self_attn.q_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 2048, + 256 + ] + }, + { + "module": "model.layers.0.self_attn.v_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.1.mlp.down_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 768 + ] + }, + { + "module": "model.layers.1.mlp.gate_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.1.mlp.up_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.1.self_attn.k_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.1.self_attn.o_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 512 + ] + }, + { + "module": "model.layers.1.self_attn.q_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 2048, + 256 + ] + }, + { + "module": "model.layers.1.self_attn.v_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.10.mlp.down_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 768 + ] + }, + { + "module": "model.layers.10.mlp.gate_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.10.mlp.up_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.10.self_attn.k_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.10.self_attn.o_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 512 + ] + }, + { + "module": "model.layers.10.self_attn.q_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 2048, + 256 + ] + }, + { + "module": "model.layers.10.self_attn.v_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.11.mlp.down_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 768 + ] + }, + { + "module": "model.layers.11.mlp.gate_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.11.mlp.up_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.11.self_attn.k_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.11.self_attn.o_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 512 + ] + }, + { + "module": "model.layers.11.self_attn.q_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 2048, + 256 + ] + }, + { + "module": "model.layers.11.self_attn.v_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.12.mlp.down_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 768 + ] + }, + { + "module": "model.layers.12.mlp.gate_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.12.mlp.up_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.12.self_attn.k_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.12.self_attn.o_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 512 + ] + }, + { + "module": "model.layers.12.self_attn.q_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 2048, + 256 + ] + }, + { + "module": "model.layers.12.self_attn.v_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.13.mlp.down_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 768 + ] + }, + { + "module": "model.layers.13.mlp.gate_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.13.mlp.up_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.13.self_attn.k_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.13.self_attn.o_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 512 + ] + }, + { + "module": "model.layers.13.self_attn.q_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 2048, + 256 + ] + }, + { + "module": "model.layers.13.self_attn.v_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.14.mlp.down_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 768 + ] + }, + { + "module": "model.layers.14.mlp.gate_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.14.mlp.up_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.14.self_attn.k_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.14.self_attn.o_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 512 + ] + }, + { + "module": "model.layers.14.self_attn.q_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 2048, + 256 + ] + }, + { + "module": "model.layers.14.self_attn.v_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.15.mlp.down_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 768 + ] + }, + { + "module": "model.layers.15.mlp.gate_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.15.mlp.up_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.15.self_attn.k_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.15.self_attn.o_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 512 + ] + }, + { + "module": "model.layers.15.self_attn.q_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 2048, + 256 + ] + }, + { + "module": "model.layers.15.self_attn.v_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.16.mlp.down_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 768 + ] + }, + { + "module": "model.layers.16.mlp.gate_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.16.mlp.up_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.16.self_attn.k_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.16.self_attn.o_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 512 + ] + }, + { + "module": "model.layers.16.self_attn.q_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 2048, + 256 + ] + }, + { + "module": "model.layers.16.self_attn.v_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.17.mlp.down_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 768 + ] + }, + { + "module": "model.layers.17.mlp.gate_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.17.mlp.up_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.17.self_attn.k_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.17.self_attn.o_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 512 + ] + }, + { + "module": "model.layers.17.self_attn.q_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 2048, + 256 + ] + }, + { + "module": "model.layers.17.self_attn.v_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.18.mlp.down_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 768 + ] + }, + { + "module": "model.layers.18.mlp.gate_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.18.mlp.up_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.18.self_attn.k_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.18.self_attn.o_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 512 + ] + }, + { + "module": "model.layers.18.self_attn.q_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 2048, + 256 + ] + }, + { + "module": "model.layers.18.self_attn.v_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.19.mlp.down_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 768 + ] + }, + { + "module": "model.layers.19.mlp.gate_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.19.mlp.up_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.19.self_attn.k_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.19.self_attn.o_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 512 + ] + }, + { + "module": "model.layers.19.self_attn.q_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 2048, + 256 + ] + }, + { + "module": "model.layers.19.self_attn.v_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.2.mlp.down_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 768 + ] + }, + { + "module": "model.layers.2.mlp.gate_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.2.mlp.up_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.2.self_attn.k_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.2.self_attn.o_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 512 + ] + }, + { + "module": "model.layers.2.self_attn.q_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 2048, + 256 + ] + }, + { + "module": "model.layers.2.self_attn.v_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.20.mlp.down_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 768 + ] + }, + { + "module": "model.layers.20.mlp.gate_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.20.mlp.up_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.20.self_attn.k_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.20.self_attn.o_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 512 + ] + }, + { + "module": "model.layers.20.self_attn.q_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 2048, + 256 + ] + }, + { + "module": "model.layers.20.self_attn.v_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.21.mlp.down_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 768 + ] + }, + { + "module": "model.layers.21.mlp.gate_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.21.mlp.up_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.21.self_attn.k_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.21.self_attn.o_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 512 + ] + }, + { + "module": "model.layers.21.self_attn.q_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 2048, + 256 + ] + }, + { + "module": "model.layers.21.self_attn.v_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.22.mlp.down_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 768 + ] + }, + { + "module": "model.layers.22.mlp.gate_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.22.mlp.up_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.22.self_attn.k_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.22.self_attn.o_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 512 + ] + }, + { + "module": "model.layers.22.self_attn.q_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 2048, + 256 + ] + }, + { + "module": "model.layers.22.self_attn.v_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.23.mlp.down_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 768 + ] + }, + { + "module": "model.layers.23.mlp.gate_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.23.mlp.up_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.23.self_attn.k_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.23.self_attn.o_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 512 + ] + }, + { + "module": "model.layers.23.self_attn.q_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 2048, + 256 + ] + }, + { + "module": "model.layers.23.self_attn.v_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.24.mlp.down_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 768 + ] + }, + { + "module": "model.layers.24.mlp.gate_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.24.mlp.up_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.24.self_attn.k_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.24.self_attn.o_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 512 + ] + }, + { + "module": "model.layers.24.self_attn.q_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 2048, + 256 + ] + }, + { + "module": "model.layers.24.self_attn.v_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.25.mlp.down_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 768 + ] + }, + { + "module": "model.layers.25.mlp.gate_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.25.mlp.up_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.25.self_attn.k_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.25.self_attn.o_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 512 + ] + }, + { + "module": "model.layers.25.self_attn.q_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 2048, + 256 + ] + }, + { + "module": "model.layers.25.self_attn.v_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.26.mlp.down_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 768 + ] + }, + { + "module": "model.layers.26.mlp.gate_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.26.mlp.up_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.26.self_attn.k_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.26.self_attn.o_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 512 + ] + }, + { + "module": "model.layers.26.self_attn.q_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 2048, + 256 + ] + }, + { + "module": "model.layers.26.self_attn.v_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.27.mlp.down_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 768 + ] + }, + { + "module": "model.layers.27.mlp.gate_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.27.mlp.up_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.27.self_attn.k_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.27.self_attn.o_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 512 + ] + }, + { + "module": "model.layers.27.self_attn.q_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 2048, + 256 + ] + }, + { + "module": "model.layers.27.self_attn.v_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.3.mlp.down_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 768 + ] + }, + { + "module": "model.layers.3.mlp.gate_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.3.mlp.up_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.3.self_attn.k_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.3.self_attn.o_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 512 + ] + }, + { + "module": "model.layers.3.self_attn.q_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 2048, + 256 + ] + }, + { + "module": "model.layers.3.self_attn.v_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.4.mlp.down_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 768 + ] + }, + { + "module": "model.layers.4.mlp.gate_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.4.mlp.up_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.4.self_attn.k_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.4.self_attn.o_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 512 + ] + }, + { + "module": "model.layers.4.self_attn.q_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 2048, + 256 + ] + }, + { + "module": "model.layers.4.self_attn.v_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.5.mlp.down_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 768 + ] + }, + { + "module": "model.layers.5.mlp.gate_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.5.mlp.up_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.5.self_attn.k_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.5.self_attn.o_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 512 + ] + }, + { + "module": "model.layers.5.self_attn.q_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 2048, + 256 + ] + }, + { + "module": "model.layers.5.self_attn.v_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.6.mlp.down_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 768 + ] + }, + { + "module": "model.layers.6.mlp.gate_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.6.mlp.up_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.6.self_attn.k_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.6.self_attn.o_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 512 + ] + }, + { + "module": "model.layers.6.self_attn.q_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 2048, + 256 + ] + }, + { + "module": "model.layers.6.self_attn.v_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.7.mlp.down_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 768 + ] + }, + { + "module": "model.layers.7.mlp.gate_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.7.mlp.up_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.7.self_attn.k_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.7.self_attn.o_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 512 + ] + }, + { + "module": "model.layers.7.self_attn.q_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 2048, + 256 + ] + }, + { + "module": "model.layers.7.self_attn.v_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.8.mlp.down_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 768 + ] + }, + { + "module": "model.layers.8.mlp.gate_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.8.mlp.up_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.8.self_attn.k_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.8.self_attn.o_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 512 + ] + }, + { + "module": "model.layers.8.self_attn.q_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 2048, + 256 + ] + }, + { + "module": "model.layers.8.self_attn.v_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.9.mlp.down_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 768 + ] + }, + { + "module": "model.layers.9.mlp.gate_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.9.mlp.up_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 3072, + 256 + ] + }, + { + "module": "model.layers.9.self_attn.k_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + }, + { + "module": "model.layers.9.self_attn.o_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 512 + ] + }, + { + "module": "model.layers.9.self_attn.q_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 2048, + 256 + ] + }, + { + "module": "model.layers.9.self_attn.v_proj", + "default_target": "afq8", + "resolved_target": "afq8", + "stored": "afq8", + "shape": [ + 1024, + 256 + ] + } + ] + }, + { + "quant": "q2k", + "shards": [ + "q2k-0.uqff" + ], + "layers": 197, + "actual_counts": { + "q2k": 197 + }, + "fallback_count": 0, + "layer_details": [ + { + "module": "lm_head", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 151936, + 1024 + ] + }, + { + "module": "model.layers.0.mlp.down_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.0.mlp.gate_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.0.mlp.up_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.0.self_attn.k_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.0.self_attn.o_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.0.self_attn.q_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.0.self_attn.v_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.1.mlp.down_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.1.mlp.gate_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.1.mlp.up_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.1.self_attn.k_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.1.self_attn.o_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.1.self_attn.q_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.1.self_attn.v_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.10.mlp.down_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.10.mlp.gate_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.10.mlp.up_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.10.self_attn.k_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.10.self_attn.o_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.10.self_attn.q_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.10.self_attn.v_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.11.mlp.down_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.11.mlp.gate_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.11.mlp.up_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.11.self_attn.k_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.11.self_attn.o_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.11.self_attn.q_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.11.self_attn.v_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.12.mlp.down_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.12.mlp.gate_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.12.mlp.up_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.12.self_attn.k_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.12.self_attn.o_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.12.self_attn.q_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.12.self_attn.v_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.13.mlp.down_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.13.mlp.gate_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.13.mlp.up_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.13.self_attn.k_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.13.self_attn.o_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.13.self_attn.q_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.13.self_attn.v_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.14.mlp.down_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.14.mlp.gate_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.14.mlp.up_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.14.self_attn.k_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.14.self_attn.o_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.14.self_attn.q_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.14.self_attn.v_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.15.mlp.down_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.15.mlp.gate_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.15.mlp.up_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.15.self_attn.k_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.15.self_attn.o_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.15.self_attn.q_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.15.self_attn.v_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.16.mlp.down_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.16.mlp.gate_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.16.mlp.up_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.16.self_attn.k_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.16.self_attn.o_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.16.self_attn.q_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.16.self_attn.v_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.17.mlp.down_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.17.mlp.gate_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.17.mlp.up_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.17.self_attn.k_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.17.self_attn.o_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.17.self_attn.q_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.17.self_attn.v_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.18.mlp.down_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.18.mlp.gate_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.18.mlp.up_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.18.self_attn.k_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.18.self_attn.o_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.18.self_attn.q_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.18.self_attn.v_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.19.mlp.down_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.19.mlp.gate_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.19.mlp.up_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.19.self_attn.k_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.19.self_attn.o_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.19.self_attn.q_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.19.self_attn.v_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.2.mlp.down_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.2.mlp.gate_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.2.mlp.up_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.2.self_attn.k_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.2.self_attn.o_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.2.self_attn.q_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.2.self_attn.v_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.20.mlp.down_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.20.mlp.gate_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.20.mlp.up_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.20.self_attn.k_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.20.self_attn.o_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.20.self_attn.q_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.20.self_attn.v_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.21.mlp.down_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.21.mlp.gate_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.21.mlp.up_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.21.self_attn.k_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.21.self_attn.o_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.21.self_attn.q_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.21.self_attn.v_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.22.mlp.down_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.22.mlp.gate_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.22.mlp.up_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.22.self_attn.k_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.22.self_attn.o_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.22.self_attn.q_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.22.self_attn.v_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.23.mlp.down_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.23.mlp.gate_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.23.mlp.up_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.23.self_attn.k_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.23.self_attn.o_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.23.self_attn.q_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.23.self_attn.v_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.24.mlp.down_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.24.mlp.gate_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.24.mlp.up_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.24.self_attn.k_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.24.self_attn.o_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.24.self_attn.q_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.24.self_attn.v_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.25.mlp.down_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.25.mlp.gate_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.25.mlp.up_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.25.self_attn.k_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.25.self_attn.o_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.25.self_attn.q_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.25.self_attn.v_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.26.mlp.down_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.26.mlp.gate_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.26.mlp.up_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.26.self_attn.k_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.26.self_attn.o_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.26.self_attn.q_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.26.self_attn.v_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.27.mlp.down_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.27.mlp.gate_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.27.mlp.up_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.27.self_attn.k_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.27.self_attn.o_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.27.self_attn.q_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.27.self_attn.v_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.3.mlp.down_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.3.mlp.gate_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.3.mlp.up_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.3.self_attn.k_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.3.self_attn.o_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.3.self_attn.q_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.3.self_attn.v_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.4.mlp.down_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.4.mlp.gate_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.4.mlp.up_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.4.self_attn.k_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.4.self_attn.o_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.4.self_attn.q_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.4.self_attn.v_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.5.mlp.down_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.5.mlp.gate_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.5.mlp.up_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.5.self_attn.k_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.5.self_attn.o_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.5.self_attn.q_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.5.self_attn.v_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.6.mlp.down_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.6.mlp.gate_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.6.mlp.up_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.6.self_attn.k_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.6.self_attn.o_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.6.self_attn.q_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.6.self_attn.v_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.7.mlp.down_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.7.mlp.gate_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.7.mlp.up_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.7.self_attn.k_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.7.self_attn.o_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.7.self_attn.q_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.7.self_attn.v_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.8.mlp.down_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.8.mlp.gate_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.8.mlp.up_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.8.self_attn.k_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.8.self_attn.o_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.8.self_attn.q_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.8.self_attn.v_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.9.mlp.down_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 3072 + ] + }, + { + "module": "model.layers.9.mlp.gate_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.9.mlp.up_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 3072, + 1024 + ] + }, + { + "module": "model.layers.9.self_attn.k_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + }, + { + "module": "model.layers.9.self_attn.o_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 2048 + ] + }, + { + "module": "model.layers.9.self_attn.q_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 2048, + 1024 + ] + }, + { + "module": "model.layers.9.self_attn.v_proj", + "default_target": "q2k", + "resolved_target": "q2k", + "stored": "q2k", + "shape": [ + 1024, + 1024 + ] + } + ] + } + ] +} \ No newline at end of file