{ "metadata": { "total_parameters": 6120003328, "total_size": 12240020480 }, "weight_map": { "lm_head.weight": "model-00003-of-00003.safetensors", "model.embed_tokens.weight": "model-00001-of-00003.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.0.post_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.0.pre_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.1.post_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.1.pre_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.expert_bias": "model-00001-of-00003.safetensors", "model.layers.10.mlp.moe_mlp.experts.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.moe_mlp.output_experts.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.router.gate.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.shared_experts.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.shared_experts.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.10.post_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.10.pre_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.11.mlp.expert_bias": "model-00001-of-00003.safetensors", "model.layers.11.mlp.moe_mlp.experts.weight": "model-00001-of-00003.safetensors", "model.layers.11.mlp.moe_mlp.output_experts.weight": "model-00001-of-00003.safetensors", "model.layers.11.mlp.router.gate.weight": "model-00001-of-00003.safetensors", "model.layers.11.mlp.shared_experts.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.mlp.shared_experts.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.11.post_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.11.pre_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.12.mlp.expert_bias": "model-00001-of-00003.safetensors", "model.layers.12.mlp.moe_mlp.experts.weight": "model-00001-of-00003.safetensors", "model.layers.12.mlp.moe_mlp.output_experts.weight": "model-00001-of-00003.safetensors", "model.layers.12.mlp.router.gate.weight": "model-00001-of-00003.safetensors", "model.layers.12.mlp.shared_experts.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.mlp.shared_experts.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.12.post_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.12.pre_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.13.mlp.expert_bias": "model-00001-of-00003.safetensors", "model.layers.13.mlp.moe_mlp.experts.weight": "model-00001-of-00003.safetensors", "model.layers.13.mlp.moe_mlp.output_experts.weight": "model-00001-of-00003.safetensors", "model.layers.13.mlp.router.gate.weight": "model-00001-of-00003.safetensors", "model.layers.13.mlp.shared_experts.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.mlp.shared_experts.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.13.post_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.13.pre_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.14.mlp.expert_bias": "model-00001-of-00003.safetensors", "model.layers.14.mlp.moe_mlp.experts.weight": "model-00001-of-00003.safetensors", "model.layers.14.mlp.moe_mlp.output_experts.weight": "model-00001-of-00003.safetensors", "model.layers.14.mlp.router.gate.weight": "model-00001-of-00003.safetensors", "model.layers.14.mlp.shared_experts.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.mlp.shared_experts.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.14.post_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.14.pre_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.15.mlp.expert_bias": "model-00001-of-00003.safetensors", "model.layers.15.mlp.moe_mlp.experts.weight": "model-00001-of-00003.safetensors", "model.layers.15.mlp.moe_mlp.output_experts.weight": "model-00001-of-00003.safetensors", "model.layers.15.mlp.router.gate.weight": "model-00001-of-00003.safetensors", "model.layers.15.mlp.shared_experts.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.mlp.shared_experts.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.15.post_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.15.pre_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.15.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.16.mlp.expert_bias": "model-00001-of-00003.safetensors", "model.layers.16.mlp.moe_mlp.experts.weight": "model-00001-of-00003.safetensors", "model.layers.16.mlp.moe_mlp.output_experts.weight": "model-00001-of-00003.safetensors", "model.layers.16.mlp.router.gate.weight": "model-00001-of-00003.safetensors", "model.layers.16.mlp.shared_experts.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.mlp.shared_experts.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.16.post_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.16.pre_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.17.mlp.expert_bias": "model-00001-of-00003.safetensors", "model.layers.17.mlp.moe_mlp.experts.weight": "model-00001-of-00003.safetensors", "model.layers.17.mlp.moe_mlp.output_experts.weight": "model-00001-of-00003.safetensors", "model.layers.17.mlp.router.gate.weight": "model-00001-of-00003.safetensors", "model.layers.17.mlp.shared_experts.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.mlp.shared_experts.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.17.post_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.17.pre_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.18.mlp.expert_bias": "model-00001-of-00003.safetensors", "model.layers.18.mlp.moe_mlp.experts.weight": "model-00001-of-00003.safetensors", "model.layers.18.mlp.moe_mlp.output_experts.weight": "model-00001-of-00003.safetensors", "model.layers.18.mlp.router.gate.weight": "model-00001-of-00003.safetensors", "model.layers.18.mlp.shared_experts.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.mlp.shared_experts.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.18.post_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.18.pre_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.18.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.19.mlp.expert_bias": "model-00001-of-00003.safetensors", "model.layers.19.mlp.moe_mlp.experts.weight": "model-00001-of-00003.safetensors", "model.layers.19.mlp.moe_mlp.output_experts.weight": "model-00001-of-00003.safetensors", "model.layers.19.mlp.router.gate.weight": "model-00001-of-00003.safetensors", "model.layers.19.mlp.shared_experts.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.mlp.shared_experts.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.19.post_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.19.pre_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.expert_bias": "model-00001-of-00003.safetensors", "model.layers.2.mlp.moe_mlp.experts.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.moe_mlp.output_experts.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.router.gate.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.shared_experts.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.shared_experts.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.2.post_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.2.pre_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.20.mlp.expert_bias": "model-00001-of-00003.safetensors", "model.layers.20.mlp.moe_mlp.experts.weight": "model-00001-of-00003.safetensors", "model.layers.20.mlp.moe_mlp.output_experts.weight": "model-00001-of-00003.safetensors", "model.layers.20.mlp.router.gate.weight": "model-00001-of-00003.safetensors", "model.layers.20.mlp.shared_experts.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.mlp.shared_experts.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.20.post_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.20.pre_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.21.mlp.expert_bias": "model-00001-of-00003.safetensors", "model.layers.21.mlp.moe_mlp.experts.weight": "model-00001-of-00003.safetensors", "model.layers.21.mlp.moe_mlp.output_experts.weight": "model-00001-of-00003.safetensors", "model.layers.21.mlp.router.gate.weight": "model-00001-of-00003.safetensors", "model.layers.21.mlp.shared_experts.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.mlp.shared_experts.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.21.post_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.21.pre_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.22.mlp.expert_bias": "model-00001-of-00003.safetensors", "model.layers.22.mlp.moe_mlp.experts.weight": "model-00001-of-00003.safetensors", "model.layers.22.mlp.moe_mlp.output_experts.weight": "model-00001-of-00003.safetensors", "model.layers.22.mlp.router.gate.weight": "model-00001-of-00003.safetensors", "model.layers.22.mlp.shared_experts.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.mlp.shared_experts.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.22.post_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.22.pre_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.23.mlp.expert_bias": "model-00001-of-00003.safetensors", "model.layers.23.mlp.moe_mlp.experts.weight": "model-00002-of-00003.safetensors", "model.layers.23.mlp.moe_mlp.output_experts.weight": "model-00002-of-00003.safetensors", "model.layers.23.mlp.router.gate.weight": "model-00001-of-00003.safetensors", "model.layers.23.mlp.shared_experts.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.mlp.shared_experts.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.23.post_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.23.pre_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.24.mlp.expert_bias": "model-00002-of-00003.safetensors", "model.layers.24.mlp.moe_mlp.experts.weight": "model-00002-of-00003.safetensors", "model.layers.24.mlp.moe_mlp.output_experts.weight": "model-00002-of-00003.safetensors", "model.layers.24.mlp.router.gate.weight": "model-00002-of-00003.safetensors", "model.layers.24.mlp.shared_experts.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.mlp.shared_experts.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.24.post_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.24.pre_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.25.mlp.expert_bias": "model-00002-of-00003.safetensors", "model.layers.25.mlp.moe_mlp.experts.weight": "model-00002-of-00003.safetensors", "model.layers.25.mlp.moe_mlp.output_experts.weight": "model-00002-of-00003.safetensors", "model.layers.25.mlp.router.gate.weight": "model-00002-of-00003.safetensors", "model.layers.25.mlp.shared_experts.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.mlp.shared_experts.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.25.post_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.25.pre_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.25.self_attn.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.26.mlp.expert_bias": "model-00002-of-00003.safetensors", "model.layers.26.mlp.moe_mlp.experts.weight": "model-00002-of-00003.safetensors", "model.layers.26.mlp.moe_mlp.output_experts.weight": "model-00002-of-00003.safetensors", "model.layers.26.mlp.router.gate.weight": "model-00002-of-00003.safetensors", "model.layers.26.mlp.shared_experts.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.mlp.shared_experts.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.26.post_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.26.pre_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.26.self_attn.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.27.mlp.expert_bias": "model-00002-of-00003.safetensors", "model.layers.27.mlp.moe_mlp.experts.weight": "model-00002-of-00003.safetensors", "model.layers.27.mlp.moe_mlp.output_experts.weight": "model-00002-of-00003.safetensors", "model.layers.27.mlp.router.gate.weight": "model-00002-of-00003.safetensors", "model.layers.27.mlp.shared_experts.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.mlp.shared_experts.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.27.post_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.27.pre_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.27.self_attn.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.28.mlp.expert_bias": "model-00002-of-00003.safetensors", "model.layers.28.mlp.moe_mlp.experts.weight": "model-00002-of-00003.safetensors", "model.layers.28.mlp.moe_mlp.output_experts.weight": "model-00002-of-00003.safetensors", "model.layers.28.mlp.router.gate.weight": "model-00002-of-00003.safetensors", "model.layers.28.mlp.shared_experts.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.mlp.shared_experts.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.mlp.shared_experts.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.28.post_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.28.pre_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.28.self_attn.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.29.mlp.expert_bias": "model-00002-of-00003.safetensors", "model.layers.29.mlp.moe_mlp.experts.weight": "model-00002-of-00003.safetensors", "model.layers.29.mlp.moe_mlp.output_experts.weight": "model-00002-of-00003.safetensors", "model.layers.29.mlp.router.gate.weight": "model-00002-of-00003.safetensors", "model.layers.29.mlp.shared_experts.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.mlp.shared_experts.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.mlp.shared_experts.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.29.post_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.29.pre_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.29.self_attn.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.3.mlp.expert_bias": "model-00001-of-00003.safetensors", "model.layers.3.mlp.moe_mlp.experts.weight": "model-00001-of-00003.safetensors", "model.layers.3.mlp.moe_mlp.output_experts.weight": "model-00001-of-00003.safetensors", "model.layers.3.mlp.router.gate.weight": "model-00001-of-00003.safetensors", "model.layers.3.mlp.shared_experts.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.mlp.shared_experts.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.3.post_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.3.pre_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.30.mlp.expert_bias": "model-00002-of-00003.safetensors", "model.layers.30.mlp.moe_mlp.experts.weight": "model-00002-of-00003.safetensors", "model.layers.30.mlp.moe_mlp.output_experts.weight": "model-00002-of-00003.safetensors", "model.layers.30.mlp.router.gate.weight": "model-00002-of-00003.safetensors", "model.layers.30.mlp.shared_experts.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.mlp.shared_experts.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.mlp.shared_experts.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.30.post_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.30.pre_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.30.self_attn.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.31.mlp.expert_bias": "model-00002-of-00003.safetensors", "model.layers.31.mlp.moe_mlp.experts.weight": "model-00002-of-00003.safetensors", "model.layers.31.mlp.moe_mlp.output_experts.weight": "model-00002-of-00003.safetensors", "model.layers.31.mlp.router.gate.weight": "model-00002-of-00003.safetensors", "model.layers.31.mlp.shared_experts.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.31.mlp.shared_experts.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.31.mlp.shared_experts.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.31.post_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.31.pre_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.31.self_attn.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.32.mlp.expert_bias": "model-00002-of-00003.safetensors", "model.layers.32.mlp.moe_mlp.experts.weight": "model-00002-of-00003.safetensors", "model.layers.32.mlp.moe_mlp.output_experts.weight": "model-00002-of-00003.safetensors", "model.layers.32.mlp.router.gate.weight": "model-00002-of-00003.safetensors", "model.layers.32.mlp.shared_experts.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.32.mlp.shared_experts.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.32.mlp.shared_experts.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.32.post_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.32.pre_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.32.self_attn.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.33.mlp.expert_bias": "model-00002-of-00003.safetensors", "model.layers.33.mlp.moe_mlp.experts.weight": "model-00002-of-00003.safetensors", "model.layers.33.mlp.moe_mlp.output_experts.weight": "model-00002-of-00003.safetensors", "model.layers.33.mlp.router.gate.weight": "model-00002-of-00003.safetensors", "model.layers.33.mlp.shared_experts.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.33.mlp.shared_experts.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.33.mlp.shared_experts.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.33.post_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.33.pre_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.33.self_attn.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.34.mlp.expert_bias": "model-00002-of-00003.safetensors", "model.layers.34.mlp.moe_mlp.experts.weight": "model-00002-of-00003.safetensors", "model.layers.34.mlp.moe_mlp.output_experts.weight": "model-00002-of-00003.safetensors", "model.layers.34.mlp.router.gate.weight": "model-00002-of-00003.safetensors", "model.layers.34.mlp.shared_experts.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.34.mlp.shared_experts.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.34.mlp.shared_experts.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.34.post_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.34.pre_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.34.self_attn.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.35.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.35.mlp.expert_bias": "model-00002-of-00003.safetensors", "model.layers.35.mlp.moe_mlp.experts.weight": "model-00002-of-00003.safetensors", "model.layers.35.mlp.moe_mlp.output_experts.weight": "model-00002-of-00003.safetensors", "model.layers.35.mlp.router.gate.weight": "model-00002-of-00003.safetensors", "model.layers.35.mlp.shared_experts.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.35.mlp.shared_experts.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.35.mlp.shared_experts.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.35.post_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.35.pre_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.35.self_attn.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.36.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.36.mlp.expert_bias": "model-00002-of-00003.safetensors", "model.layers.36.mlp.moe_mlp.experts.weight": "model-00002-of-00003.safetensors", "model.layers.36.mlp.moe_mlp.output_experts.weight": "model-00002-of-00003.safetensors", "model.layers.36.mlp.router.gate.weight": "model-00002-of-00003.safetensors", "model.layers.36.mlp.shared_experts.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.36.mlp.shared_experts.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.36.mlp.shared_experts.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.36.post_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.36.pre_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.36.self_attn.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.36.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.36.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.37.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.37.mlp.expert_bias": "model-00002-of-00003.safetensors", "model.layers.37.mlp.moe_mlp.experts.weight": "model-00002-of-00003.safetensors", "model.layers.37.mlp.moe_mlp.output_experts.weight": "model-00002-of-00003.safetensors", "model.layers.37.mlp.router.gate.weight": "model-00002-of-00003.safetensors", "model.layers.37.mlp.shared_experts.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.37.mlp.shared_experts.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.37.mlp.shared_experts.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.37.post_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.37.pre_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.37.self_attn.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.37.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.37.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.38.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.38.mlp.expert_bias": "model-00002-of-00003.safetensors", "model.layers.38.mlp.moe_mlp.experts.weight": "model-00002-of-00003.safetensors", "model.layers.38.mlp.moe_mlp.output_experts.weight": "model-00002-of-00003.safetensors", "model.layers.38.mlp.router.gate.weight": "model-00002-of-00003.safetensors", "model.layers.38.mlp.shared_experts.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.38.mlp.shared_experts.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.38.mlp.shared_experts.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.38.post_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.38.pre_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.38.self_attn.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.38.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.38.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.39.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.39.mlp.expert_bias": "model-00002-of-00003.safetensors", "model.layers.39.mlp.moe_mlp.experts.weight": "model-00002-of-00003.safetensors", "model.layers.39.mlp.moe_mlp.output_experts.weight": "model-00002-of-00003.safetensors", "model.layers.39.mlp.router.gate.weight": "model-00002-of-00003.safetensors", "model.layers.39.mlp.shared_experts.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.39.mlp.shared_experts.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.39.mlp.shared_experts.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.39.post_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.39.pre_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.39.self_attn.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.39.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.39.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.4.mlp.expert_bias": "model-00001-of-00003.safetensors", "model.layers.4.mlp.moe_mlp.experts.weight": "model-00001-of-00003.safetensors", "model.layers.4.mlp.moe_mlp.output_experts.weight": "model-00001-of-00003.safetensors", "model.layers.4.mlp.router.gate.weight": "model-00001-of-00003.safetensors", "model.layers.4.mlp.shared_experts.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.mlp.shared_experts.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.4.post_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.4.pre_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.40.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.40.mlp.expert_bias": "model-00002-of-00003.safetensors", "model.layers.40.mlp.moe_mlp.experts.weight": "model-00002-of-00003.safetensors", "model.layers.40.mlp.moe_mlp.output_experts.weight": "model-00002-of-00003.safetensors", "model.layers.40.mlp.router.gate.weight": "model-00002-of-00003.safetensors", "model.layers.40.mlp.shared_experts.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.40.mlp.shared_experts.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.40.mlp.shared_experts.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.40.post_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.40.pre_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.40.self_attn.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.40.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.40.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.41.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.41.mlp.expert_bias": "model-00002-of-00003.safetensors", "model.layers.41.mlp.moe_mlp.experts.weight": "model-00002-of-00003.safetensors", "model.layers.41.mlp.moe_mlp.output_experts.weight": "model-00002-of-00003.safetensors", "model.layers.41.mlp.router.gate.weight": "model-00002-of-00003.safetensors", "model.layers.41.mlp.shared_experts.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.41.mlp.shared_experts.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.41.mlp.shared_experts.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.41.post_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.41.pre_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.41.self_attn.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.41.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.41.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.42.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.42.mlp.expert_bias": "model-00002-of-00003.safetensors", "model.layers.42.mlp.moe_mlp.experts.weight": "model-00002-of-00003.safetensors", "model.layers.42.mlp.moe_mlp.output_experts.weight": "model-00002-of-00003.safetensors", "model.layers.42.mlp.router.gate.weight": "model-00002-of-00003.safetensors", "model.layers.42.mlp.shared_experts.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.42.mlp.shared_experts.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.42.mlp.shared_experts.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.42.post_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.42.pre_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.42.self_attn.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.42.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.42.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.43.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.43.mlp.expert_bias": "model-00002-of-00003.safetensors", "model.layers.43.mlp.moe_mlp.experts.weight": "model-00002-of-00003.safetensors", "model.layers.43.mlp.moe_mlp.output_experts.weight": "model-00002-of-00003.safetensors", "model.layers.43.mlp.router.gate.weight": "model-00002-of-00003.safetensors", "model.layers.43.mlp.shared_experts.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.43.mlp.shared_experts.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.43.mlp.shared_experts.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.43.post_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.43.pre_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.43.self_attn.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.43.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.43.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.44.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.44.mlp.expert_bias": "model-00002-of-00003.safetensors", "model.layers.44.mlp.moe_mlp.experts.weight": "model-00002-of-00003.safetensors", "model.layers.44.mlp.moe_mlp.output_experts.weight": "model-00002-of-00003.safetensors", "model.layers.44.mlp.router.gate.weight": "model-00002-of-00003.safetensors", "model.layers.44.mlp.shared_experts.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.44.mlp.shared_experts.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.44.mlp.shared_experts.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.44.post_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.44.pre_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.44.self_attn.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.44.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.44.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.45.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.45.mlp.expert_bias": "model-00002-of-00003.safetensors", "model.layers.45.mlp.moe_mlp.experts.weight": "model-00002-of-00003.safetensors", "model.layers.45.mlp.moe_mlp.output_experts.weight": "model-00002-of-00003.safetensors", "model.layers.45.mlp.router.gate.weight": "model-00002-of-00003.safetensors", "model.layers.45.mlp.shared_experts.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.45.mlp.shared_experts.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.45.mlp.shared_experts.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.45.post_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.45.pre_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.45.self_attn.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.45.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.45.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.46.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.46.mlp.expert_bias": "model-00002-of-00003.safetensors", "model.layers.46.mlp.moe_mlp.experts.weight": "model-00002-of-00003.safetensors", "model.layers.46.mlp.moe_mlp.output_experts.weight": "model-00003-of-00003.safetensors", "model.layers.46.mlp.router.gate.weight": "model-00002-of-00003.safetensors", "model.layers.46.mlp.shared_experts.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.46.mlp.shared_experts.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.46.mlp.shared_experts.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.46.post_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.46.pre_mlp_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.46.self_attn.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.46.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.46.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.47.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.47.mlp.expert_bias": "model-00003-of-00003.safetensors", "model.layers.47.mlp.moe_mlp.experts.weight": "model-00003-of-00003.safetensors", "model.layers.47.mlp.moe_mlp.output_experts.weight": "model-00003-of-00003.safetensors", "model.layers.47.mlp.router.gate.weight": "model-00003-of-00003.safetensors", "model.layers.47.mlp.shared_experts.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.47.mlp.shared_experts.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.47.mlp.shared_experts.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.47.post_mlp_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.47.pre_mlp_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.47.self_attn.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.47.self_attn.k_norm.weight": "model-00003-of-00003.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.47.self_attn.q_norm.weight": "model-00003-of-00003.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.48.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.48.mlp.expert_bias": "model-00003-of-00003.safetensors", "model.layers.48.mlp.moe_mlp.experts.weight": "model-00003-of-00003.safetensors", "model.layers.48.mlp.moe_mlp.output_experts.weight": "model-00003-of-00003.safetensors", "model.layers.48.mlp.router.gate.weight": "model-00003-of-00003.safetensors", "model.layers.48.mlp.shared_experts.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.48.mlp.shared_experts.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.48.mlp.shared_experts.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.48.post_mlp_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.48.pre_mlp_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.48.self_attn.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.48.self_attn.k_norm.weight": "model-00003-of-00003.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.48.self_attn.q_norm.weight": "model-00003-of-00003.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.49.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.49.mlp.expert_bias": "model-00003-of-00003.safetensors", "model.layers.49.mlp.moe_mlp.experts.weight": "model-00003-of-00003.safetensors", "model.layers.49.mlp.moe_mlp.output_experts.weight": "model-00003-of-00003.safetensors", "model.layers.49.mlp.router.gate.weight": "model-00003-of-00003.safetensors", "model.layers.49.mlp.shared_experts.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.49.mlp.shared_experts.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.49.mlp.shared_experts.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.49.post_mlp_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.49.pre_mlp_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.49.self_attn.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.49.self_attn.k_norm.weight": "model-00003-of-00003.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.49.self_attn.q_norm.weight": "model-00003-of-00003.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.5.mlp.expert_bias": "model-00001-of-00003.safetensors", "model.layers.5.mlp.moe_mlp.experts.weight": "model-00001-of-00003.safetensors", "model.layers.5.mlp.moe_mlp.output_experts.weight": "model-00001-of-00003.safetensors", "model.layers.5.mlp.router.gate.weight": "model-00001-of-00003.safetensors", "model.layers.5.mlp.shared_experts.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.mlp.shared_experts.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.5.post_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.5.pre_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.50.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.50.mlp.expert_bias": "model-00003-of-00003.safetensors", "model.layers.50.mlp.moe_mlp.experts.weight": "model-00003-of-00003.safetensors", "model.layers.50.mlp.moe_mlp.output_experts.weight": "model-00003-of-00003.safetensors", "model.layers.50.mlp.router.gate.weight": "model-00003-of-00003.safetensors", "model.layers.50.mlp.shared_experts.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.50.mlp.shared_experts.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.50.mlp.shared_experts.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.50.post_mlp_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.50.pre_mlp_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.50.self_attn.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.50.self_attn.k_norm.weight": "model-00003-of-00003.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.50.self_attn.q_norm.weight": "model-00003-of-00003.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.51.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.51.mlp.expert_bias": "model-00003-of-00003.safetensors", "model.layers.51.mlp.moe_mlp.experts.weight": "model-00003-of-00003.safetensors", "model.layers.51.mlp.moe_mlp.output_experts.weight": "model-00003-of-00003.safetensors", "model.layers.51.mlp.router.gate.weight": "model-00003-of-00003.safetensors", "model.layers.51.mlp.shared_experts.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.51.mlp.shared_experts.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.51.mlp.shared_experts.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.51.post_mlp_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.51.pre_mlp_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.51.self_attn.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.51.self_attn.k_norm.weight": "model-00003-of-00003.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.51.self_attn.q_norm.weight": "model-00003-of-00003.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.52.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.52.mlp.expert_bias": "model-00003-of-00003.safetensors", "model.layers.52.mlp.moe_mlp.experts.weight": "model-00003-of-00003.safetensors", "model.layers.52.mlp.moe_mlp.output_experts.weight": "model-00003-of-00003.safetensors", "model.layers.52.mlp.router.gate.weight": "model-00003-of-00003.safetensors", "model.layers.52.mlp.shared_experts.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.52.mlp.shared_experts.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.52.mlp.shared_experts.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.52.post_mlp_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.52.pre_mlp_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.52.self_attn.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.52.self_attn.k_norm.weight": "model-00003-of-00003.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.52.self_attn.q_norm.weight": "model-00003-of-00003.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.53.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.53.mlp.expert_bias": "model-00003-of-00003.safetensors", "model.layers.53.mlp.moe_mlp.experts.weight": "model-00003-of-00003.safetensors", "model.layers.53.mlp.moe_mlp.output_experts.weight": "model-00003-of-00003.safetensors", "model.layers.53.mlp.router.gate.weight": "model-00003-of-00003.safetensors", "model.layers.53.mlp.shared_experts.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.53.mlp.shared_experts.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.53.mlp.shared_experts.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.53.post_mlp_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.53.pre_mlp_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.53.self_attn.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.53.self_attn.k_norm.weight": "model-00003-of-00003.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.53.self_attn.q_norm.weight": "model-00003-of-00003.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.54.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.54.mlp.expert_bias": "model-00003-of-00003.safetensors", "model.layers.54.mlp.moe_mlp.experts.weight": "model-00003-of-00003.safetensors", "model.layers.54.mlp.moe_mlp.output_experts.weight": "model-00003-of-00003.safetensors", "model.layers.54.mlp.router.gate.weight": "model-00003-of-00003.safetensors", "model.layers.54.mlp.shared_experts.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.54.mlp.shared_experts.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.54.mlp.shared_experts.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.54.post_mlp_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.54.pre_mlp_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.54.self_attn.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.54.self_attn.k_norm.weight": "model-00003-of-00003.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.54.self_attn.q_norm.weight": "model-00003-of-00003.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.55.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.55.mlp.expert_bias": "model-00003-of-00003.safetensors", "model.layers.55.mlp.moe_mlp.experts.weight": "model-00003-of-00003.safetensors", "model.layers.55.mlp.moe_mlp.output_experts.weight": "model-00003-of-00003.safetensors", "model.layers.55.mlp.router.gate.weight": "model-00003-of-00003.safetensors", "model.layers.55.mlp.shared_experts.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.55.mlp.shared_experts.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.55.mlp.shared_experts.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.55.post_mlp_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.55.pre_mlp_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.55.self_attn.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.55.self_attn.k_norm.weight": "model-00003-of-00003.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.55.self_attn.q_norm.weight": "model-00003-of-00003.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.6.mlp.expert_bias": "model-00001-of-00003.safetensors", "model.layers.6.mlp.moe_mlp.experts.weight": "model-00001-of-00003.safetensors", "model.layers.6.mlp.moe_mlp.output_experts.weight": "model-00001-of-00003.safetensors", "model.layers.6.mlp.router.gate.weight": "model-00001-of-00003.safetensors", "model.layers.6.mlp.shared_experts.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.mlp.shared_experts.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.6.post_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.6.pre_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.7.mlp.expert_bias": "model-00001-of-00003.safetensors", "model.layers.7.mlp.moe_mlp.experts.weight": "model-00001-of-00003.safetensors", "model.layers.7.mlp.moe_mlp.output_experts.weight": "model-00001-of-00003.safetensors", "model.layers.7.mlp.router.gate.weight": "model-00001-of-00003.safetensors", "model.layers.7.mlp.shared_experts.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.mlp.shared_experts.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.7.post_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.7.pre_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.expert_bias": "model-00001-of-00003.safetensors", "model.layers.8.mlp.moe_mlp.experts.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.moe_mlp.output_experts.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.router.gate.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.shared_experts.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.shared_experts.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.8.post_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.8.pre_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.expert_bias": "model-00001-of-00003.safetensors", "model.layers.9.mlp.moe_mlp.experts.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.moe_mlp.output_experts.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.router.gate.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.shared_experts.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.shared_experts.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.9.post_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.9.pre_mlp_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.norm.weight": "model-00003-of-00003.safetensors" } }