| { |
| "metadata": { |
| "total_size": 114505943040 |
| }, |
| "weight_map": { |
| "language_model.lm_head.biases": "model-00023-of-00023.safetensors", |
| "language_model.lm_head.scales": "model-00023-of-00023.safetensors", |
| "language_model.lm_head.weight": "model-00023-of-00023.safetensors", |
| "language_model.model.embed_tokens.biases": "model-00001-of-00023.safetensors", |
| "language_model.model.embed_tokens.scales": "model-00001-of-00023.safetensors", |
| "language_model.model.embed_tokens.weight": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.0.feed_forward.experts.down_proj.biases": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.0.feed_forward.experts.down_proj.scales": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.0.feed_forward.experts.down_proj.weight": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.0.feed_forward.experts.gate_proj.biases": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.0.feed_forward.experts.gate_proj.scales": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.0.feed_forward.experts.gate_proj.weight": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.0.feed_forward.experts.up_proj.biases": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.0.feed_forward.experts.up_proj.scales": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.0.feed_forward.experts.up_proj.weight": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.0.feed_forward.router.biases": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.0.feed_forward.router.scales": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.0.feed_forward.router.weight": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.0.feed_forward.shared_expert.down_proj.biases": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.0.feed_forward.shared_expert.down_proj.scales": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.0.feed_forward.shared_expert.down_proj.weight": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.0.feed_forward.shared_expert.gate_proj.biases": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.0.feed_forward.shared_expert.gate_proj.scales": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.0.feed_forward.shared_expert.gate_proj.weight": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.0.feed_forward.shared_expert.up_proj.biases": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.0.feed_forward.shared_expert.up_proj.scales": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.0.feed_forward.shared_expert.up_proj.weight": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.0.self_attn.k_proj.biases": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.0.self_attn.k_proj.scales": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.0.self_attn.o_proj.biases": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.0.self_attn.o_proj.scales": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.0.self_attn.q_proj.biases": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.0.self_attn.q_proj.scales": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.0.self_attn.v_proj.biases": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.0.self_attn.v_proj.scales": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.1.feed_forward.experts.down_proj.biases": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.1.feed_forward.experts.down_proj.scales": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.1.feed_forward.experts.down_proj.weight": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.1.feed_forward.experts.gate_proj.biases": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.1.feed_forward.experts.gate_proj.scales": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.1.feed_forward.experts.gate_proj.weight": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.1.feed_forward.experts.up_proj.biases": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.1.feed_forward.experts.up_proj.scales": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.1.feed_forward.experts.up_proj.weight": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.1.feed_forward.router.biases": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.1.feed_forward.router.scales": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.1.feed_forward.router.weight": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.1.feed_forward.shared_expert.down_proj.biases": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.1.feed_forward.shared_expert.down_proj.scales": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.1.feed_forward.shared_expert.down_proj.weight": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.1.feed_forward.shared_expert.gate_proj.biases": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.1.feed_forward.shared_expert.gate_proj.scales": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.1.feed_forward.shared_expert.gate_proj.weight": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.1.feed_forward.shared_expert.up_proj.biases": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.1.feed_forward.shared_expert.up_proj.scales": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.1.feed_forward.shared_expert.up_proj.weight": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.1.input_layernorm.weight": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.1.post_attention_layernorm.weight": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.1.self_attn.k_proj.biases": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.1.self_attn.k_proj.scales": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.1.self_attn.o_proj.biases": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.1.self_attn.o_proj.scales": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.1.self_attn.q_proj.biases": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.1.self_attn.q_proj.scales": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.1.self_attn.v_proj.biases": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.1.self_attn.v_proj.scales": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00023.safetensors", |
| "language_model.model.layers.10.feed_forward.experts.down_proj.biases": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.10.feed_forward.experts.down_proj.scales": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.10.feed_forward.experts.down_proj.weight": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.10.feed_forward.experts.gate_proj.biases": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.10.feed_forward.experts.gate_proj.scales": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.10.feed_forward.experts.gate_proj.weight": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.10.feed_forward.experts.up_proj.biases": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.10.feed_forward.experts.up_proj.scales": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.10.feed_forward.experts.up_proj.weight": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.10.feed_forward.router.biases": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.10.feed_forward.router.scales": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.10.feed_forward.router.weight": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.10.feed_forward.shared_expert.down_proj.biases": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.10.feed_forward.shared_expert.down_proj.scales": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.10.feed_forward.shared_expert.down_proj.weight": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.10.feed_forward.shared_expert.gate_proj.biases": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.10.feed_forward.shared_expert.gate_proj.scales": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.10.feed_forward.shared_expert.gate_proj.weight": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.10.feed_forward.shared_expert.up_proj.biases": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.10.feed_forward.shared_expert.up_proj.scales": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.10.feed_forward.shared_expert.up_proj.weight": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.10.input_layernorm.weight": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.10.post_attention_layernorm.weight": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.10.self_attn.k_proj.biases": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.10.self_attn.k_proj.scales": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.10.self_attn.k_proj.weight": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.10.self_attn.o_proj.biases": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.10.self_attn.o_proj.scales": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.10.self_attn.o_proj.weight": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.10.self_attn.q_proj.biases": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.10.self_attn.q_proj.scales": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.10.self_attn.q_proj.weight": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.10.self_attn.v_proj.biases": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.10.self_attn.v_proj.scales": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.10.self_attn.v_proj.weight": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.11.feed_forward.experts.down_proj.biases": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.11.feed_forward.experts.down_proj.scales": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.11.feed_forward.experts.down_proj.weight": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.11.feed_forward.experts.gate_proj.biases": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.11.feed_forward.experts.gate_proj.scales": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.11.feed_forward.experts.gate_proj.weight": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.11.feed_forward.experts.up_proj.biases": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.11.feed_forward.experts.up_proj.scales": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.11.feed_forward.experts.up_proj.weight": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.11.feed_forward.router.biases": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.11.feed_forward.router.scales": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.11.feed_forward.router.weight": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.11.feed_forward.shared_expert.down_proj.biases": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.11.feed_forward.shared_expert.down_proj.scales": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.11.feed_forward.shared_expert.down_proj.weight": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.11.feed_forward.shared_expert.gate_proj.biases": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.11.feed_forward.shared_expert.gate_proj.scales": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.11.feed_forward.shared_expert.gate_proj.weight": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.11.feed_forward.shared_expert.up_proj.biases": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.11.feed_forward.shared_expert.up_proj.scales": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.11.feed_forward.shared_expert.up_proj.weight": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.11.input_layernorm.weight": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.11.post_attention_layernorm.weight": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.11.self_attn.k_proj.biases": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.11.self_attn.k_proj.scales": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.11.self_attn.k_proj.weight": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.11.self_attn.o_proj.biases": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.11.self_attn.o_proj.scales": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.11.self_attn.o_proj.weight": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.11.self_attn.q_proj.biases": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.11.self_attn.q_proj.scales": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.11.self_attn.q_proj.weight": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.11.self_attn.v_proj.biases": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.11.self_attn.v_proj.scales": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.11.self_attn.v_proj.weight": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.12.feed_forward.experts.down_proj.biases": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.12.feed_forward.experts.down_proj.scales": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.12.feed_forward.experts.down_proj.weight": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.12.feed_forward.experts.gate_proj.biases": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.12.feed_forward.experts.gate_proj.scales": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.12.feed_forward.experts.gate_proj.weight": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.12.feed_forward.experts.up_proj.biases": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.12.feed_forward.experts.up_proj.scales": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.12.feed_forward.experts.up_proj.weight": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.12.feed_forward.router.biases": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.12.feed_forward.router.scales": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.12.feed_forward.router.weight": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.12.feed_forward.shared_expert.down_proj.biases": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.12.feed_forward.shared_expert.down_proj.scales": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.12.feed_forward.shared_expert.down_proj.weight": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.12.feed_forward.shared_expert.gate_proj.biases": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.12.feed_forward.shared_expert.gate_proj.scales": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.12.feed_forward.shared_expert.gate_proj.weight": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.12.feed_forward.shared_expert.up_proj.biases": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.12.feed_forward.shared_expert.up_proj.scales": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.12.feed_forward.shared_expert.up_proj.weight": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.12.input_layernorm.weight": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.12.post_attention_layernorm.weight": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.12.self_attn.k_proj.biases": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.12.self_attn.k_proj.scales": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.12.self_attn.k_proj.weight": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.12.self_attn.o_proj.biases": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.12.self_attn.o_proj.scales": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.12.self_attn.o_proj.weight": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.12.self_attn.q_proj.biases": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.12.self_attn.q_proj.scales": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.12.self_attn.q_proj.weight": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.12.self_attn.v_proj.biases": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.12.self_attn.v_proj.scales": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.12.self_attn.v_proj.weight": "model-00006-of-00023.safetensors", |
| "language_model.model.layers.13.feed_forward.experts.down_proj.biases": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.13.feed_forward.experts.down_proj.scales": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.13.feed_forward.experts.down_proj.weight": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.13.feed_forward.experts.gate_proj.biases": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.13.feed_forward.experts.gate_proj.scales": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.13.feed_forward.experts.gate_proj.weight": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.13.feed_forward.experts.up_proj.biases": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.13.feed_forward.experts.up_proj.scales": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.13.feed_forward.experts.up_proj.weight": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.13.feed_forward.router.biases": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.13.feed_forward.router.scales": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.13.feed_forward.router.weight": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.13.feed_forward.shared_expert.down_proj.biases": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.13.feed_forward.shared_expert.down_proj.scales": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.13.feed_forward.shared_expert.down_proj.weight": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.13.feed_forward.shared_expert.gate_proj.biases": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.13.feed_forward.shared_expert.gate_proj.scales": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.13.feed_forward.shared_expert.gate_proj.weight": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.13.feed_forward.shared_expert.up_proj.biases": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.13.feed_forward.shared_expert.up_proj.scales": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.13.feed_forward.shared_expert.up_proj.weight": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.13.input_layernorm.weight": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.13.post_attention_layernorm.weight": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.13.self_attn.k_proj.biases": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.13.self_attn.k_proj.scales": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.13.self_attn.k_proj.weight": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.13.self_attn.o_proj.biases": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.13.self_attn.o_proj.scales": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.13.self_attn.o_proj.weight": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.13.self_attn.q_proj.biases": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.13.self_attn.q_proj.scales": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.13.self_attn.q_proj.weight": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.13.self_attn.v_proj.biases": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.13.self_attn.v_proj.scales": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.13.self_attn.v_proj.weight": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.14.feed_forward.experts.down_proj.biases": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.14.feed_forward.experts.down_proj.scales": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.14.feed_forward.experts.down_proj.weight": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.14.feed_forward.experts.gate_proj.biases": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.14.feed_forward.experts.gate_proj.scales": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.14.feed_forward.experts.gate_proj.weight": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.14.feed_forward.experts.up_proj.biases": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.14.feed_forward.experts.up_proj.scales": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.14.feed_forward.experts.up_proj.weight": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.14.feed_forward.router.biases": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.14.feed_forward.router.scales": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.14.feed_forward.router.weight": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.14.feed_forward.shared_expert.down_proj.biases": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.14.feed_forward.shared_expert.down_proj.scales": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.14.feed_forward.shared_expert.down_proj.weight": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.14.feed_forward.shared_expert.gate_proj.biases": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.14.feed_forward.shared_expert.gate_proj.scales": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.14.feed_forward.shared_expert.gate_proj.weight": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.14.feed_forward.shared_expert.up_proj.biases": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.14.feed_forward.shared_expert.up_proj.scales": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.14.feed_forward.shared_expert.up_proj.weight": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.14.input_layernorm.weight": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.14.post_attention_layernorm.weight": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.14.self_attn.k_proj.biases": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.14.self_attn.k_proj.scales": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.14.self_attn.k_proj.weight": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.14.self_attn.o_proj.biases": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.14.self_attn.o_proj.scales": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.14.self_attn.o_proj.weight": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.14.self_attn.q_proj.biases": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.14.self_attn.q_proj.scales": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.14.self_attn.q_proj.weight": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.14.self_attn.v_proj.biases": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.14.self_attn.v_proj.scales": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.14.self_attn.v_proj.weight": "model-00007-of-00023.safetensors", |
| "language_model.model.layers.15.feed_forward.experts.down_proj.biases": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.15.feed_forward.experts.down_proj.scales": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.15.feed_forward.experts.down_proj.weight": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.15.feed_forward.experts.gate_proj.biases": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.15.feed_forward.experts.gate_proj.scales": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.15.feed_forward.experts.gate_proj.weight": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.15.feed_forward.experts.up_proj.biases": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.15.feed_forward.experts.up_proj.scales": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.15.feed_forward.experts.up_proj.weight": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.15.feed_forward.router.biases": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.15.feed_forward.router.scales": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.15.feed_forward.router.weight": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.15.feed_forward.shared_expert.down_proj.biases": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.15.feed_forward.shared_expert.down_proj.scales": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.15.feed_forward.shared_expert.down_proj.weight": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.15.feed_forward.shared_expert.gate_proj.biases": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.15.feed_forward.shared_expert.gate_proj.scales": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.15.feed_forward.shared_expert.gate_proj.weight": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.15.feed_forward.shared_expert.up_proj.biases": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.15.feed_forward.shared_expert.up_proj.scales": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.15.feed_forward.shared_expert.up_proj.weight": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.15.input_layernorm.weight": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.15.post_attention_layernorm.weight": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.15.self_attn.k_proj.biases": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.15.self_attn.k_proj.scales": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.15.self_attn.k_proj.weight": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.15.self_attn.o_proj.biases": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.15.self_attn.o_proj.scales": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.15.self_attn.o_proj.weight": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.15.self_attn.q_proj.biases": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.15.self_attn.q_proj.scales": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.15.self_attn.q_proj.weight": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.15.self_attn.v_proj.biases": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.15.self_attn.v_proj.scales": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.15.self_attn.v_proj.weight": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.16.feed_forward.experts.down_proj.biases": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.16.feed_forward.experts.down_proj.scales": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.16.feed_forward.experts.down_proj.weight": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.16.feed_forward.experts.gate_proj.biases": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.16.feed_forward.experts.gate_proj.scales": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.16.feed_forward.experts.gate_proj.weight": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.16.feed_forward.experts.up_proj.biases": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.16.feed_forward.experts.up_proj.scales": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.16.feed_forward.experts.up_proj.weight": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.16.feed_forward.router.biases": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.16.feed_forward.router.scales": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.16.feed_forward.router.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.16.feed_forward.shared_expert.down_proj.biases": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.16.feed_forward.shared_expert.down_proj.scales": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.16.feed_forward.shared_expert.down_proj.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.16.feed_forward.shared_expert.gate_proj.biases": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.16.feed_forward.shared_expert.gate_proj.scales": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.16.feed_forward.shared_expert.gate_proj.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.16.feed_forward.shared_expert.up_proj.biases": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.16.feed_forward.shared_expert.up_proj.scales": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.16.feed_forward.shared_expert.up_proj.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.16.input_layernorm.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.16.post_attention_layernorm.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.16.self_attn.k_proj.biases": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.16.self_attn.k_proj.scales": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.16.self_attn.k_proj.weight": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.16.self_attn.o_proj.biases": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.16.self_attn.o_proj.scales": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.16.self_attn.o_proj.weight": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.16.self_attn.q_proj.biases": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.16.self_attn.q_proj.scales": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.16.self_attn.q_proj.weight": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.16.self_attn.v_proj.biases": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.16.self_attn.v_proj.scales": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.16.self_attn.v_proj.weight": "model-00008-of-00023.safetensors", |
| "language_model.model.layers.17.feed_forward.experts.down_proj.biases": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.17.feed_forward.experts.down_proj.scales": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.17.feed_forward.experts.down_proj.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.17.feed_forward.experts.gate_proj.biases": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.17.feed_forward.experts.gate_proj.scales": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.17.feed_forward.experts.gate_proj.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.17.feed_forward.experts.up_proj.biases": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.17.feed_forward.experts.up_proj.scales": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.17.feed_forward.experts.up_proj.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.17.feed_forward.router.biases": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.17.feed_forward.router.scales": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.17.feed_forward.router.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.17.feed_forward.shared_expert.down_proj.biases": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.17.feed_forward.shared_expert.down_proj.scales": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.17.feed_forward.shared_expert.down_proj.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.17.feed_forward.shared_expert.gate_proj.biases": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.17.feed_forward.shared_expert.gate_proj.scales": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.17.feed_forward.shared_expert.gate_proj.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.17.feed_forward.shared_expert.up_proj.biases": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.17.feed_forward.shared_expert.up_proj.scales": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.17.feed_forward.shared_expert.up_proj.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.17.input_layernorm.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.17.post_attention_layernorm.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.17.self_attn.k_proj.biases": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.17.self_attn.k_proj.scales": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.17.self_attn.k_proj.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.17.self_attn.o_proj.biases": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.17.self_attn.o_proj.scales": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.17.self_attn.o_proj.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.17.self_attn.q_proj.biases": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.17.self_attn.q_proj.scales": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.17.self_attn.q_proj.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.17.self_attn.v_proj.biases": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.17.self_attn.v_proj.scales": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.17.self_attn.v_proj.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.18.feed_forward.experts.down_proj.biases": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.18.feed_forward.experts.down_proj.scales": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.18.feed_forward.experts.down_proj.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.18.feed_forward.experts.gate_proj.biases": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.18.feed_forward.experts.gate_proj.scales": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.18.feed_forward.experts.gate_proj.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.18.feed_forward.experts.up_proj.biases": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.18.feed_forward.experts.up_proj.scales": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.18.feed_forward.experts.up_proj.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.18.feed_forward.router.biases": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.18.feed_forward.router.scales": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.18.feed_forward.router.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.18.feed_forward.shared_expert.down_proj.biases": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.18.feed_forward.shared_expert.down_proj.scales": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.18.feed_forward.shared_expert.down_proj.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.18.feed_forward.shared_expert.gate_proj.biases": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.18.feed_forward.shared_expert.gate_proj.scales": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.18.feed_forward.shared_expert.gate_proj.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.18.feed_forward.shared_expert.up_proj.biases": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.18.feed_forward.shared_expert.up_proj.scales": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.18.feed_forward.shared_expert.up_proj.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.18.input_layernorm.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.18.post_attention_layernorm.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.18.self_attn.k_proj.biases": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.18.self_attn.k_proj.scales": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.18.self_attn.k_proj.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.18.self_attn.o_proj.biases": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.18.self_attn.o_proj.scales": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.18.self_attn.o_proj.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.18.self_attn.q_proj.biases": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.18.self_attn.q_proj.scales": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.18.self_attn.q_proj.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.18.self_attn.v_proj.biases": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.18.self_attn.v_proj.scales": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.18.self_attn.v_proj.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.19.feed_forward.experts.down_proj.biases": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.19.feed_forward.experts.down_proj.scales": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.19.feed_forward.experts.down_proj.weight": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.19.feed_forward.experts.gate_proj.biases": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.19.feed_forward.experts.gate_proj.scales": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.19.feed_forward.experts.gate_proj.weight": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.19.feed_forward.experts.up_proj.biases": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.19.feed_forward.experts.up_proj.scales": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.19.feed_forward.experts.up_proj.weight": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.19.feed_forward.router.biases": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.19.feed_forward.router.scales": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.19.feed_forward.router.weight": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.19.feed_forward.shared_expert.down_proj.biases": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.19.feed_forward.shared_expert.down_proj.scales": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.19.feed_forward.shared_expert.down_proj.weight": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.19.feed_forward.shared_expert.gate_proj.biases": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.19.feed_forward.shared_expert.gate_proj.scales": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.19.feed_forward.shared_expert.gate_proj.weight": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.19.feed_forward.shared_expert.up_proj.biases": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.19.feed_forward.shared_expert.up_proj.scales": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.19.feed_forward.shared_expert.up_proj.weight": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.19.input_layernorm.weight": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.19.post_attention_layernorm.weight": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.19.self_attn.k_proj.biases": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.19.self_attn.k_proj.scales": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.19.self_attn.k_proj.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.19.self_attn.o_proj.biases": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.19.self_attn.o_proj.scales": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.19.self_attn.o_proj.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.19.self_attn.q_proj.biases": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.19.self_attn.q_proj.scales": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.19.self_attn.q_proj.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.19.self_attn.v_proj.biases": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.19.self_attn.v_proj.scales": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.19.self_attn.v_proj.weight": "model-00009-of-00023.safetensors", |
| "language_model.model.layers.2.feed_forward.experts.down_proj.biases": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.2.feed_forward.experts.down_proj.scales": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.2.feed_forward.experts.down_proj.weight": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.2.feed_forward.experts.gate_proj.biases": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.2.feed_forward.experts.gate_proj.scales": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.2.feed_forward.experts.gate_proj.weight": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.2.feed_forward.experts.up_proj.biases": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.2.feed_forward.experts.up_proj.scales": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.2.feed_forward.experts.up_proj.weight": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.2.feed_forward.router.biases": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.2.feed_forward.router.scales": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.2.feed_forward.router.weight": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.2.feed_forward.shared_expert.down_proj.biases": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.2.feed_forward.shared_expert.down_proj.scales": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.2.feed_forward.shared_expert.down_proj.weight": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.2.feed_forward.shared_expert.gate_proj.biases": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.2.feed_forward.shared_expert.gate_proj.scales": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.2.feed_forward.shared_expert.gate_proj.weight": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.2.feed_forward.shared_expert.up_proj.biases": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.2.feed_forward.shared_expert.up_proj.scales": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.2.feed_forward.shared_expert.up_proj.weight": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.2.input_layernorm.weight": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.2.post_attention_layernorm.weight": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.2.self_attn.k_proj.biases": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.2.self_attn.k_proj.scales": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.2.self_attn.k_proj.weight": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.2.self_attn.o_proj.biases": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.2.self_attn.o_proj.scales": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.2.self_attn.o_proj.weight": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.2.self_attn.q_proj.biases": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.2.self_attn.q_proj.scales": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.2.self_attn.q_proj.weight": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.2.self_attn.v_proj.biases": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.2.self_attn.v_proj.scales": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.2.self_attn.v_proj.weight": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.20.feed_forward.experts.down_proj.biases": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.20.feed_forward.experts.down_proj.scales": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.20.feed_forward.experts.down_proj.weight": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.20.feed_forward.experts.gate_proj.biases": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.20.feed_forward.experts.gate_proj.scales": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.20.feed_forward.experts.gate_proj.weight": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.20.feed_forward.experts.up_proj.biases": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.20.feed_forward.experts.up_proj.scales": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.20.feed_forward.experts.up_proj.weight": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.20.feed_forward.router.biases": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.20.feed_forward.router.scales": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.20.feed_forward.router.weight": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.20.feed_forward.shared_expert.down_proj.biases": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.20.feed_forward.shared_expert.down_proj.scales": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.20.feed_forward.shared_expert.down_proj.weight": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.20.feed_forward.shared_expert.gate_proj.biases": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.20.feed_forward.shared_expert.gate_proj.scales": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.20.feed_forward.shared_expert.gate_proj.weight": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.20.feed_forward.shared_expert.up_proj.biases": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.20.feed_forward.shared_expert.up_proj.scales": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.20.feed_forward.shared_expert.up_proj.weight": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.20.input_layernorm.weight": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.20.post_attention_layernorm.weight": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.20.self_attn.k_proj.biases": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.20.self_attn.k_proj.scales": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.20.self_attn.k_proj.weight": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.20.self_attn.o_proj.biases": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.20.self_attn.o_proj.scales": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.20.self_attn.o_proj.weight": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.20.self_attn.q_proj.biases": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.20.self_attn.q_proj.scales": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.20.self_attn.q_proj.weight": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.20.self_attn.v_proj.biases": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.20.self_attn.v_proj.scales": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.20.self_attn.v_proj.weight": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.21.feed_forward.experts.down_proj.biases": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.21.feed_forward.experts.down_proj.scales": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.21.feed_forward.experts.down_proj.weight": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.21.feed_forward.experts.gate_proj.biases": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.21.feed_forward.experts.gate_proj.scales": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.21.feed_forward.experts.gate_proj.weight": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.21.feed_forward.experts.up_proj.biases": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.21.feed_forward.experts.up_proj.scales": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.21.feed_forward.experts.up_proj.weight": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.21.feed_forward.router.biases": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.21.feed_forward.router.scales": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.21.feed_forward.router.weight": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.21.feed_forward.shared_expert.down_proj.biases": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.21.feed_forward.shared_expert.down_proj.scales": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.21.feed_forward.shared_expert.down_proj.weight": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.21.feed_forward.shared_expert.gate_proj.biases": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.21.feed_forward.shared_expert.gate_proj.scales": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.21.feed_forward.shared_expert.gate_proj.weight": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.21.feed_forward.shared_expert.up_proj.biases": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.21.feed_forward.shared_expert.up_proj.scales": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.21.feed_forward.shared_expert.up_proj.weight": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.21.input_layernorm.weight": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.21.post_attention_layernorm.weight": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.21.self_attn.k_proj.biases": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.21.self_attn.k_proj.scales": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.21.self_attn.k_proj.weight": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.21.self_attn.o_proj.biases": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.21.self_attn.o_proj.scales": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.21.self_attn.o_proj.weight": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.21.self_attn.q_proj.biases": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.21.self_attn.q_proj.scales": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.21.self_attn.q_proj.weight": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.21.self_attn.v_proj.biases": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.21.self_attn.v_proj.scales": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.21.self_attn.v_proj.weight": "model-00010-of-00023.safetensors", |
| "language_model.model.layers.22.feed_forward.experts.down_proj.biases": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.22.feed_forward.experts.down_proj.scales": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.22.feed_forward.experts.down_proj.weight": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.22.feed_forward.experts.gate_proj.biases": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.22.feed_forward.experts.gate_proj.scales": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.22.feed_forward.experts.gate_proj.weight": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.22.feed_forward.experts.up_proj.biases": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.22.feed_forward.experts.up_proj.scales": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.22.feed_forward.experts.up_proj.weight": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.22.feed_forward.router.biases": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.22.feed_forward.router.scales": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.22.feed_forward.router.weight": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.22.feed_forward.shared_expert.down_proj.biases": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.22.feed_forward.shared_expert.down_proj.scales": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.22.feed_forward.shared_expert.down_proj.weight": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.22.feed_forward.shared_expert.gate_proj.biases": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.22.feed_forward.shared_expert.gate_proj.scales": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.22.feed_forward.shared_expert.gate_proj.weight": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.22.feed_forward.shared_expert.up_proj.biases": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.22.feed_forward.shared_expert.up_proj.scales": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.22.feed_forward.shared_expert.up_proj.weight": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.22.input_layernorm.weight": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.22.post_attention_layernorm.weight": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.22.self_attn.k_proj.biases": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.22.self_attn.k_proj.scales": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.22.self_attn.k_proj.weight": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.22.self_attn.o_proj.biases": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.22.self_attn.o_proj.scales": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.22.self_attn.o_proj.weight": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.22.self_attn.q_proj.biases": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.22.self_attn.q_proj.scales": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.22.self_attn.q_proj.weight": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.22.self_attn.v_proj.biases": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.22.self_attn.v_proj.scales": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.22.self_attn.v_proj.weight": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.23.feed_forward.experts.down_proj.biases": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.23.feed_forward.experts.down_proj.scales": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.23.feed_forward.experts.down_proj.weight": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.23.feed_forward.experts.gate_proj.biases": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.23.feed_forward.experts.gate_proj.scales": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.23.feed_forward.experts.gate_proj.weight": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.23.feed_forward.experts.up_proj.biases": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.23.feed_forward.experts.up_proj.scales": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.23.feed_forward.experts.up_proj.weight": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.23.feed_forward.router.biases": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.23.feed_forward.router.scales": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.23.feed_forward.router.weight": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.23.feed_forward.shared_expert.down_proj.biases": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.23.feed_forward.shared_expert.down_proj.scales": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.23.feed_forward.shared_expert.down_proj.weight": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.23.feed_forward.shared_expert.gate_proj.biases": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.23.feed_forward.shared_expert.gate_proj.scales": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.23.feed_forward.shared_expert.gate_proj.weight": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.23.feed_forward.shared_expert.up_proj.biases": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.23.feed_forward.shared_expert.up_proj.scales": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.23.feed_forward.shared_expert.up_proj.weight": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.23.input_layernorm.weight": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.23.post_attention_layernorm.weight": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.23.self_attn.k_proj.biases": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.23.self_attn.k_proj.scales": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.23.self_attn.k_proj.weight": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.23.self_attn.o_proj.biases": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.23.self_attn.o_proj.scales": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.23.self_attn.o_proj.weight": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.23.self_attn.q_proj.biases": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.23.self_attn.q_proj.scales": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.23.self_attn.q_proj.weight": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.23.self_attn.v_proj.biases": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.23.self_attn.v_proj.scales": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.23.self_attn.v_proj.weight": "model-00011-of-00023.safetensors", |
| "language_model.model.layers.24.feed_forward.experts.down_proj.biases": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.24.feed_forward.experts.down_proj.scales": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.24.feed_forward.experts.down_proj.weight": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.24.feed_forward.experts.gate_proj.biases": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.24.feed_forward.experts.gate_proj.scales": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.24.feed_forward.experts.gate_proj.weight": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.24.feed_forward.experts.up_proj.biases": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.24.feed_forward.experts.up_proj.scales": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.24.feed_forward.experts.up_proj.weight": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.24.feed_forward.router.biases": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.24.feed_forward.router.scales": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.24.feed_forward.router.weight": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.24.feed_forward.shared_expert.down_proj.biases": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.24.feed_forward.shared_expert.down_proj.scales": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.24.feed_forward.shared_expert.down_proj.weight": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.24.feed_forward.shared_expert.gate_proj.biases": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.24.feed_forward.shared_expert.gate_proj.scales": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.24.feed_forward.shared_expert.gate_proj.weight": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.24.feed_forward.shared_expert.up_proj.biases": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.24.feed_forward.shared_expert.up_proj.scales": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.24.feed_forward.shared_expert.up_proj.weight": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.24.input_layernorm.weight": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.24.post_attention_layernorm.weight": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.24.self_attn.k_proj.biases": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.24.self_attn.k_proj.scales": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.24.self_attn.k_proj.weight": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.24.self_attn.o_proj.biases": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.24.self_attn.o_proj.scales": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.24.self_attn.o_proj.weight": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.24.self_attn.q_proj.biases": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.24.self_attn.q_proj.scales": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.24.self_attn.q_proj.weight": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.24.self_attn.v_proj.biases": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.24.self_attn.v_proj.scales": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.24.self_attn.v_proj.weight": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.25.feed_forward.experts.down_proj.biases": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.25.feed_forward.experts.down_proj.scales": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.25.feed_forward.experts.down_proj.weight": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.25.feed_forward.experts.gate_proj.biases": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.25.feed_forward.experts.gate_proj.scales": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.25.feed_forward.experts.gate_proj.weight": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.25.feed_forward.experts.up_proj.biases": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.25.feed_forward.experts.up_proj.scales": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.25.feed_forward.experts.up_proj.weight": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.25.feed_forward.router.biases": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.25.feed_forward.router.scales": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.25.feed_forward.router.weight": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.25.feed_forward.shared_expert.down_proj.biases": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.25.feed_forward.shared_expert.down_proj.scales": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.25.feed_forward.shared_expert.down_proj.weight": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.25.feed_forward.shared_expert.gate_proj.biases": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.25.feed_forward.shared_expert.gate_proj.scales": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.25.feed_forward.shared_expert.gate_proj.weight": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.25.feed_forward.shared_expert.up_proj.biases": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.25.feed_forward.shared_expert.up_proj.scales": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.25.feed_forward.shared_expert.up_proj.weight": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.25.input_layernorm.weight": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.25.post_attention_layernorm.weight": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.25.self_attn.k_proj.biases": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.25.self_attn.k_proj.scales": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.25.self_attn.k_proj.weight": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.25.self_attn.o_proj.biases": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.25.self_attn.o_proj.scales": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.25.self_attn.o_proj.weight": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.25.self_attn.q_proj.biases": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.25.self_attn.q_proj.scales": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.25.self_attn.q_proj.weight": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.25.self_attn.v_proj.biases": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.25.self_attn.v_proj.scales": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.25.self_attn.v_proj.weight": "model-00012-of-00023.safetensors", |
| "language_model.model.layers.26.feed_forward.experts.down_proj.biases": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.26.feed_forward.experts.down_proj.scales": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.26.feed_forward.experts.down_proj.weight": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.26.feed_forward.experts.gate_proj.biases": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.26.feed_forward.experts.gate_proj.scales": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.26.feed_forward.experts.gate_proj.weight": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.26.feed_forward.experts.up_proj.biases": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.26.feed_forward.experts.up_proj.scales": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.26.feed_forward.experts.up_proj.weight": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.26.feed_forward.router.biases": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.26.feed_forward.router.scales": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.26.feed_forward.router.weight": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.26.feed_forward.shared_expert.down_proj.biases": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.26.feed_forward.shared_expert.down_proj.scales": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.26.feed_forward.shared_expert.down_proj.weight": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.26.feed_forward.shared_expert.gate_proj.biases": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.26.feed_forward.shared_expert.gate_proj.scales": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.26.feed_forward.shared_expert.gate_proj.weight": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.26.feed_forward.shared_expert.up_proj.biases": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.26.feed_forward.shared_expert.up_proj.scales": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.26.feed_forward.shared_expert.up_proj.weight": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.26.input_layernorm.weight": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.26.post_attention_layernorm.weight": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.26.self_attn.k_proj.biases": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.26.self_attn.k_proj.scales": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.26.self_attn.k_proj.weight": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.26.self_attn.o_proj.biases": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.26.self_attn.o_proj.scales": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.26.self_attn.o_proj.weight": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.26.self_attn.q_proj.biases": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.26.self_attn.q_proj.scales": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.26.self_attn.q_proj.weight": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.26.self_attn.v_proj.biases": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.26.self_attn.v_proj.scales": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.26.self_attn.v_proj.weight": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.27.feed_forward.experts.down_proj.biases": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.27.feed_forward.experts.down_proj.scales": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.27.feed_forward.experts.down_proj.weight": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.27.feed_forward.experts.gate_proj.biases": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.27.feed_forward.experts.gate_proj.scales": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.27.feed_forward.experts.gate_proj.weight": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.27.feed_forward.experts.up_proj.biases": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.27.feed_forward.experts.up_proj.scales": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.27.feed_forward.experts.up_proj.weight": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.27.feed_forward.router.biases": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.27.feed_forward.router.scales": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.27.feed_forward.router.weight": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.27.feed_forward.shared_expert.down_proj.biases": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.27.feed_forward.shared_expert.down_proj.scales": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.27.feed_forward.shared_expert.down_proj.weight": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.27.feed_forward.shared_expert.gate_proj.biases": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.27.feed_forward.shared_expert.gate_proj.scales": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.27.feed_forward.shared_expert.gate_proj.weight": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.27.feed_forward.shared_expert.up_proj.biases": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.27.feed_forward.shared_expert.up_proj.scales": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.27.feed_forward.shared_expert.up_proj.weight": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.27.input_layernorm.weight": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.27.post_attention_layernorm.weight": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.27.self_attn.k_proj.biases": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.27.self_attn.k_proj.scales": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.27.self_attn.k_proj.weight": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.27.self_attn.o_proj.biases": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.27.self_attn.o_proj.scales": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.27.self_attn.o_proj.weight": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.27.self_attn.q_proj.biases": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.27.self_attn.q_proj.scales": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.27.self_attn.q_proj.weight": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.27.self_attn.v_proj.biases": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.27.self_attn.v_proj.scales": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.27.self_attn.v_proj.weight": "model-00013-of-00023.safetensors", |
| "language_model.model.layers.28.feed_forward.experts.down_proj.biases": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.28.feed_forward.experts.down_proj.scales": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.28.feed_forward.experts.down_proj.weight": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.28.feed_forward.experts.gate_proj.biases": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.28.feed_forward.experts.gate_proj.scales": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.28.feed_forward.experts.gate_proj.weight": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.28.feed_forward.experts.up_proj.biases": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.28.feed_forward.experts.up_proj.scales": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.28.feed_forward.experts.up_proj.weight": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.28.feed_forward.router.biases": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.28.feed_forward.router.scales": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.28.feed_forward.router.weight": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.28.feed_forward.shared_expert.down_proj.biases": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.28.feed_forward.shared_expert.down_proj.scales": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.28.feed_forward.shared_expert.down_proj.weight": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.28.feed_forward.shared_expert.gate_proj.biases": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.28.feed_forward.shared_expert.gate_proj.scales": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.28.feed_forward.shared_expert.gate_proj.weight": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.28.feed_forward.shared_expert.up_proj.biases": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.28.feed_forward.shared_expert.up_proj.scales": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.28.feed_forward.shared_expert.up_proj.weight": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.28.input_layernorm.weight": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.28.post_attention_layernorm.weight": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.28.self_attn.k_proj.biases": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.28.self_attn.k_proj.scales": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.28.self_attn.k_proj.weight": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.28.self_attn.o_proj.biases": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.28.self_attn.o_proj.scales": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.28.self_attn.o_proj.weight": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.28.self_attn.q_proj.biases": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.28.self_attn.q_proj.scales": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.28.self_attn.q_proj.weight": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.28.self_attn.v_proj.biases": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.28.self_attn.v_proj.scales": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.28.self_attn.v_proj.weight": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.29.feed_forward.experts.down_proj.biases": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.29.feed_forward.experts.down_proj.scales": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.29.feed_forward.experts.down_proj.weight": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.29.feed_forward.experts.gate_proj.biases": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.29.feed_forward.experts.gate_proj.scales": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.29.feed_forward.experts.gate_proj.weight": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.29.feed_forward.experts.up_proj.biases": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.29.feed_forward.experts.up_proj.scales": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.29.feed_forward.experts.up_proj.weight": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.29.feed_forward.router.biases": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.29.feed_forward.router.scales": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.29.feed_forward.router.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.29.feed_forward.shared_expert.down_proj.biases": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.29.feed_forward.shared_expert.down_proj.scales": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.29.feed_forward.shared_expert.down_proj.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.29.feed_forward.shared_expert.gate_proj.biases": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.29.feed_forward.shared_expert.gate_proj.scales": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.29.feed_forward.shared_expert.gate_proj.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.29.feed_forward.shared_expert.up_proj.biases": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.29.feed_forward.shared_expert.up_proj.scales": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.29.feed_forward.shared_expert.up_proj.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.29.input_layernorm.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.29.post_attention_layernorm.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.29.self_attn.k_proj.biases": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.29.self_attn.k_proj.scales": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.29.self_attn.k_proj.weight": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.29.self_attn.o_proj.biases": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.29.self_attn.o_proj.scales": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.29.self_attn.o_proj.weight": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.29.self_attn.q_proj.biases": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.29.self_attn.q_proj.scales": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.29.self_attn.q_proj.weight": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.29.self_attn.v_proj.biases": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.29.self_attn.v_proj.scales": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.29.self_attn.v_proj.weight": "model-00014-of-00023.safetensors", |
| "language_model.model.layers.3.feed_forward.experts.down_proj.biases": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.3.feed_forward.experts.down_proj.scales": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.3.feed_forward.experts.down_proj.weight": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.3.feed_forward.experts.gate_proj.biases": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.3.feed_forward.experts.gate_proj.scales": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.3.feed_forward.experts.gate_proj.weight": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.3.feed_forward.experts.up_proj.biases": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.3.feed_forward.experts.up_proj.scales": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.3.feed_forward.experts.up_proj.weight": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.3.feed_forward.router.biases": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.3.feed_forward.router.scales": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.3.feed_forward.router.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.3.feed_forward.shared_expert.down_proj.biases": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.3.feed_forward.shared_expert.down_proj.scales": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.3.feed_forward.shared_expert.down_proj.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.3.feed_forward.shared_expert.gate_proj.biases": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.3.feed_forward.shared_expert.gate_proj.scales": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.3.feed_forward.shared_expert.gate_proj.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.3.feed_forward.shared_expert.up_proj.biases": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.3.feed_forward.shared_expert.up_proj.scales": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.3.feed_forward.shared_expert.up_proj.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.3.input_layernorm.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.3.post_attention_layernorm.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.3.self_attn.k_proj.biases": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.3.self_attn.k_proj.scales": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.3.self_attn.k_proj.weight": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.3.self_attn.o_proj.biases": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.3.self_attn.o_proj.scales": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.3.self_attn.o_proj.weight": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.3.self_attn.q_proj.biases": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.3.self_attn.q_proj.scales": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.3.self_attn.q_proj.weight": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.3.self_attn.v_proj.biases": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.3.self_attn.v_proj.scales": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.3.self_attn.v_proj.weight": "model-00002-of-00023.safetensors", |
| "language_model.model.layers.30.feed_forward.experts.down_proj.biases": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.30.feed_forward.experts.down_proj.scales": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.30.feed_forward.experts.down_proj.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.30.feed_forward.experts.gate_proj.biases": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.30.feed_forward.experts.gate_proj.scales": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.30.feed_forward.experts.gate_proj.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.30.feed_forward.experts.up_proj.biases": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.30.feed_forward.experts.up_proj.scales": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.30.feed_forward.experts.up_proj.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.30.feed_forward.router.biases": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.30.feed_forward.router.scales": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.30.feed_forward.router.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.30.feed_forward.shared_expert.down_proj.biases": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.30.feed_forward.shared_expert.down_proj.scales": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.30.feed_forward.shared_expert.down_proj.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.30.feed_forward.shared_expert.gate_proj.biases": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.30.feed_forward.shared_expert.gate_proj.scales": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.30.feed_forward.shared_expert.gate_proj.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.30.feed_forward.shared_expert.up_proj.biases": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.30.feed_forward.shared_expert.up_proj.scales": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.30.feed_forward.shared_expert.up_proj.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.30.input_layernorm.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.30.post_attention_layernorm.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.30.self_attn.k_proj.biases": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.30.self_attn.k_proj.scales": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.30.self_attn.k_proj.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.30.self_attn.o_proj.biases": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.30.self_attn.o_proj.scales": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.30.self_attn.o_proj.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.30.self_attn.q_proj.biases": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.30.self_attn.q_proj.scales": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.30.self_attn.q_proj.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.30.self_attn.v_proj.biases": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.30.self_attn.v_proj.scales": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.30.self_attn.v_proj.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.31.feed_forward.experts.down_proj.biases": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.31.feed_forward.experts.down_proj.scales": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.31.feed_forward.experts.down_proj.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.31.feed_forward.experts.gate_proj.biases": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.31.feed_forward.experts.gate_proj.scales": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.31.feed_forward.experts.gate_proj.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.31.feed_forward.experts.up_proj.biases": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.31.feed_forward.experts.up_proj.scales": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.31.feed_forward.experts.up_proj.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.31.feed_forward.router.biases": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.31.feed_forward.router.scales": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.31.feed_forward.router.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.31.feed_forward.shared_expert.down_proj.biases": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.31.feed_forward.shared_expert.down_proj.scales": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.31.feed_forward.shared_expert.down_proj.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.31.feed_forward.shared_expert.gate_proj.biases": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.31.feed_forward.shared_expert.gate_proj.scales": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.31.feed_forward.shared_expert.gate_proj.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.31.feed_forward.shared_expert.up_proj.biases": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.31.feed_forward.shared_expert.up_proj.scales": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.31.feed_forward.shared_expert.up_proj.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.31.input_layernorm.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.31.post_attention_layernorm.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.31.self_attn.k_proj.biases": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.31.self_attn.k_proj.scales": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.31.self_attn.k_proj.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.31.self_attn.o_proj.biases": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.31.self_attn.o_proj.scales": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.31.self_attn.o_proj.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.31.self_attn.q_proj.biases": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.31.self_attn.q_proj.scales": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.31.self_attn.q_proj.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.31.self_attn.v_proj.biases": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.31.self_attn.v_proj.scales": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.31.self_attn.v_proj.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.32.feed_forward.experts.down_proj.biases": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.32.feed_forward.experts.down_proj.scales": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.32.feed_forward.experts.down_proj.weight": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.32.feed_forward.experts.gate_proj.biases": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.32.feed_forward.experts.gate_proj.scales": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.32.feed_forward.experts.gate_proj.weight": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.32.feed_forward.experts.up_proj.biases": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.32.feed_forward.experts.up_proj.scales": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.32.feed_forward.experts.up_proj.weight": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.32.feed_forward.router.biases": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.32.feed_forward.router.scales": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.32.feed_forward.router.weight": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.32.feed_forward.shared_expert.down_proj.biases": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.32.feed_forward.shared_expert.down_proj.scales": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.32.feed_forward.shared_expert.down_proj.weight": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.32.feed_forward.shared_expert.gate_proj.biases": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.32.feed_forward.shared_expert.gate_proj.scales": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.32.feed_forward.shared_expert.gate_proj.weight": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.32.feed_forward.shared_expert.up_proj.biases": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.32.feed_forward.shared_expert.up_proj.scales": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.32.feed_forward.shared_expert.up_proj.weight": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.32.input_layernorm.weight": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.32.post_attention_layernorm.weight": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.32.self_attn.k_proj.biases": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.32.self_attn.k_proj.scales": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.32.self_attn.k_proj.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.32.self_attn.o_proj.biases": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.32.self_attn.o_proj.scales": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.32.self_attn.o_proj.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.32.self_attn.q_proj.biases": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.32.self_attn.q_proj.scales": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.32.self_attn.q_proj.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.32.self_attn.v_proj.biases": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.32.self_attn.v_proj.scales": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.32.self_attn.v_proj.weight": "model-00015-of-00023.safetensors", |
| "language_model.model.layers.33.feed_forward.experts.down_proj.biases": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.33.feed_forward.experts.down_proj.scales": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.33.feed_forward.experts.down_proj.weight": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.33.feed_forward.experts.gate_proj.biases": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.33.feed_forward.experts.gate_proj.scales": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.33.feed_forward.experts.gate_proj.weight": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.33.feed_forward.experts.up_proj.biases": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.33.feed_forward.experts.up_proj.scales": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.33.feed_forward.experts.up_proj.weight": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.33.feed_forward.router.biases": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.33.feed_forward.router.scales": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.33.feed_forward.router.weight": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.33.feed_forward.shared_expert.down_proj.biases": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.33.feed_forward.shared_expert.down_proj.scales": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.33.feed_forward.shared_expert.down_proj.weight": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.33.feed_forward.shared_expert.gate_proj.biases": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.33.feed_forward.shared_expert.gate_proj.scales": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.33.feed_forward.shared_expert.gate_proj.weight": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.33.feed_forward.shared_expert.up_proj.biases": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.33.feed_forward.shared_expert.up_proj.scales": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.33.feed_forward.shared_expert.up_proj.weight": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.33.input_layernorm.weight": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.33.post_attention_layernorm.weight": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.33.self_attn.k_proj.biases": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.33.self_attn.k_proj.scales": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.33.self_attn.k_proj.weight": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.33.self_attn.o_proj.biases": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.33.self_attn.o_proj.scales": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.33.self_attn.o_proj.weight": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.33.self_attn.q_proj.biases": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.33.self_attn.q_proj.scales": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.33.self_attn.q_proj.weight": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.33.self_attn.v_proj.biases": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.33.self_attn.v_proj.scales": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.33.self_attn.v_proj.weight": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.34.feed_forward.experts.down_proj.biases": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.34.feed_forward.experts.down_proj.scales": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.34.feed_forward.experts.down_proj.weight": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.34.feed_forward.experts.gate_proj.biases": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.34.feed_forward.experts.gate_proj.scales": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.34.feed_forward.experts.gate_proj.weight": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.34.feed_forward.experts.up_proj.biases": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.34.feed_forward.experts.up_proj.scales": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.34.feed_forward.experts.up_proj.weight": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.34.feed_forward.router.biases": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.34.feed_forward.router.scales": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.34.feed_forward.router.weight": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.34.feed_forward.shared_expert.down_proj.biases": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.34.feed_forward.shared_expert.down_proj.scales": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.34.feed_forward.shared_expert.down_proj.weight": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.34.feed_forward.shared_expert.gate_proj.biases": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.34.feed_forward.shared_expert.gate_proj.scales": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.34.feed_forward.shared_expert.gate_proj.weight": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.34.feed_forward.shared_expert.up_proj.biases": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.34.feed_forward.shared_expert.up_proj.scales": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.34.feed_forward.shared_expert.up_proj.weight": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.34.input_layernorm.weight": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.34.post_attention_layernorm.weight": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.34.self_attn.k_proj.biases": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.34.self_attn.k_proj.scales": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.34.self_attn.k_proj.weight": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.34.self_attn.o_proj.biases": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.34.self_attn.o_proj.scales": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.34.self_attn.o_proj.weight": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.34.self_attn.q_proj.biases": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.34.self_attn.q_proj.scales": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.34.self_attn.q_proj.weight": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.34.self_attn.v_proj.biases": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.34.self_attn.v_proj.scales": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.34.self_attn.v_proj.weight": "model-00016-of-00023.safetensors", |
| "language_model.model.layers.35.feed_forward.experts.down_proj.biases": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.35.feed_forward.experts.down_proj.scales": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.35.feed_forward.experts.down_proj.weight": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.35.feed_forward.experts.gate_proj.biases": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.35.feed_forward.experts.gate_proj.scales": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.35.feed_forward.experts.gate_proj.weight": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.35.feed_forward.experts.up_proj.biases": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.35.feed_forward.experts.up_proj.scales": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.35.feed_forward.experts.up_proj.weight": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.35.feed_forward.router.biases": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.35.feed_forward.router.scales": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.35.feed_forward.router.weight": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.35.feed_forward.shared_expert.down_proj.biases": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.35.feed_forward.shared_expert.down_proj.scales": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.35.feed_forward.shared_expert.down_proj.weight": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.35.feed_forward.shared_expert.gate_proj.biases": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.35.feed_forward.shared_expert.gate_proj.scales": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.35.feed_forward.shared_expert.gate_proj.weight": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.35.feed_forward.shared_expert.up_proj.biases": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.35.feed_forward.shared_expert.up_proj.scales": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.35.feed_forward.shared_expert.up_proj.weight": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.35.input_layernorm.weight": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.35.post_attention_layernorm.weight": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.35.self_attn.k_proj.biases": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.35.self_attn.k_proj.scales": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.35.self_attn.k_proj.weight": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.35.self_attn.o_proj.biases": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.35.self_attn.o_proj.scales": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.35.self_attn.o_proj.weight": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.35.self_attn.q_proj.biases": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.35.self_attn.q_proj.scales": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.35.self_attn.q_proj.weight": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.35.self_attn.v_proj.biases": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.35.self_attn.v_proj.scales": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.35.self_attn.v_proj.weight": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.36.feed_forward.experts.down_proj.biases": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.36.feed_forward.experts.down_proj.scales": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.36.feed_forward.experts.down_proj.weight": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.36.feed_forward.experts.gate_proj.biases": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.36.feed_forward.experts.gate_proj.scales": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.36.feed_forward.experts.gate_proj.weight": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.36.feed_forward.experts.up_proj.biases": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.36.feed_forward.experts.up_proj.scales": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.36.feed_forward.experts.up_proj.weight": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.36.feed_forward.router.biases": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.36.feed_forward.router.scales": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.36.feed_forward.router.weight": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.36.feed_forward.shared_expert.down_proj.biases": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.36.feed_forward.shared_expert.down_proj.scales": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.36.feed_forward.shared_expert.down_proj.weight": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.36.feed_forward.shared_expert.gate_proj.biases": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.36.feed_forward.shared_expert.gate_proj.scales": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.36.feed_forward.shared_expert.gate_proj.weight": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.36.feed_forward.shared_expert.up_proj.biases": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.36.feed_forward.shared_expert.up_proj.scales": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.36.feed_forward.shared_expert.up_proj.weight": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.36.input_layernorm.weight": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.36.post_attention_layernorm.weight": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.36.self_attn.k_proj.biases": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.36.self_attn.k_proj.scales": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.36.self_attn.k_proj.weight": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.36.self_attn.o_proj.biases": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.36.self_attn.o_proj.scales": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.36.self_attn.o_proj.weight": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.36.self_attn.q_proj.biases": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.36.self_attn.q_proj.scales": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.36.self_attn.q_proj.weight": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.36.self_attn.v_proj.biases": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.36.self_attn.v_proj.scales": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.36.self_attn.v_proj.weight": "model-00017-of-00023.safetensors", |
| "language_model.model.layers.37.feed_forward.experts.down_proj.biases": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.37.feed_forward.experts.down_proj.scales": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.37.feed_forward.experts.down_proj.weight": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.37.feed_forward.experts.gate_proj.biases": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.37.feed_forward.experts.gate_proj.scales": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.37.feed_forward.experts.gate_proj.weight": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.37.feed_forward.experts.up_proj.biases": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.37.feed_forward.experts.up_proj.scales": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.37.feed_forward.experts.up_proj.weight": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.37.feed_forward.router.biases": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.37.feed_forward.router.scales": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.37.feed_forward.router.weight": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.37.feed_forward.shared_expert.down_proj.biases": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.37.feed_forward.shared_expert.down_proj.scales": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.37.feed_forward.shared_expert.down_proj.weight": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.37.feed_forward.shared_expert.gate_proj.biases": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.37.feed_forward.shared_expert.gate_proj.scales": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.37.feed_forward.shared_expert.gate_proj.weight": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.37.feed_forward.shared_expert.up_proj.biases": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.37.feed_forward.shared_expert.up_proj.scales": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.37.feed_forward.shared_expert.up_proj.weight": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.37.input_layernorm.weight": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.37.post_attention_layernorm.weight": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.37.self_attn.k_proj.biases": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.37.self_attn.k_proj.scales": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.37.self_attn.k_proj.weight": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.37.self_attn.o_proj.biases": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.37.self_attn.o_proj.scales": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.37.self_attn.o_proj.weight": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.37.self_attn.q_proj.biases": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.37.self_attn.q_proj.scales": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.37.self_attn.q_proj.weight": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.37.self_attn.v_proj.biases": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.37.self_attn.v_proj.scales": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.37.self_attn.v_proj.weight": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.38.feed_forward.experts.down_proj.biases": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.38.feed_forward.experts.down_proj.scales": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.38.feed_forward.experts.down_proj.weight": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.38.feed_forward.experts.gate_proj.biases": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.38.feed_forward.experts.gate_proj.scales": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.38.feed_forward.experts.gate_proj.weight": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.38.feed_forward.experts.up_proj.biases": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.38.feed_forward.experts.up_proj.scales": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.38.feed_forward.experts.up_proj.weight": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.38.feed_forward.router.biases": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.38.feed_forward.router.scales": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.38.feed_forward.router.weight": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.38.feed_forward.shared_expert.down_proj.biases": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.38.feed_forward.shared_expert.down_proj.scales": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.38.feed_forward.shared_expert.down_proj.weight": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.38.feed_forward.shared_expert.gate_proj.biases": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.38.feed_forward.shared_expert.gate_proj.scales": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.38.feed_forward.shared_expert.gate_proj.weight": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.38.feed_forward.shared_expert.up_proj.biases": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.38.feed_forward.shared_expert.up_proj.scales": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.38.feed_forward.shared_expert.up_proj.weight": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.38.input_layernorm.weight": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.38.post_attention_layernorm.weight": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.38.self_attn.k_proj.biases": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.38.self_attn.k_proj.scales": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.38.self_attn.k_proj.weight": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.38.self_attn.o_proj.biases": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.38.self_attn.o_proj.scales": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.38.self_attn.o_proj.weight": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.38.self_attn.q_proj.biases": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.38.self_attn.q_proj.scales": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.38.self_attn.q_proj.weight": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.38.self_attn.v_proj.biases": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.38.self_attn.v_proj.scales": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.38.self_attn.v_proj.weight": "model-00018-of-00023.safetensors", |
| "language_model.model.layers.39.feed_forward.experts.down_proj.biases": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.39.feed_forward.experts.down_proj.scales": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.39.feed_forward.experts.down_proj.weight": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.39.feed_forward.experts.gate_proj.biases": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.39.feed_forward.experts.gate_proj.scales": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.39.feed_forward.experts.gate_proj.weight": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.39.feed_forward.experts.up_proj.biases": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.39.feed_forward.experts.up_proj.scales": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.39.feed_forward.experts.up_proj.weight": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.39.feed_forward.router.biases": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.39.feed_forward.router.scales": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.39.feed_forward.router.weight": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.39.feed_forward.shared_expert.down_proj.biases": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.39.feed_forward.shared_expert.down_proj.scales": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.39.feed_forward.shared_expert.down_proj.weight": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.39.feed_forward.shared_expert.gate_proj.biases": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.39.feed_forward.shared_expert.gate_proj.scales": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.39.feed_forward.shared_expert.gate_proj.weight": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.39.feed_forward.shared_expert.up_proj.biases": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.39.feed_forward.shared_expert.up_proj.scales": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.39.feed_forward.shared_expert.up_proj.weight": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.39.input_layernorm.weight": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.39.post_attention_layernorm.weight": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.39.self_attn.k_proj.biases": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.39.self_attn.k_proj.scales": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.39.self_attn.k_proj.weight": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.39.self_attn.o_proj.biases": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.39.self_attn.o_proj.scales": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.39.self_attn.o_proj.weight": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.39.self_attn.q_proj.biases": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.39.self_attn.q_proj.scales": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.39.self_attn.q_proj.weight": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.39.self_attn.v_proj.biases": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.39.self_attn.v_proj.scales": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.39.self_attn.v_proj.weight": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.4.feed_forward.experts.down_proj.biases": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.4.feed_forward.experts.down_proj.scales": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.4.feed_forward.experts.down_proj.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.4.feed_forward.experts.gate_proj.biases": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.4.feed_forward.experts.gate_proj.scales": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.4.feed_forward.experts.gate_proj.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.4.feed_forward.experts.up_proj.biases": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.4.feed_forward.experts.up_proj.scales": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.4.feed_forward.experts.up_proj.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.4.feed_forward.router.biases": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.4.feed_forward.router.scales": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.4.feed_forward.router.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.4.feed_forward.shared_expert.down_proj.biases": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.4.feed_forward.shared_expert.down_proj.scales": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.4.feed_forward.shared_expert.down_proj.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.4.feed_forward.shared_expert.gate_proj.biases": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.4.feed_forward.shared_expert.gate_proj.scales": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.4.feed_forward.shared_expert.gate_proj.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.4.feed_forward.shared_expert.up_proj.biases": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.4.feed_forward.shared_expert.up_proj.scales": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.4.feed_forward.shared_expert.up_proj.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.4.input_layernorm.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.4.post_attention_layernorm.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.4.self_attn.k_proj.biases": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.4.self_attn.k_proj.scales": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.4.self_attn.k_proj.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.4.self_attn.o_proj.biases": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.4.self_attn.o_proj.scales": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.4.self_attn.o_proj.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.4.self_attn.q_proj.biases": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.4.self_attn.q_proj.scales": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.4.self_attn.q_proj.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.4.self_attn.v_proj.biases": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.4.self_attn.v_proj.scales": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.4.self_attn.v_proj.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.40.feed_forward.experts.down_proj.biases": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.40.feed_forward.experts.down_proj.scales": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.40.feed_forward.experts.down_proj.weight": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.40.feed_forward.experts.gate_proj.biases": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.40.feed_forward.experts.gate_proj.scales": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.40.feed_forward.experts.gate_proj.weight": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.40.feed_forward.experts.up_proj.biases": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.40.feed_forward.experts.up_proj.scales": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.40.feed_forward.experts.up_proj.weight": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.40.feed_forward.router.biases": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.40.feed_forward.router.scales": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.40.feed_forward.router.weight": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.40.feed_forward.shared_expert.down_proj.biases": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.40.feed_forward.shared_expert.down_proj.scales": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.40.feed_forward.shared_expert.down_proj.weight": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.40.feed_forward.shared_expert.gate_proj.biases": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.40.feed_forward.shared_expert.gate_proj.scales": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.40.feed_forward.shared_expert.gate_proj.weight": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.40.feed_forward.shared_expert.up_proj.biases": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.40.feed_forward.shared_expert.up_proj.scales": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.40.feed_forward.shared_expert.up_proj.weight": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.40.input_layernorm.weight": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.40.post_attention_layernorm.weight": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.40.self_attn.k_proj.biases": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.40.self_attn.k_proj.scales": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.40.self_attn.k_proj.weight": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.40.self_attn.o_proj.biases": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.40.self_attn.o_proj.scales": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.40.self_attn.o_proj.weight": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.40.self_attn.q_proj.biases": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.40.self_attn.q_proj.scales": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.40.self_attn.q_proj.weight": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.40.self_attn.v_proj.biases": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.40.self_attn.v_proj.scales": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.40.self_attn.v_proj.weight": "model-00019-of-00023.safetensors", |
| "language_model.model.layers.41.feed_forward.experts.down_proj.biases": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.41.feed_forward.experts.down_proj.scales": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.41.feed_forward.experts.down_proj.weight": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.41.feed_forward.experts.gate_proj.biases": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.41.feed_forward.experts.gate_proj.scales": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.41.feed_forward.experts.gate_proj.weight": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.41.feed_forward.experts.up_proj.biases": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.41.feed_forward.experts.up_proj.scales": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.41.feed_forward.experts.up_proj.weight": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.41.feed_forward.router.biases": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.41.feed_forward.router.scales": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.41.feed_forward.router.weight": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.41.feed_forward.shared_expert.down_proj.biases": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.41.feed_forward.shared_expert.down_proj.scales": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.41.feed_forward.shared_expert.down_proj.weight": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.41.feed_forward.shared_expert.gate_proj.biases": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.41.feed_forward.shared_expert.gate_proj.scales": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.41.feed_forward.shared_expert.gate_proj.weight": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.41.feed_forward.shared_expert.up_proj.biases": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.41.feed_forward.shared_expert.up_proj.scales": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.41.feed_forward.shared_expert.up_proj.weight": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.41.input_layernorm.weight": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.41.post_attention_layernorm.weight": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.41.self_attn.k_proj.biases": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.41.self_attn.k_proj.scales": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.41.self_attn.k_proj.weight": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.41.self_attn.o_proj.biases": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.41.self_attn.o_proj.scales": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.41.self_attn.o_proj.weight": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.41.self_attn.q_proj.biases": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.41.self_attn.q_proj.scales": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.41.self_attn.q_proj.weight": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.41.self_attn.v_proj.biases": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.41.self_attn.v_proj.scales": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.41.self_attn.v_proj.weight": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.42.feed_forward.experts.down_proj.biases": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.42.feed_forward.experts.down_proj.scales": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.42.feed_forward.experts.down_proj.weight": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.42.feed_forward.experts.gate_proj.biases": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.42.feed_forward.experts.gate_proj.scales": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.42.feed_forward.experts.gate_proj.weight": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.42.feed_forward.experts.up_proj.biases": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.42.feed_forward.experts.up_proj.scales": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.42.feed_forward.experts.up_proj.weight": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.42.feed_forward.router.biases": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.42.feed_forward.router.scales": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.42.feed_forward.router.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.42.feed_forward.shared_expert.down_proj.biases": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.42.feed_forward.shared_expert.down_proj.scales": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.42.feed_forward.shared_expert.down_proj.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.42.feed_forward.shared_expert.gate_proj.biases": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.42.feed_forward.shared_expert.gate_proj.scales": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.42.feed_forward.shared_expert.gate_proj.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.42.feed_forward.shared_expert.up_proj.biases": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.42.feed_forward.shared_expert.up_proj.scales": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.42.feed_forward.shared_expert.up_proj.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.42.input_layernorm.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.42.post_attention_layernorm.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.42.self_attn.k_proj.biases": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.42.self_attn.k_proj.scales": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.42.self_attn.k_proj.weight": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.42.self_attn.o_proj.biases": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.42.self_attn.o_proj.scales": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.42.self_attn.o_proj.weight": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.42.self_attn.q_proj.biases": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.42.self_attn.q_proj.scales": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.42.self_attn.q_proj.weight": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.42.self_attn.v_proj.biases": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.42.self_attn.v_proj.scales": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.42.self_attn.v_proj.weight": "model-00020-of-00023.safetensors", |
| "language_model.model.layers.43.feed_forward.experts.down_proj.biases": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.43.feed_forward.experts.down_proj.scales": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.43.feed_forward.experts.down_proj.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.43.feed_forward.experts.gate_proj.biases": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.43.feed_forward.experts.gate_proj.scales": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.43.feed_forward.experts.gate_proj.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.43.feed_forward.experts.up_proj.biases": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.43.feed_forward.experts.up_proj.scales": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.43.feed_forward.experts.up_proj.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.43.feed_forward.router.biases": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.43.feed_forward.router.scales": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.43.feed_forward.router.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.43.feed_forward.shared_expert.down_proj.biases": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.43.feed_forward.shared_expert.down_proj.scales": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.43.feed_forward.shared_expert.down_proj.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.43.feed_forward.shared_expert.gate_proj.biases": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.43.feed_forward.shared_expert.gate_proj.scales": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.43.feed_forward.shared_expert.gate_proj.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.43.feed_forward.shared_expert.up_proj.biases": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.43.feed_forward.shared_expert.up_proj.scales": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.43.feed_forward.shared_expert.up_proj.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.43.input_layernorm.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.43.post_attention_layernorm.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.43.self_attn.k_proj.biases": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.43.self_attn.k_proj.scales": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.43.self_attn.k_proj.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.43.self_attn.o_proj.biases": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.43.self_attn.o_proj.scales": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.43.self_attn.o_proj.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.43.self_attn.q_proj.biases": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.43.self_attn.q_proj.scales": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.43.self_attn.q_proj.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.43.self_attn.v_proj.biases": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.43.self_attn.v_proj.scales": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.43.self_attn.v_proj.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.44.feed_forward.experts.down_proj.biases": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.44.feed_forward.experts.down_proj.scales": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.44.feed_forward.experts.down_proj.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.44.feed_forward.experts.gate_proj.biases": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.44.feed_forward.experts.gate_proj.scales": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.44.feed_forward.experts.gate_proj.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.44.feed_forward.experts.up_proj.biases": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.44.feed_forward.experts.up_proj.scales": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.44.feed_forward.experts.up_proj.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.44.feed_forward.router.biases": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.44.feed_forward.router.scales": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.44.feed_forward.router.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.44.feed_forward.shared_expert.down_proj.biases": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.44.feed_forward.shared_expert.down_proj.scales": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.44.feed_forward.shared_expert.down_proj.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.44.feed_forward.shared_expert.gate_proj.biases": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.44.feed_forward.shared_expert.gate_proj.scales": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.44.feed_forward.shared_expert.gate_proj.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.44.feed_forward.shared_expert.up_proj.biases": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.44.feed_forward.shared_expert.up_proj.scales": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.44.feed_forward.shared_expert.up_proj.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.44.input_layernorm.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.44.post_attention_layernorm.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.44.self_attn.k_proj.biases": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.44.self_attn.k_proj.scales": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.44.self_attn.k_proj.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.44.self_attn.o_proj.biases": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.44.self_attn.o_proj.scales": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.44.self_attn.o_proj.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.44.self_attn.q_proj.biases": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.44.self_attn.q_proj.scales": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.44.self_attn.q_proj.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.44.self_attn.v_proj.biases": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.44.self_attn.v_proj.scales": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.44.self_attn.v_proj.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.45.feed_forward.experts.down_proj.biases": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.45.feed_forward.experts.down_proj.scales": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.45.feed_forward.experts.down_proj.weight": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.45.feed_forward.experts.gate_proj.biases": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.45.feed_forward.experts.gate_proj.scales": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.45.feed_forward.experts.gate_proj.weight": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.45.feed_forward.experts.up_proj.biases": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.45.feed_forward.experts.up_proj.scales": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.45.feed_forward.experts.up_proj.weight": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.45.feed_forward.router.biases": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.45.feed_forward.router.scales": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.45.feed_forward.router.weight": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.45.feed_forward.shared_expert.down_proj.biases": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.45.feed_forward.shared_expert.down_proj.scales": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.45.feed_forward.shared_expert.down_proj.weight": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.45.feed_forward.shared_expert.gate_proj.biases": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.45.feed_forward.shared_expert.gate_proj.scales": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.45.feed_forward.shared_expert.gate_proj.weight": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.45.feed_forward.shared_expert.up_proj.biases": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.45.feed_forward.shared_expert.up_proj.scales": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.45.feed_forward.shared_expert.up_proj.weight": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.45.input_layernorm.weight": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.45.post_attention_layernorm.weight": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.45.self_attn.k_proj.biases": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.45.self_attn.k_proj.scales": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.45.self_attn.k_proj.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.45.self_attn.o_proj.biases": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.45.self_attn.o_proj.scales": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.45.self_attn.o_proj.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.45.self_attn.q_proj.biases": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.45.self_attn.q_proj.scales": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.45.self_attn.q_proj.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.45.self_attn.v_proj.biases": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.45.self_attn.v_proj.scales": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.45.self_attn.v_proj.weight": "model-00021-of-00023.safetensors", |
| "language_model.model.layers.46.feed_forward.experts.down_proj.biases": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.46.feed_forward.experts.down_proj.scales": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.46.feed_forward.experts.down_proj.weight": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.46.feed_forward.experts.gate_proj.biases": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.46.feed_forward.experts.gate_proj.scales": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.46.feed_forward.experts.gate_proj.weight": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.46.feed_forward.experts.up_proj.biases": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.46.feed_forward.experts.up_proj.scales": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.46.feed_forward.experts.up_proj.weight": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.46.feed_forward.router.biases": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.46.feed_forward.router.scales": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.46.feed_forward.router.weight": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.46.feed_forward.shared_expert.down_proj.biases": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.46.feed_forward.shared_expert.down_proj.scales": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.46.feed_forward.shared_expert.down_proj.weight": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.46.feed_forward.shared_expert.gate_proj.biases": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.46.feed_forward.shared_expert.gate_proj.scales": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.46.feed_forward.shared_expert.gate_proj.weight": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.46.feed_forward.shared_expert.up_proj.biases": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.46.feed_forward.shared_expert.up_proj.scales": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.46.feed_forward.shared_expert.up_proj.weight": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.46.input_layernorm.weight": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.46.post_attention_layernorm.weight": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.46.self_attn.k_proj.biases": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.46.self_attn.k_proj.scales": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.46.self_attn.k_proj.weight": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.46.self_attn.o_proj.biases": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.46.self_attn.o_proj.scales": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.46.self_attn.o_proj.weight": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.46.self_attn.q_proj.biases": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.46.self_attn.q_proj.scales": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.46.self_attn.q_proj.weight": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.46.self_attn.v_proj.biases": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.46.self_attn.v_proj.scales": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.46.self_attn.v_proj.weight": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.47.feed_forward.experts.down_proj.biases": "model-00023-of-00023.safetensors", |
| "language_model.model.layers.47.feed_forward.experts.down_proj.scales": "model-00023-of-00023.safetensors", |
| "language_model.model.layers.47.feed_forward.experts.down_proj.weight": "model-00023-of-00023.safetensors", |
| "language_model.model.layers.47.feed_forward.experts.gate_proj.biases": "model-00023-of-00023.safetensors", |
| "language_model.model.layers.47.feed_forward.experts.gate_proj.scales": "model-00023-of-00023.safetensors", |
| "language_model.model.layers.47.feed_forward.experts.gate_proj.weight": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.47.feed_forward.experts.up_proj.biases": "model-00023-of-00023.safetensors", |
| "language_model.model.layers.47.feed_forward.experts.up_proj.scales": "model-00023-of-00023.safetensors", |
| "language_model.model.layers.47.feed_forward.experts.up_proj.weight": "model-00023-of-00023.safetensors", |
| "language_model.model.layers.47.feed_forward.router.biases": "model-00023-of-00023.safetensors", |
| "language_model.model.layers.47.feed_forward.router.scales": "model-00023-of-00023.safetensors", |
| "language_model.model.layers.47.feed_forward.router.weight": "model-00023-of-00023.safetensors", |
| "language_model.model.layers.47.feed_forward.shared_expert.down_proj.biases": "model-00023-of-00023.safetensors", |
| "language_model.model.layers.47.feed_forward.shared_expert.down_proj.scales": "model-00023-of-00023.safetensors", |
| "language_model.model.layers.47.feed_forward.shared_expert.down_proj.weight": "model-00023-of-00023.safetensors", |
| "language_model.model.layers.47.feed_forward.shared_expert.gate_proj.biases": "model-00023-of-00023.safetensors", |
| "language_model.model.layers.47.feed_forward.shared_expert.gate_proj.scales": "model-00023-of-00023.safetensors", |
| "language_model.model.layers.47.feed_forward.shared_expert.gate_proj.weight": "model-00023-of-00023.safetensors", |
| "language_model.model.layers.47.feed_forward.shared_expert.up_proj.biases": "model-00023-of-00023.safetensors", |
| "language_model.model.layers.47.feed_forward.shared_expert.up_proj.scales": "model-00023-of-00023.safetensors", |
| "language_model.model.layers.47.feed_forward.shared_expert.up_proj.weight": "model-00023-of-00023.safetensors", |
| "language_model.model.layers.47.input_layernorm.weight": "model-00023-of-00023.safetensors", |
| "language_model.model.layers.47.post_attention_layernorm.weight": "model-00023-of-00023.safetensors", |
| "language_model.model.layers.47.self_attn.k_proj.biases": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.47.self_attn.k_proj.scales": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.47.self_attn.k_proj.weight": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.47.self_attn.o_proj.biases": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.47.self_attn.o_proj.scales": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.47.self_attn.o_proj.weight": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.47.self_attn.q_proj.biases": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.47.self_attn.q_proj.scales": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.47.self_attn.q_proj.weight": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.47.self_attn.v_proj.biases": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.47.self_attn.v_proj.scales": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.47.self_attn.v_proj.weight": "model-00022-of-00023.safetensors", |
| "language_model.model.layers.5.feed_forward.experts.down_proj.biases": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.5.feed_forward.experts.down_proj.scales": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.5.feed_forward.experts.down_proj.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.5.feed_forward.experts.gate_proj.biases": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.5.feed_forward.experts.gate_proj.scales": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.5.feed_forward.experts.gate_proj.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.5.feed_forward.experts.up_proj.biases": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.5.feed_forward.experts.up_proj.scales": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.5.feed_forward.experts.up_proj.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.5.feed_forward.router.biases": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.5.feed_forward.router.scales": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.5.feed_forward.router.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.5.feed_forward.shared_expert.down_proj.biases": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.5.feed_forward.shared_expert.down_proj.scales": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.5.feed_forward.shared_expert.down_proj.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.5.feed_forward.shared_expert.gate_proj.biases": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.5.feed_forward.shared_expert.gate_proj.scales": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.5.feed_forward.shared_expert.gate_proj.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.5.feed_forward.shared_expert.up_proj.biases": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.5.feed_forward.shared_expert.up_proj.scales": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.5.feed_forward.shared_expert.up_proj.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.5.input_layernorm.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.5.post_attention_layernorm.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.5.self_attn.k_proj.biases": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.5.self_attn.k_proj.scales": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.5.self_attn.k_proj.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.5.self_attn.o_proj.biases": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.5.self_attn.o_proj.scales": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.5.self_attn.o_proj.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.5.self_attn.q_proj.biases": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.5.self_attn.q_proj.scales": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.5.self_attn.q_proj.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.5.self_attn.v_proj.biases": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.5.self_attn.v_proj.scales": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.5.self_attn.v_proj.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.6.feed_forward.experts.down_proj.biases": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.6.feed_forward.experts.down_proj.scales": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.6.feed_forward.experts.down_proj.weight": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.6.feed_forward.experts.gate_proj.biases": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.6.feed_forward.experts.gate_proj.scales": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.6.feed_forward.experts.gate_proj.weight": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.6.feed_forward.experts.up_proj.biases": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.6.feed_forward.experts.up_proj.scales": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.6.feed_forward.experts.up_proj.weight": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.6.feed_forward.router.biases": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.6.feed_forward.router.scales": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.6.feed_forward.router.weight": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.6.feed_forward.shared_expert.down_proj.biases": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.6.feed_forward.shared_expert.down_proj.scales": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.6.feed_forward.shared_expert.down_proj.weight": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.6.feed_forward.shared_expert.gate_proj.biases": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.6.feed_forward.shared_expert.gate_proj.scales": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.6.feed_forward.shared_expert.gate_proj.weight": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.6.feed_forward.shared_expert.up_proj.biases": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.6.feed_forward.shared_expert.up_proj.scales": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.6.feed_forward.shared_expert.up_proj.weight": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.6.input_layernorm.weight": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.6.post_attention_layernorm.weight": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.6.self_attn.k_proj.biases": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.6.self_attn.k_proj.scales": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.6.self_attn.k_proj.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.6.self_attn.o_proj.biases": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.6.self_attn.o_proj.scales": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.6.self_attn.o_proj.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.6.self_attn.q_proj.biases": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.6.self_attn.q_proj.scales": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.6.self_attn.q_proj.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.6.self_attn.v_proj.biases": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.6.self_attn.v_proj.scales": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.6.self_attn.v_proj.weight": "model-00003-of-00023.safetensors", |
| "language_model.model.layers.7.feed_forward.experts.down_proj.biases": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.7.feed_forward.experts.down_proj.scales": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.7.feed_forward.experts.down_proj.weight": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.7.feed_forward.experts.gate_proj.biases": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.7.feed_forward.experts.gate_proj.scales": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.7.feed_forward.experts.gate_proj.weight": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.7.feed_forward.experts.up_proj.biases": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.7.feed_forward.experts.up_proj.scales": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.7.feed_forward.experts.up_proj.weight": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.7.feed_forward.router.biases": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.7.feed_forward.router.scales": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.7.feed_forward.router.weight": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.7.feed_forward.shared_expert.down_proj.biases": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.7.feed_forward.shared_expert.down_proj.scales": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.7.feed_forward.shared_expert.down_proj.weight": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.7.feed_forward.shared_expert.gate_proj.biases": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.7.feed_forward.shared_expert.gate_proj.scales": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.7.feed_forward.shared_expert.gate_proj.weight": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.7.feed_forward.shared_expert.up_proj.biases": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.7.feed_forward.shared_expert.up_proj.scales": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.7.feed_forward.shared_expert.up_proj.weight": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.7.input_layernorm.weight": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.7.post_attention_layernorm.weight": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.7.self_attn.k_proj.biases": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.7.self_attn.k_proj.scales": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.7.self_attn.k_proj.weight": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.7.self_attn.o_proj.biases": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.7.self_attn.o_proj.scales": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.7.self_attn.o_proj.weight": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.7.self_attn.q_proj.biases": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.7.self_attn.q_proj.scales": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.7.self_attn.q_proj.weight": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.7.self_attn.v_proj.biases": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.7.self_attn.v_proj.scales": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.7.self_attn.v_proj.weight": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.8.feed_forward.experts.down_proj.biases": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.8.feed_forward.experts.down_proj.scales": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.8.feed_forward.experts.down_proj.weight": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.8.feed_forward.experts.gate_proj.biases": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.8.feed_forward.experts.gate_proj.scales": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.8.feed_forward.experts.gate_proj.weight": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.8.feed_forward.experts.up_proj.biases": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.8.feed_forward.experts.up_proj.scales": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.8.feed_forward.experts.up_proj.weight": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.8.feed_forward.router.biases": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.8.feed_forward.router.scales": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.8.feed_forward.router.weight": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.8.feed_forward.shared_expert.down_proj.biases": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.8.feed_forward.shared_expert.down_proj.scales": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.8.feed_forward.shared_expert.down_proj.weight": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.8.feed_forward.shared_expert.gate_proj.biases": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.8.feed_forward.shared_expert.gate_proj.scales": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.8.feed_forward.shared_expert.gate_proj.weight": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.8.feed_forward.shared_expert.up_proj.biases": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.8.feed_forward.shared_expert.up_proj.scales": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.8.feed_forward.shared_expert.up_proj.weight": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.8.input_layernorm.weight": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.8.post_attention_layernorm.weight": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.8.self_attn.k_proj.biases": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.8.self_attn.k_proj.scales": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.8.self_attn.k_proj.weight": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.8.self_attn.o_proj.biases": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.8.self_attn.o_proj.scales": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.8.self_attn.o_proj.weight": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.8.self_attn.q_proj.biases": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.8.self_attn.q_proj.scales": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.8.self_attn.q_proj.weight": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.8.self_attn.v_proj.biases": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.8.self_attn.v_proj.scales": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.8.self_attn.v_proj.weight": "model-00004-of-00023.safetensors", |
| "language_model.model.layers.9.feed_forward.experts.down_proj.biases": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.9.feed_forward.experts.down_proj.scales": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.9.feed_forward.experts.down_proj.weight": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.9.feed_forward.experts.gate_proj.biases": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.9.feed_forward.experts.gate_proj.scales": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.9.feed_forward.experts.gate_proj.weight": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.9.feed_forward.experts.up_proj.biases": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.9.feed_forward.experts.up_proj.scales": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.9.feed_forward.experts.up_proj.weight": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.9.feed_forward.router.biases": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.9.feed_forward.router.scales": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.9.feed_forward.router.weight": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.9.feed_forward.shared_expert.down_proj.biases": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.9.feed_forward.shared_expert.down_proj.scales": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.9.feed_forward.shared_expert.down_proj.weight": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.9.feed_forward.shared_expert.gate_proj.biases": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.9.feed_forward.shared_expert.gate_proj.scales": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.9.feed_forward.shared_expert.gate_proj.weight": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.9.feed_forward.shared_expert.up_proj.biases": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.9.feed_forward.shared_expert.up_proj.scales": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.9.feed_forward.shared_expert.up_proj.weight": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.9.input_layernorm.weight": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.9.post_attention_layernorm.weight": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.9.self_attn.k_proj.biases": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.9.self_attn.k_proj.scales": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.9.self_attn.k_proj.weight": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.9.self_attn.o_proj.biases": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.9.self_attn.o_proj.scales": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.9.self_attn.o_proj.weight": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.9.self_attn.q_proj.biases": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.9.self_attn.q_proj.scales": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.9.self_attn.q_proj.weight": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.9.self_attn.v_proj.biases": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.9.self_attn.v_proj.scales": "model-00005-of-00023.safetensors", |
| "language_model.model.layers.9.self_attn.v_proj.weight": "model-00005-of-00023.safetensors", |
| "language_model.model.norm.weight": "model-00023-of-00023.safetensors" |
| } |
| } |
