diff --git "a/config.json" "b/config.json"
new file mode 100644--- /dev/null
+++ "b/config.json"
@@ -0,0 +1,4235 @@
+{
+    "architectures": [
+        "Qwen3_5MoeForConditionalGeneration"
+    ],
+    "bos_token_id": null,
+    "do_sample": true,
+    "dtype": "bfloat16",
+    "eos_token_id": [
+        248046,
+        248044
+    ],
+    "generation_config": {
+        "bos_token_id": 248044,
+        "do_sample": true,
+        "eos_token_id": [
+            248046,
+            248044
+        ],
+        "pad_token_id": 248044,
+        "temperature": 1.0,
+        "top_k": 20,
+        "top_p": 0.95,
+        "transformers_version": "5.8.1"
+    },
+    "hidden_size": 2048,
+    "image_token_id": 248056,
+    "model_type": "qwen3_5_moe",
+    "pad_token_id": 248044,
+    "quantization": {
+        "group_size": 32,
+        "bits": 4,
+        "mode": "affine",
+        "language_model.model.embed_tokens": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.linear_attn.in_proj_z": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.linear_attn.in_proj_z": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.self_attn.q_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.self_attn.k_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.self_attn.v_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.self_attn.o_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.linear_attn.in_proj_qkv": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.self_attn.q_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.self_attn.k_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.self_attn.v_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.self_attn.o_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.self_attn.q_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.self_attn.k_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.self_attn.v_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.self_attn.o_proj": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.linear_attn.in_proj_qkv": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.self_attn.q_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.self_attn.k_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.self_attn.v_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.self_attn.o_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.linear_attn.out_proj": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.linear_attn.out_proj": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.linear_attn.in_proj_z": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.self_attn.q_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.self_attn.k_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.self_attn.v_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.self_attn.o_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.linear_attn.out_proj": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.linear_attn.out_proj": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.linear_attn.in_proj_z": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.self_attn.q_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.self_attn.k_proj": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.self_attn.v_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.self_attn.o_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.linear_attn.in_proj_z": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.linear_attn.in_proj_z": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.linear_attn.in_proj_z": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.self_attn.q_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.self_attn.k_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.self_attn.v_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.self_attn.o_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.linear_attn.in_proj_z": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.linear_attn.in_proj_z": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.linear_attn.in_proj_z": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.self_attn.q_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.self_attn.k_proj": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.self_attn.v_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.self_attn.o_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.32.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.32.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.32.linear_attn.in_proj_b": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.32.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.32.linear_attn.out_proj": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.32.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.32.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.32.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.32.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.32.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.32.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.32.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.32.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.33.linear_attn.in_proj_qkv": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.33.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.33.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.33.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.33.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.33.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.33.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.33.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.33.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.33.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.33.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.33.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.33.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.34.linear_attn.in_proj_qkv": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.34.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.34.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.34.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.34.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.34.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.34.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.34.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.34.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.34.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.34.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.34.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.34.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.35.self_attn.q_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.35.self_attn.k_proj": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.35.self_attn.v_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.35.self_attn.o_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.35.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.35.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.35.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.35.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.35.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.35.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.35.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.35.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.36.linear_attn.in_proj_qkv": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.36.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.36.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.36.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.36.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.36.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.36.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.36.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.36.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.36.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.36.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.36.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.36.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.37.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.37.linear_attn.in_proj_z": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.37.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.37.linear_attn.in_proj_a": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.37.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.37.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.37.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.37.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.37.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.37.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.37.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.37.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.37.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.38.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.38.linear_attn.in_proj_z": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.38.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.38.linear_attn.in_proj_a": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.38.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.38.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.38.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.38.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.38.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.38.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.38.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.38.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.38.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.39.self_attn.q_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.39.self_attn.k_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.39.self_attn.v_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.39.self_attn.o_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.39.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.39.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.39.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.39.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.39.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.39.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.39.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.39.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.lm_head": {
+            "bits": 8,
+            "group_size": 32
+        }
+    },
+    "quantization_config": {
+        "group_size": 32,
+        "bits": 4,
+        "mode": "affine",
+        "language_model.model.embed_tokens": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.linear_attn.in_proj_z": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.linear_attn.in_proj_z": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.self_attn.q_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.self_attn.k_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.self_attn.v_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.self_attn.o_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.linear_attn.in_proj_qkv": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.self_attn.q_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.self_attn.k_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.self_attn.v_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.self_attn.o_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.self_attn.q_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.self_attn.k_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.self_attn.v_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.self_attn.o_proj": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.linear_attn.in_proj_qkv": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.self_attn.q_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.self_attn.k_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.self_attn.v_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.self_attn.o_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.linear_attn.out_proj": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.linear_attn.out_proj": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.linear_attn.in_proj_z": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.self_attn.q_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.self_attn.k_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.self_attn.v_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.self_attn.o_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.linear_attn.out_proj": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.linear_attn.out_proj": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.linear_attn.in_proj_z": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.self_attn.q_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.self_attn.k_proj": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.self_attn.v_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.self_attn.o_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.linear_attn.in_proj_z": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.linear_attn.in_proj_z": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.linear_attn.in_proj_z": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.self_attn.q_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.self_attn.k_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.self_attn.v_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.self_attn.o_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.linear_attn.in_proj_z": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.linear_attn.in_proj_z": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.linear_attn.in_proj_z": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.self_attn.q_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.self_attn.k_proj": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.self_attn.v_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.self_attn.o_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.32.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.32.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.32.linear_attn.in_proj_b": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.32.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.32.linear_attn.out_proj": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.32.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.32.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.32.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.32.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.32.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.32.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.32.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.32.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.33.linear_attn.in_proj_qkv": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.33.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.33.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.33.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.33.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.33.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.33.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.33.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.33.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.33.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.33.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.33.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.33.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.34.linear_attn.in_proj_qkv": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.34.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.34.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.34.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.34.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.34.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.34.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.34.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.34.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.34.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.34.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.34.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.34.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.35.self_attn.q_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.35.self_attn.k_proj": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.35.self_attn.v_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.35.self_attn.o_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.35.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.35.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.35.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.35.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.35.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.35.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.35.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.35.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.36.linear_attn.in_proj_qkv": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.36.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.36.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.36.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.36.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.36.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.36.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.36.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.36.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.36.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.36.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.36.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.36.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.37.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.37.linear_attn.in_proj_z": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.37.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.37.linear_attn.in_proj_a": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.37.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.37.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.37.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.37.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.37.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.37.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.37.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.37.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.37.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.38.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.38.linear_attn.in_proj_z": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.38.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.38.linear_attn.in_proj_a": {
+            "bits": 6,
+            "group_size": 32
+        },
+        "language_model.model.layers.38.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.38.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.38.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.38.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.38.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.38.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.38.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.38.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.38.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.39.self_attn.q_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.39.self_attn.k_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.39.self_attn.v_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.39.self_attn.o_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.39.mlp.gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.39.mlp.switch_mlp.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.39.mlp.switch_mlp.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.39.mlp.switch_mlp.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.39.mlp.shared_expert.gate_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.39.mlp.shared_expert.down_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.39.mlp.shared_expert.up_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.39.mlp.shared_expert_gate": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.lm_head": {
+            "bits": 8,
+            "group_size": 32
+        }
+    },
+    "temperature": 1.0,
+    "text_config": {
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "attn_output_gate": true,
+        "bos_token_id": 248044,
+        "dtype": "bfloat16",
+        "eos_token_id": 248044,
+        "full_attention_interval": 4,
+        "head_dim": 256,
+        "hidden_act": "silu",
+        "hidden_size": 2048,
+        "initializer_range": 0.02,
+        "layer_types": [
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention"
+        ],
+        "linear_conv_kernel_dim": 4,
+        "linear_key_head_dim": 128,
+        "linear_num_key_heads": 16,
+        "linear_num_value_heads": 32,
+        "linear_value_head_dim": 128,
+        "mamba_ssm_dtype": "float32",
+        "max_position_embeddings": 262144,
+        "model_type": "qwen3_5_moe_text",
+        "moe_intermediate_size": 512,
+        "mtp_num_hidden_layers": 1,
+        "mtp_use_dedicated_embeddings": false,
+        "num_attention_heads": 16,
+        "num_experts": 256,
+        "num_experts_per_tok": 8,
+        "num_hidden_layers": 40,
+        "num_key_value_heads": 2,
+        "output_router_logits": false,
+        "pad_token_id": 248044,
+        "partial_rotary_factor": 0.25,
+        "rms_norm_eps": 1e-06,
+        "rope_parameters": {
+            "mrope_interleaved": true,
+            "mrope_section": [
+                11,
+                11,
+                10
+            ],
+            "partial_rotary_factor": 0.25,
+            "rope_theta": 10000000,
+            "type": "default"
+        },
+        "router_aux_loss_coef": 0.0,
+        "shared_expert_intermediate_size": 512,
+        "tie_word_embeddings": false,
+        "use_cache": false,
+        "vocab_size": 248320
+    },
+    "tie_word_embeddings": false,
+    "top_k": 20,
+    "top_p": 0.95,
+    "transformers_version": "5.8.1",
+    "use_cache": false,
+    "video_token_id": 248057,
+    "vision_end_token_id": 248054,
+    "vision_start_token_id": 248053
+}
\ No newline at end of file