| { |
| "metadata": { |
| "total_size": 27764509198 |
| }, |
| "weight_map": { |
| "lm_head.biases": "model-00001-of-00006.safetensors", |
| "lm_head.scales": "model-00001-of-00006.safetensors", |
| "lm_head.weight": "model-00001-of-00006.safetensors", |
| "model.embed_tokens.biases": "model-00001-of-00006.safetensors", |
| "model.embed_tokens.scales": "model-00001-of-00006.safetensors", |
| "model.embed_tokens.weight": "model-00001-of-00006.safetensors", |
| "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.0.mlp.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.0.mlp.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.0.mlp.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.0.mlp.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.0.post_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.0.pre_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.0.self_attn.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.0.self_attn.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.0.self_attn.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.1.mlp.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.1.mlp.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.1.mlp.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.1.mlp.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.1.post_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.1.pre_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.1.self_attn.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.1.self_attn.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.1.self_attn.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.10.input_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.10.mlp.expert_bias": "model-00001-of-00006.safetensors", |
| "model.layers.10.mlp.experts.down_proj.biases": "model-00002-of-00006.safetensors", |
| "model.layers.10.mlp.experts.down_proj.scales": "model-00002-of-00006.safetensors", |
| "model.layers.10.mlp.experts.down_proj.weight": "model-00002-of-00006.safetensors", |
| "model.layers.10.mlp.experts.gate_proj.biases": "model-00002-of-00006.safetensors", |
| "model.layers.10.mlp.experts.gate_proj.scales": "model-00002-of-00006.safetensors", |
| "model.layers.10.mlp.experts.gate_proj.weight": "model-00002-of-00006.safetensors", |
| "model.layers.10.mlp.experts.up_proj.biases": "model-00002-of-00006.safetensors", |
| "model.layers.10.mlp.experts.up_proj.scales": "model-00002-of-00006.safetensors", |
| "model.layers.10.mlp.experts.up_proj.weight": "model-00002-of-00006.safetensors", |
| "model.layers.10.mlp.router.gate.weight": "model-00001-of-00006.safetensors", |
| "model.layers.10.mlp.shared_experts.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.10.mlp.shared_experts.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.10.mlp.shared_experts.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.10.mlp.shared_experts.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.10.mlp.shared_experts.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.10.mlp.shared_experts.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.10.mlp.shared_experts.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.10.mlp.shared_experts.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.10.post_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.10.pre_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.10.self_attn.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.10.self_attn.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.10.self_attn.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.11.input_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.11.mlp.expert_bias": "model-00001-of-00006.safetensors", |
| "model.layers.11.mlp.experts.down_proj.biases": "model-00002-of-00006.safetensors", |
| "model.layers.11.mlp.experts.down_proj.scales": "model-00002-of-00006.safetensors", |
| "model.layers.11.mlp.experts.down_proj.weight": "model-00002-of-00006.safetensors", |
| "model.layers.11.mlp.experts.gate_proj.biases": "model-00003-of-00006.safetensors", |
| "model.layers.11.mlp.experts.gate_proj.scales": "model-00003-of-00006.safetensors", |
| "model.layers.11.mlp.experts.gate_proj.weight": "model-00003-of-00006.safetensors", |
| "model.layers.11.mlp.experts.up_proj.biases": "model-00002-of-00006.safetensors", |
| "model.layers.11.mlp.experts.up_proj.scales": "model-00002-of-00006.safetensors", |
| "model.layers.11.mlp.experts.up_proj.weight": "model-00002-of-00006.safetensors", |
| "model.layers.11.mlp.router.gate.weight": "model-00001-of-00006.safetensors", |
| "model.layers.11.mlp.shared_experts.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.11.mlp.shared_experts.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.11.mlp.shared_experts.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.11.mlp.shared_experts.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.11.mlp.shared_experts.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.11.mlp.shared_experts.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.11.mlp.shared_experts.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.11.mlp.shared_experts.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.11.post_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.11.pre_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.11.self_attn.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.11.self_attn.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.11.self_attn.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.12.input_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.12.mlp.expert_bias": "model-00001-of-00006.safetensors", |
| "model.layers.12.mlp.experts.down_proj.biases": "model-00003-of-00006.safetensors", |
| "model.layers.12.mlp.experts.down_proj.scales": "model-00003-of-00006.safetensors", |
| "model.layers.12.mlp.experts.down_proj.weight": "model-00003-of-00006.safetensors", |
| "model.layers.12.mlp.experts.gate_proj.biases": "model-00003-of-00006.safetensors", |
| "model.layers.12.mlp.experts.gate_proj.scales": "model-00003-of-00006.safetensors", |
| "model.layers.12.mlp.experts.gate_proj.weight": "model-00003-of-00006.safetensors", |
| "model.layers.12.mlp.experts.up_proj.biases": "model-00003-of-00006.safetensors", |
| "model.layers.12.mlp.experts.up_proj.scales": "model-00003-of-00006.safetensors", |
| "model.layers.12.mlp.experts.up_proj.weight": "model-00003-of-00006.safetensors", |
| "model.layers.12.mlp.router.gate.weight": "model-00001-of-00006.safetensors", |
| "model.layers.12.mlp.shared_experts.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.12.mlp.shared_experts.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.12.mlp.shared_experts.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.12.mlp.shared_experts.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.12.mlp.shared_experts.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.12.mlp.shared_experts.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.12.mlp.shared_experts.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.12.mlp.shared_experts.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.12.post_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.12.pre_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.12.self_attn.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.12.self_attn.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.12.self_attn.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.12.self_attn.k_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.12.self_attn.q_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.12.self_attn.v_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.13.input_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.13.mlp.expert_bias": "model-00001-of-00006.safetensors", |
| "model.layers.13.mlp.experts.down_proj.biases": "model-00003-of-00006.safetensors", |
| "model.layers.13.mlp.experts.down_proj.scales": "model-00003-of-00006.safetensors", |
| "model.layers.13.mlp.experts.down_proj.weight": "model-00003-of-00006.safetensors", |
| "model.layers.13.mlp.experts.gate_proj.biases": "model-00003-of-00006.safetensors", |
| "model.layers.13.mlp.experts.gate_proj.scales": "model-00003-of-00006.safetensors", |
| "model.layers.13.mlp.experts.gate_proj.weight": "model-00003-of-00006.safetensors", |
| "model.layers.13.mlp.experts.up_proj.biases": "model-00003-of-00006.safetensors", |
| "model.layers.13.mlp.experts.up_proj.scales": "model-00003-of-00006.safetensors", |
| "model.layers.13.mlp.experts.up_proj.weight": "model-00003-of-00006.safetensors", |
| "model.layers.13.mlp.router.gate.weight": "model-00001-of-00006.safetensors", |
| "model.layers.13.mlp.shared_experts.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.13.mlp.shared_experts.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.13.mlp.shared_experts.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.13.mlp.shared_experts.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.13.mlp.shared_experts.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.13.mlp.shared_experts.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.13.mlp.shared_experts.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.13.mlp.shared_experts.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.13.post_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.13.pre_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.13.self_attn.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.13.self_attn.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.13.self_attn.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.13.self_attn.k_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.13.self_attn.v_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.14.input_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.14.mlp.expert_bias": "model-00001-of-00006.safetensors", |
| "model.layers.14.mlp.experts.down_proj.biases": "model-00003-of-00006.safetensors", |
| "model.layers.14.mlp.experts.down_proj.scales": "model-00003-of-00006.safetensors", |
| "model.layers.14.mlp.experts.down_proj.weight": "model-00003-of-00006.safetensors", |
| "model.layers.14.mlp.experts.gate_proj.biases": "model-00003-of-00006.safetensors", |
| "model.layers.14.mlp.experts.gate_proj.scales": "model-00003-of-00006.safetensors", |
| "model.layers.14.mlp.experts.gate_proj.weight": "model-00003-of-00006.safetensors", |
| "model.layers.14.mlp.experts.up_proj.biases": "model-00003-of-00006.safetensors", |
| "model.layers.14.mlp.experts.up_proj.scales": "model-00003-of-00006.safetensors", |
| "model.layers.14.mlp.experts.up_proj.weight": "model-00003-of-00006.safetensors", |
| "model.layers.14.mlp.router.gate.weight": "model-00001-of-00006.safetensors", |
| "model.layers.14.mlp.shared_experts.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.14.mlp.shared_experts.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.14.mlp.shared_experts.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.14.mlp.shared_experts.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.14.mlp.shared_experts.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.14.mlp.shared_experts.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.14.mlp.shared_experts.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.14.mlp.shared_experts.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.14.post_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.14.pre_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.14.self_attn.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.14.self_attn.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.14.self_attn.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.14.self_attn.o_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.15.input_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.15.mlp.expert_bias": "model-00001-of-00006.safetensors", |
| "model.layers.15.mlp.experts.down_proj.biases": "model-00003-of-00006.safetensors", |
| "model.layers.15.mlp.experts.down_proj.scales": "model-00003-of-00006.safetensors", |
| "model.layers.15.mlp.experts.down_proj.weight": "model-00003-of-00006.safetensors", |
| "model.layers.15.mlp.experts.gate_proj.biases": "model-00003-of-00006.safetensors", |
| "model.layers.15.mlp.experts.gate_proj.scales": "model-00003-of-00006.safetensors", |
| "model.layers.15.mlp.experts.gate_proj.weight": "model-00003-of-00006.safetensors", |
| "model.layers.15.mlp.experts.up_proj.biases": "model-00003-of-00006.safetensors", |
| "model.layers.15.mlp.experts.up_proj.scales": "model-00003-of-00006.safetensors", |
| "model.layers.15.mlp.experts.up_proj.weight": "model-00003-of-00006.safetensors", |
| "model.layers.15.mlp.router.gate.weight": "model-00001-of-00006.safetensors", |
| "model.layers.15.mlp.shared_experts.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.15.mlp.shared_experts.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.15.mlp.shared_experts.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.15.mlp.shared_experts.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.15.mlp.shared_experts.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.15.mlp.shared_experts.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.15.mlp.shared_experts.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.15.mlp.shared_experts.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.15.post_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.15.pre_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.15.self_attn.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.15.self_attn.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.15.self_attn.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.15.self_attn.k_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.15.self_attn.o_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.15.self_attn.q_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.15.self_attn.v_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.16.input_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.16.mlp.expert_bias": "model-00001-of-00006.safetensors", |
| "model.layers.16.mlp.experts.down_proj.biases": "model-00003-of-00006.safetensors", |
| "model.layers.16.mlp.experts.down_proj.scales": "model-00003-of-00006.safetensors", |
| "model.layers.16.mlp.experts.down_proj.weight": "model-00003-of-00006.safetensors", |
| "model.layers.16.mlp.experts.gate_proj.biases": "model-00003-of-00006.safetensors", |
| "model.layers.16.mlp.experts.gate_proj.scales": "model-00003-of-00006.safetensors", |
| "model.layers.16.mlp.experts.gate_proj.weight": "model-00003-of-00006.safetensors", |
| "model.layers.16.mlp.experts.up_proj.biases": "model-00003-of-00006.safetensors", |
| "model.layers.16.mlp.experts.up_proj.scales": "model-00003-of-00006.safetensors", |
| "model.layers.16.mlp.experts.up_proj.weight": "model-00003-of-00006.safetensors", |
| "model.layers.16.mlp.router.gate.weight": "model-00001-of-00006.safetensors", |
| "model.layers.16.mlp.shared_experts.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.16.mlp.shared_experts.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.16.mlp.shared_experts.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.16.mlp.shared_experts.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.16.mlp.shared_experts.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.16.mlp.shared_experts.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.16.mlp.shared_experts.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.16.mlp.shared_experts.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.16.post_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.16.pre_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.16.self_attn.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.16.self_attn.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.16.self_attn.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.16.self_attn.k_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.16.self_attn.o_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.16.self_attn.q_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.16.self_attn.v_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.17.input_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.17.mlp.expert_bias": "model-00001-of-00006.safetensors", |
| "model.layers.17.mlp.experts.down_proj.biases": "model-00003-of-00006.safetensors", |
| "model.layers.17.mlp.experts.down_proj.scales": "model-00003-of-00006.safetensors", |
| "model.layers.17.mlp.experts.down_proj.weight": "model-00003-of-00006.safetensors", |
| "model.layers.17.mlp.experts.gate_proj.biases": "model-00004-of-00006.safetensors", |
| "model.layers.17.mlp.experts.gate_proj.scales": "model-00004-of-00006.safetensors", |
| "model.layers.17.mlp.experts.gate_proj.weight": "model-00004-of-00006.safetensors", |
| "model.layers.17.mlp.experts.up_proj.biases": "model-00003-of-00006.safetensors", |
| "model.layers.17.mlp.experts.up_proj.scales": "model-00003-of-00006.safetensors", |
| "model.layers.17.mlp.experts.up_proj.weight": "model-00003-of-00006.safetensors", |
| "model.layers.17.mlp.router.gate.weight": "model-00001-of-00006.safetensors", |
| "model.layers.17.mlp.shared_experts.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.17.mlp.shared_experts.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.17.mlp.shared_experts.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.17.mlp.shared_experts.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.17.mlp.shared_experts.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.17.mlp.shared_experts.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.17.mlp.shared_experts.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.17.mlp.shared_experts.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.17.post_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.17.pre_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.17.self_attn.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.17.self_attn.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.17.self_attn.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.17.self_attn.k_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.17.self_attn.o_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.17.self_attn.q_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.17.self_attn.v_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.18.input_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.18.mlp.expert_bias": "model-00001-of-00006.safetensors", |
| "model.layers.18.mlp.experts.down_proj.biases": "model-00004-of-00006.safetensors", |
| "model.layers.18.mlp.experts.down_proj.scales": "model-00004-of-00006.safetensors", |
| "model.layers.18.mlp.experts.down_proj.weight": "model-00004-of-00006.safetensors", |
| "model.layers.18.mlp.experts.gate_proj.biases": "model-00004-of-00006.safetensors", |
| "model.layers.18.mlp.experts.gate_proj.scales": "model-00004-of-00006.safetensors", |
| "model.layers.18.mlp.experts.gate_proj.weight": "model-00004-of-00006.safetensors", |
| "model.layers.18.mlp.experts.up_proj.biases": "model-00004-of-00006.safetensors", |
| "model.layers.18.mlp.experts.up_proj.scales": "model-00004-of-00006.safetensors", |
| "model.layers.18.mlp.experts.up_proj.weight": "model-00004-of-00006.safetensors", |
| "model.layers.18.mlp.router.gate.weight": "model-00001-of-00006.safetensors", |
| "model.layers.18.mlp.shared_experts.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.18.mlp.shared_experts.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.18.mlp.shared_experts.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.18.mlp.shared_experts.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.18.mlp.shared_experts.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.18.mlp.shared_experts.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.18.mlp.shared_experts.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.18.mlp.shared_experts.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.18.post_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.18.pre_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.18.self_attn.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.18.self_attn.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.18.self_attn.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.18.self_attn.k_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.18.self_attn.o_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.18.self_attn.q_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.18.self_attn.v_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.19.input_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.19.mlp.expert_bias": "model-00001-of-00006.safetensors", |
| "model.layers.19.mlp.experts.down_proj.biases": "model-00004-of-00006.safetensors", |
| "model.layers.19.mlp.experts.down_proj.scales": "model-00004-of-00006.safetensors", |
| "model.layers.19.mlp.experts.down_proj.weight": "model-00004-of-00006.safetensors", |
| "model.layers.19.mlp.experts.gate_proj.biases": "model-00004-of-00006.safetensors", |
| "model.layers.19.mlp.experts.gate_proj.scales": "model-00004-of-00006.safetensors", |
| "model.layers.19.mlp.experts.gate_proj.weight": "model-00004-of-00006.safetensors", |
| "model.layers.19.mlp.experts.up_proj.biases": "model-00004-of-00006.safetensors", |
| "model.layers.19.mlp.experts.up_proj.scales": "model-00004-of-00006.safetensors", |
| "model.layers.19.mlp.experts.up_proj.weight": "model-00004-of-00006.safetensors", |
| "model.layers.19.mlp.router.gate.weight": "model-00001-of-00006.safetensors", |
| "model.layers.19.mlp.shared_experts.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.19.mlp.shared_experts.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.19.mlp.shared_experts.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.19.mlp.shared_experts.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.19.mlp.shared_experts.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.19.mlp.shared_experts.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.19.mlp.shared_experts.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.19.mlp.shared_experts.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.19.post_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.19.pre_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.19.self_attn.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.19.self_attn.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.19.self_attn.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.19.self_attn.k_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.19.self_attn.o_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.19.self_attn.q_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.19.self_attn.v_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.2.mlp.expert_bias": "model-00001-of-00006.safetensors", |
| "model.layers.2.mlp.experts.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.2.mlp.experts.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.2.mlp.experts.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.2.mlp.experts.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.2.mlp.experts.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.2.mlp.experts.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.2.mlp.experts.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.2.mlp.experts.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.2.mlp.experts.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.2.mlp.router.gate.weight": "model-00001-of-00006.safetensors", |
| "model.layers.2.mlp.shared_experts.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.2.mlp.shared_experts.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.2.mlp.shared_experts.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.2.mlp.shared_experts.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.2.mlp.shared_experts.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.2.mlp.shared_experts.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.2.mlp.shared_experts.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.2.mlp.shared_experts.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.2.post_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.2.pre_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.2.self_attn.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.2.self_attn.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.2.self_attn.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.20.input_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.20.mlp.expert_bias": "model-00001-of-00006.safetensors", |
| "model.layers.20.mlp.experts.down_proj.biases": "model-00004-of-00006.safetensors", |
| "model.layers.20.mlp.experts.down_proj.scales": "model-00004-of-00006.safetensors", |
| "model.layers.20.mlp.experts.down_proj.weight": "model-00004-of-00006.safetensors", |
| "model.layers.20.mlp.experts.gate_proj.biases": "model-00004-of-00006.safetensors", |
| "model.layers.20.mlp.experts.gate_proj.scales": "model-00004-of-00006.safetensors", |
| "model.layers.20.mlp.experts.gate_proj.weight": "model-00004-of-00006.safetensors", |
| "model.layers.20.mlp.experts.up_proj.biases": "model-00004-of-00006.safetensors", |
| "model.layers.20.mlp.experts.up_proj.scales": "model-00004-of-00006.safetensors", |
| "model.layers.20.mlp.experts.up_proj.weight": "model-00004-of-00006.safetensors", |
| "model.layers.20.mlp.router.gate.weight": "model-00001-of-00006.safetensors", |
| "model.layers.20.mlp.shared_experts.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.20.mlp.shared_experts.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.20.mlp.shared_experts.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.20.mlp.shared_experts.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.20.mlp.shared_experts.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.20.mlp.shared_experts.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.20.mlp.shared_experts.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.20.mlp.shared_experts.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.20.post_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.20.pre_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.20.self_attn.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.20.self_attn.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.20.self_attn.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.20.self_attn.k_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.20.self_attn.o_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.20.self_attn.q_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.20.self_attn.v_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.21.input_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.21.mlp.expert_bias": "model-00001-of-00006.safetensors", |
| "model.layers.21.mlp.experts.down_proj.biases": "model-00004-of-00006.safetensors", |
| "model.layers.21.mlp.experts.down_proj.scales": "model-00004-of-00006.safetensors", |
| "model.layers.21.mlp.experts.down_proj.weight": "model-00004-of-00006.safetensors", |
| "model.layers.21.mlp.experts.gate_proj.biases": "model-00004-of-00006.safetensors", |
| "model.layers.21.mlp.experts.gate_proj.scales": "model-00004-of-00006.safetensors", |
| "model.layers.21.mlp.experts.gate_proj.weight": "model-00004-of-00006.safetensors", |
| "model.layers.21.mlp.experts.up_proj.biases": "model-00004-of-00006.safetensors", |
| "model.layers.21.mlp.experts.up_proj.scales": "model-00004-of-00006.safetensors", |
| "model.layers.21.mlp.experts.up_proj.weight": "model-00004-of-00006.safetensors", |
| "model.layers.21.mlp.router.gate.weight": "model-00001-of-00006.safetensors", |
| "model.layers.21.mlp.shared_experts.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.21.mlp.shared_experts.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.21.mlp.shared_experts.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.21.mlp.shared_experts.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.21.mlp.shared_experts.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.21.mlp.shared_experts.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.21.mlp.shared_experts.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.21.mlp.shared_experts.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.21.post_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.21.pre_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.21.self_attn.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.21.self_attn.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.21.self_attn.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.21.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.21.self_attn.k_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.21.self_attn.o_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.21.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.21.self_attn.q_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.21.self_attn.v_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.22.input_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.22.mlp.expert_bias": "model-00001-of-00006.safetensors", |
| "model.layers.22.mlp.experts.down_proj.biases": "model-00004-of-00006.safetensors", |
| "model.layers.22.mlp.experts.down_proj.scales": "model-00004-of-00006.safetensors", |
| "model.layers.22.mlp.experts.down_proj.weight": "model-00004-of-00006.safetensors", |
| "model.layers.22.mlp.experts.gate_proj.biases": "model-00004-of-00006.safetensors", |
| "model.layers.22.mlp.experts.gate_proj.scales": "model-00004-of-00006.safetensors", |
| "model.layers.22.mlp.experts.gate_proj.weight": "model-00004-of-00006.safetensors", |
| "model.layers.22.mlp.experts.up_proj.biases": "model-00004-of-00006.safetensors", |
| "model.layers.22.mlp.experts.up_proj.scales": "model-00004-of-00006.safetensors", |
| "model.layers.22.mlp.experts.up_proj.weight": "model-00004-of-00006.safetensors", |
| "model.layers.22.mlp.router.gate.weight": "model-00001-of-00006.safetensors", |
| "model.layers.22.mlp.shared_experts.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.22.mlp.shared_experts.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.22.mlp.shared_experts.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.22.mlp.shared_experts.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.22.mlp.shared_experts.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.22.mlp.shared_experts.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.22.mlp.shared_experts.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.22.mlp.shared_experts.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.22.post_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.22.pre_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.22.self_attn.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.22.self_attn.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.22.self_attn.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.22.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.22.self_attn.k_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.22.self_attn.k_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.22.self_attn.o_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.22.self_attn.o_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.22.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.22.self_attn.q_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.22.self_attn.q_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.22.self_attn.v_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.22.self_attn.v_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.23.input_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.23.mlp.expert_bias": "model-00001-of-00006.safetensors", |
| "model.layers.23.mlp.experts.down_proj.biases": "model-00004-of-00006.safetensors", |
| "model.layers.23.mlp.experts.down_proj.scales": "model-00004-of-00006.safetensors", |
| "model.layers.23.mlp.experts.down_proj.weight": "model-00004-of-00006.safetensors", |
| "model.layers.23.mlp.experts.gate_proj.biases": "model-00005-of-00006.safetensors", |
| "model.layers.23.mlp.experts.gate_proj.scales": "model-00005-of-00006.safetensors", |
| "model.layers.23.mlp.experts.gate_proj.weight": "model-00005-of-00006.safetensors", |
| "model.layers.23.mlp.experts.up_proj.biases": "model-00004-of-00006.safetensors", |
| "model.layers.23.mlp.experts.up_proj.scales": "model-00004-of-00006.safetensors", |
| "model.layers.23.mlp.experts.up_proj.weight": "model-00004-of-00006.safetensors", |
| "model.layers.23.mlp.router.gate.weight": "model-00001-of-00006.safetensors", |
| "model.layers.23.mlp.shared_experts.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.23.mlp.shared_experts.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.23.mlp.shared_experts.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.23.mlp.shared_experts.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.23.mlp.shared_experts.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.23.mlp.shared_experts.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.23.mlp.shared_experts.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.23.mlp.shared_experts.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.23.post_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.23.pre_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.23.self_attn.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.23.self_attn.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.23.self_attn.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.23.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.23.self_attn.k_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.23.self_attn.k_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.23.self_attn.o_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.23.self_attn.o_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.23.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.23.self_attn.q_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.23.self_attn.q_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.23.self_attn.v_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.23.self_attn.v_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.24.input_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.24.mlp.expert_bias": "model-00001-of-00006.safetensors", |
| "model.layers.24.mlp.experts.down_proj.biases": "model-00005-of-00006.safetensors", |
| "model.layers.24.mlp.experts.down_proj.scales": "model-00005-of-00006.safetensors", |
| "model.layers.24.mlp.experts.down_proj.weight": "model-00005-of-00006.safetensors", |
| "model.layers.24.mlp.experts.gate_proj.biases": "model-00005-of-00006.safetensors", |
| "model.layers.24.mlp.experts.gate_proj.scales": "model-00005-of-00006.safetensors", |
| "model.layers.24.mlp.experts.gate_proj.weight": "model-00005-of-00006.safetensors", |
| "model.layers.24.mlp.experts.up_proj.biases": "model-00005-of-00006.safetensors", |
| "model.layers.24.mlp.experts.up_proj.scales": "model-00005-of-00006.safetensors", |
| "model.layers.24.mlp.experts.up_proj.weight": "model-00005-of-00006.safetensors", |
| "model.layers.24.mlp.router.gate.weight": "model-00001-of-00006.safetensors", |
| "model.layers.24.mlp.shared_experts.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.24.mlp.shared_experts.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.24.mlp.shared_experts.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.24.mlp.shared_experts.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.24.mlp.shared_experts.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.24.mlp.shared_experts.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.24.mlp.shared_experts.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.24.mlp.shared_experts.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.24.post_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.24.pre_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.24.self_attn.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.24.self_attn.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.24.self_attn.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.24.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.24.self_attn.k_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.24.self_attn.k_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.24.self_attn.o_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.24.self_attn.o_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.24.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.24.self_attn.q_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.24.self_attn.q_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.24.self_attn.v_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.24.self_attn.v_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.25.input_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.25.mlp.expert_bias": "model-00001-of-00006.safetensors", |
| "model.layers.25.mlp.experts.down_proj.biases": "model-00005-of-00006.safetensors", |
| "model.layers.25.mlp.experts.down_proj.scales": "model-00005-of-00006.safetensors", |
| "model.layers.25.mlp.experts.down_proj.weight": "model-00005-of-00006.safetensors", |
| "model.layers.25.mlp.experts.gate_proj.biases": "model-00005-of-00006.safetensors", |
| "model.layers.25.mlp.experts.gate_proj.scales": "model-00005-of-00006.safetensors", |
| "model.layers.25.mlp.experts.gate_proj.weight": "model-00005-of-00006.safetensors", |
| "model.layers.25.mlp.experts.up_proj.biases": "model-00005-of-00006.safetensors", |
| "model.layers.25.mlp.experts.up_proj.scales": "model-00005-of-00006.safetensors", |
| "model.layers.25.mlp.experts.up_proj.weight": "model-00005-of-00006.safetensors", |
| "model.layers.25.mlp.router.gate.weight": "model-00001-of-00006.safetensors", |
| "model.layers.25.mlp.shared_experts.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.25.mlp.shared_experts.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.25.mlp.shared_experts.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.25.mlp.shared_experts.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.25.mlp.shared_experts.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.25.mlp.shared_experts.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.25.mlp.shared_experts.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.25.mlp.shared_experts.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.25.post_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.25.pre_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.25.self_attn.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.25.self_attn.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.25.self_attn.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.25.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.25.self_attn.k_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.25.self_attn.k_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.25.self_attn.o_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.25.self_attn.o_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.25.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.25.self_attn.q_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.25.self_attn.q_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.25.self_attn.v_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.25.self_attn.v_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.26.input_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.26.mlp.expert_bias": "model-00001-of-00006.safetensors", |
| "model.layers.26.mlp.experts.down_proj.biases": "model-00005-of-00006.safetensors", |
| "model.layers.26.mlp.experts.down_proj.scales": "model-00005-of-00006.safetensors", |
| "model.layers.26.mlp.experts.down_proj.weight": "model-00005-of-00006.safetensors", |
| "model.layers.26.mlp.experts.gate_proj.biases": "model-00005-of-00006.safetensors", |
| "model.layers.26.mlp.experts.gate_proj.scales": "model-00005-of-00006.safetensors", |
| "model.layers.26.mlp.experts.gate_proj.weight": "model-00005-of-00006.safetensors", |
| "model.layers.26.mlp.experts.up_proj.biases": "model-00005-of-00006.safetensors", |
| "model.layers.26.mlp.experts.up_proj.scales": "model-00005-of-00006.safetensors", |
| "model.layers.26.mlp.experts.up_proj.weight": "model-00005-of-00006.safetensors", |
| "model.layers.26.mlp.router.gate.weight": "model-00001-of-00006.safetensors", |
| "model.layers.26.mlp.shared_experts.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.26.mlp.shared_experts.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.26.mlp.shared_experts.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.26.mlp.shared_experts.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.26.mlp.shared_experts.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.26.mlp.shared_experts.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.26.mlp.shared_experts.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.26.mlp.shared_experts.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.26.post_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.26.pre_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.26.self_attn.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.26.self_attn.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.26.self_attn.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.26.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.26.self_attn.k_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.26.self_attn.k_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.26.self_attn.o_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.26.self_attn.o_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.26.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.26.self_attn.q_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.26.self_attn.q_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.26.self_attn.v_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.26.self_attn.v_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.27.input_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.27.mlp.expert_bias": "model-00001-of-00006.safetensors", |
| "model.layers.27.mlp.experts.down_proj.biases": "model-00005-of-00006.safetensors", |
| "model.layers.27.mlp.experts.down_proj.scales": "model-00005-of-00006.safetensors", |
| "model.layers.27.mlp.experts.down_proj.weight": "model-00005-of-00006.safetensors", |
| "model.layers.27.mlp.experts.gate_proj.biases": "model-00005-of-00006.safetensors", |
| "model.layers.27.mlp.experts.gate_proj.scales": "model-00005-of-00006.safetensors", |
| "model.layers.27.mlp.experts.gate_proj.weight": "model-00005-of-00006.safetensors", |
| "model.layers.27.mlp.experts.up_proj.biases": "model-00005-of-00006.safetensors", |
| "model.layers.27.mlp.experts.up_proj.scales": "model-00005-of-00006.safetensors", |
| "model.layers.27.mlp.experts.up_proj.weight": "model-00005-of-00006.safetensors", |
| "model.layers.27.mlp.router.gate.weight": "model-00001-of-00006.safetensors", |
| "model.layers.27.mlp.shared_experts.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.27.mlp.shared_experts.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.27.mlp.shared_experts.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.27.mlp.shared_experts.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.27.mlp.shared_experts.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.27.mlp.shared_experts.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.27.mlp.shared_experts.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.27.mlp.shared_experts.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.27.post_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.27.pre_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.27.self_attn.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.27.self_attn.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.27.self_attn.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.27.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.27.self_attn.k_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.27.self_attn.k_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.27.self_attn.o_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.27.self_attn.o_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.27.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.27.self_attn.q_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.27.self_attn.q_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.27.self_attn.v_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.27.self_attn.v_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.28.input_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.28.mlp.expert_bias": "model-00001-of-00006.safetensors", |
| "model.layers.28.mlp.experts.down_proj.biases": "model-00005-of-00006.safetensors", |
| "model.layers.28.mlp.experts.down_proj.scales": "model-00005-of-00006.safetensors", |
| "model.layers.28.mlp.experts.down_proj.weight": "model-00005-of-00006.safetensors", |
| "model.layers.28.mlp.experts.gate_proj.biases": "model-00005-of-00006.safetensors", |
| "model.layers.28.mlp.experts.gate_proj.scales": "model-00005-of-00006.safetensors", |
| "model.layers.28.mlp.experts.gate_proj.weight": "model-00005-of-00006.safetensors", |
| "model.layers.28.mlp.experts.up_proj.biases": "model-00005-of-00006.safetensors", |
| "model.layers.28.mlp.experts.up_proj.scales": "model-00005-of-00006.safetensors", |
| "model.layers.28.mlp.experts.up_proj.weight": "model-00005-of-00006.safetensors", |
| "model.layers.28.mlp.router.gate.weight": "model-00001-of-00006.safetensors", |
| "model.layers.28.mlp.shared_experts.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.28.mlp.shared_experts.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.28.mlp.shared_experts.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.28.mlp.shared_experts.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.28.mlp.shared_experts.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.28.mlp.shared_experts.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.28.mlp.shared_experts.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.28.mlp.shared_experts.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.28.mlp.shared_experts.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.28.post_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.28.pre_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.28.self_attn.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.28.self_attn.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.28.self_attn.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.28.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.28.self_attn.k_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.28.self_attn.k_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.28.self_attn.o_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.28.self_attn.o_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.28.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.28.self_attn.q_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.28.self_attn.q_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.28.self_attn.v_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.28.self_attn.v_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.29.input_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.29.mlp.expert_bias": "model-00001-of-00006.safetensors", |
| "model.layers.29.mlp.experts.down_proj.biases": "model-00005-of-00006.safetensors", |
| "model.layers.29.mlp.experts.down_proj.scales": "model-00005-of-00006.safetensors", |
| "model.layers.29.mlp.experts.down_proj.weight": "model-00005-of-00006.safetensors", |
| "model.layers.29.mlp.experts.gate_proj.biases": "model-00006-of-00006.safetensors", |
| "model.layers.29.mlp.experts.gate_proj.scales": "model-00006-of-00006.safetensors", |
| "model.layers.29.mlp.experts.gate_proj.weight": "model-00006-of-00006.safetensors", |
| "model.layers.29.mlp.experts.up_proj.biases": "model-00005-of-00006.safetensors", |
| "model.layers.29.mlp.experts.up_proj.scales": "model-00005-of-00006.safetensors", |
| "model.layers.29.mlp.experts.up_proj.weight": "model-00005-of-00006.safetensors", |
| "model.layers.29.mlp.router.gate.weight": "model-00001-of-00006.safetensors", |
| "model.layers.29.mlp.shared_experts.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.29.mlp.shared_experts.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.29.mlp.shared_experts.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.29.mlp.shared_experts.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.29.mlp.shared_experts.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.29.mlp.shared_experts.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.29.mlp.shared_experts.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.29.mlp.shared_experts.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.29.mlp.shared_experts.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.29.post_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.29.pre_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.29.self_attn.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.29.self_attn.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.29.self_attn.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.29.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.29.self_attn.k_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.29.self_attn.k_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.29.self_attn.o_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.29.self_attn.o_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.29.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.29.self_attn.q_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.29.self_attn.q_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.29.self_attn.v_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.29.self_attn.v_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.3.mlp.expert_bias": "model-00001-of-00006.safetensors", |
| "model.layers.3.mlp.experts.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.3.mlp.experts.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.3.mlp.experts.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.3.mlp.experts.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.3.mlp.experts.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.3.mlp.experts.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.3.mlp.experts.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.3.mlp.experts.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.3.mlp.experts.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.3.mlp.router.gate.weight": "model-00001-of-00006.safetensors", |
| "model.layers.3.mlp.shared_experts.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.3.mlp.shared_experts.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.3.mlp.shared_experts.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.3.mlp.shared_experts.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.3.mlp.shared_experts.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.3.mlp.shared_experts.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.3.mlp.shared_experts.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.3.mlp.shared_experts.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.3.post_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.3.pre_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.3.self_attn.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.3.self_attn.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.3.self_attn.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.30.input_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.30.mlp.expert_bias": "model-00001-of-00006.safetensors", |
| "model.layers.30.mlp.experts.down_proj.biases": "model-00006-of-00006.safetensors", |
| "model.layers.30.mlp.experts.down_proj.scales": "model-00006-of-00006.safetensors", |
| "model.layers.30.mlp.experts.down_proj.weight": "model-00006-of-00006.safetensors", |
| "model.layers.30.mlp.experts.gate_proj.biases": "model-00006-of-00006.safetensors", |
| "model.layers.30.mlp.experts.gate_proj.scales": "model-00006-of-00006.safetensors", |
| "model.layers.30.mlp.experts.gate_proj.weight": "model-00006-of-00006.safetensors", |
| "model.layers.30.mlp.experts.up_proj.biases": "model-00006-of-00006.safetensors", |
| "model.layers.30.mlp.experts.up_proj.scales": "model-00006-of-00006.safetensors", |
| "model.layers.30.mlp.experts.up_proj.weight": "model-00006-of-00006.safetensors", |
| "model.layers.30.mlp.router.gate.weight": "model-00001-of-00006.safetensors", |
| "model.layers.30.mlp.shared_experts.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.30.mlp.shared_experts.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.30.mlp.shared_experts.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.30.mlp.shared_experts.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.30.mlp.shared_experts.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.30.mlp.shared_experts.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.30.mlp.shared_experts.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.30.mlp.shared_experts.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.30.mlp.shared_experts.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.30.post_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.30.pre_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.30.self_attn.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.30.self_attn.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.30.self_attn.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.30.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.30.self_attn.k_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.30.self_attn.k_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.30.self_attn.o_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.30.self_attn.o_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.30.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.30.self_attn.q_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.30.self_attn.q_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.30.self_attn.v_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.30.self_attn.v_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.31.input_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.31.mlp.expert_bias": "model-00001-of-00006.safetensors", |
| "model.layers.31.mlp.experts.down_proj.biases": "model-00006-of-00006.safetensors", |
| "model.layers.31.mlp.experts.down_proj.scales": "model-00006-of-00006.safetensors", |
| "model.layers.31.mlp.experts.down_proj.weight": "model-00006-of-00006.safetensors", |
| "model.layers.31.mlp.experts.gate_proj.biases": "model-00006-of-00006.safetensors", |
| "model.layers.31.mlp.experts.gate_proj.scales": "model-00006-of-00006.safetensors", |
| "model.layers.31.mlp.experts.gate_proj.weight": "model-00006-of-00006.safetensors", |
| "model.layers.31.mlp.experts.up_proj.biases": "model-00006-of-00006.safetensors", |
| "model.layers.31.mlp.experts.up_proj.scales": "model-00006-of-00006.safetensors", |
| "model.layers.31.mlp.experts.up_proj.weight": "model-00006-of-00006.safetensors", |
| "model.layers.31.mlp.router.gate.weight": "model-00001-of-00006.safetensors", |
| "model.layers.31.mlp.shared_experts.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.31.mlp.shared_experts.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.31.mlp.shared_experts.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.31.mlp.shared_experts.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.31.mlp.shared_experts.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.31.mlp.shared_experts.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.31.mlp.shared_experts.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.31.mlp.shared_experts.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.31.mlp.shared_experts.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.31.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.31.post_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.31.pre_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.31.self_attn.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.31.self_attn.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.31.self_attn.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.31.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.31.self_attn.k_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.31.self_attn.k_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.31.self_attn.o_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.31.self_attn.o_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.31.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.31.self_attn.q_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.31.self_attn.q_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.31.self_attn.v_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.31.self_attn.v_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.4.mlp.expert_bias": "model-00001-of-00006.safetensors", |
| "model.layers.4.mlp.experts.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.4.mlp.experts.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.4.mlp.experts.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.4.mlp.experts.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.4.mlp.experts.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.4.mlp.experts.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.4.mlp.experts.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.4.mlp.experts.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.4.mlp.experts.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.4.mlp.router.gate.weight": "model-00001-of-00006.safetensors", |
| "model.layers.4.mlp.shared_experts.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.4.mlp.shared_experts.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.4.mlp.shared_experts.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.4.mlp.shared_experts.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.4.mlp.shared_experts.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.4.mlp.shared_experts.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.4.mlp.shared_experts.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.4.mlp.shared_experts.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.4.post_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.4.pre_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.4.self_attn.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.4.self_attn.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.4.self_attn.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.5.mlp.expert_bias": "model-00001-of-00006.safetensors", |
| "model.layers.5.mlp.experts.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.5.mlp.experts.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.5.mlp.experts.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.5.mlp.experts.gate_proj.biases": "model-00002-of-00006.safetensors", |
| "model.layers.5.mlp.experts.gate_proj.scales": "model-00002-of-00006.safetensors", |
| "model.layers.5.mlp.experts.gate_proj.weight": "model-00002-of-00006.safetensors", |
| "model.layers.5.mlp.experts.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.5.mlp.experts.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.5.mlp.experts.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.5.mlp.router.gate.weight": "model-00001-of-00006.safetensors", |
| "model.layers.5.mlp.shared_experts.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.5.mlp.shared_experts.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.5.mlp.shared_experts.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.5.mlp.shared_experts.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.5.mlp.shared_experts.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.5.mlp.shared_experts.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.5.mlp.shared_experts.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.5.mlp.shared_experts.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.5.post_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.5.pre_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.5.self_attn.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.5.self_attn.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.5.self_attn.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.6.input_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.6.mlp.expert_bias": "model-00001-of-00006.safetensors", |
| "model.layers.6.mlp.experts.down_proj.biases": "model-00002-of-00006.safetensors", |
| "model.layers.6.mlp.experts.down_proj.scales": "model-00002-of-00006.safetensors", |
| "model.layers.6.mlp.experts.down_proj.weight": "model-00002-of-00006.safetensors", |
| "model.layers.6.mlp.experts.gate_proj.biases": "model-00002-of-00006.safetensors", |
| "model.layers.6.mlp.experts.gate_proj.scales": "model-00002-of-00006.safetensors", |
| "model.layers.6.mlp.experts.gate_proj.weight": "model-00002-of-00006.safetensors", |
| "model.layers.6.mlp.experts.up_proj.biases": "model-00002-of-00006.safetensors", |
| "model.layers.6.mlp.experts.up_proj.scales": "model-00002-of-00006.safetensors", |
| "model.layers.6.mlp.experts.up_proj.weight": "model-00002-of-00006.safetensors", |
| "model.layers.6.mlp.router.gate.weight": "model-00001-of-00006.safetensors", |
| "model.layers.6.mlp.shared_experts.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.6.mlp.shared_experts.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.6.mlp.shared_experts.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.6.mlp.shared_experts.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.6.mlp.shared_experts.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.6.mlp.shared_experts.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.6.mlp.shared_experts.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.6.mlp.shared_experts.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.6.post_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.6.pre_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.6.self_attn.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.6.self_attn.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.6.self_attn.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.7.input_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.7.mlp.expert_bias": "model-00001-of-00006.safetensors", |
| "model.layers.7.mlp.experts.down_proj.biases": "model-00002-of-00006.safetensors", |
| "model.layers.7.mlp.experts.down_proj.scales": "model-00002-of-00006.safetensors", |
| "model.layers.7.mlp.experts.down_proj.weight": "model-00002-of-00006.safetensors", |
| "model.layers.7.mlp.experts.gate_proj.biases": "model-00002-of-00006.safetensors", |
| "model.layers.7.mlp.experts.gate_proj.scales": "model-00002-of-00006.safetensors", |
| "model.layers.7.mlp.experts.gate_proj.weight": "model-00002-of-00006.safetensors", |
| "model.layers.7.mlp.experts.up_proj.biases": "model-00002-of-00006.safetensors", |
| "model.layers.7.mlp.experts.up_proj.scales": "model-00002-of-00006.safetensors", |
| "model.layers.7.mlp.experts.up_proj.weight": "model-00002-of-00006.safetensors", |
| "model.layers.7.mlp.router.gate.weight": "model-00001-of-00006.safetensors", |
| "model.layers.7.mlp.shared_experts.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.7.mlp.shared_experts.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.7.mlp.shared_experts.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.7.mlp.shared_experts.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.7.mlp.shared_experts.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.7.mlp.shared_experts.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.7.mlp.shared_experts.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.7.mlp.shared_experts.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.7.post_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.7.pre_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.7.self_attn.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.7.self_attn.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.7.self_attn.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.8.input_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.8.mlp.expert_bias": "model-00001-of-00006.safetensors", |
| "model.layers.8.mlp.experts.down_proj.biases": "model-00002-of-00006.safetensors", |
| "model.layers.8.mlp.experts.down_proj.scales": "model-00002-of-00006.safetensors", |
| "model.layers.8.mlp.experts.down_proj.weight": "model-00002-of-00006.safetensors", |
| "model.layers.8.mlp.experts.gate_proj.biases": "model-00002-of-00006.safetensors", |
| "model.layers.8.mlp.experts.gate_proj.scales": "model-00002-of-00006.safetensors", |
| "model.layers.8.mlp.experts.gate_proj.weight": "model-00002-of-00006.safetensors", |
| "model.layers.8.mlp.experts.up_proj.biases": "model-00002-of-00006.safetensors", |
| "model.layers.8.mlp.experts.up_proj.scales": "model-00002-of-00006.safetensors", |
| "model.layers.8.mlp.experts.up_proj.weight": "model-00002-of-00006.safetensors", |
| "model.layers.8.mlp.router.gate.weight": "model-00001-of-00006.safetensors", |
| "model.layers.8.mlp.shared_experts.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.8.mlp.shared_experts.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.8.mlp.shared_experts.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.8.mlp.shared_experts.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.8.mlp.shared_experts.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.8.mlp.shared_experts.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.8.mlp.shared_experts.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.8.mlp.shared_experts.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.8.post_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.8.pre_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.8.self_attn.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.8.self_attn.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.8.self_attn.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.9.input_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.9.mlp.expert_bias": "model-00001-of-00006.safetensors", |
| "model.layers.9.mlp.experts.down_proj.biases": "model-00002-of-00006.safetensors", |
| "model.layers.9.mlp.experts.down_proj.scales": "model-00002-of-00006.safetensors", |
| "model.layers.9.mlp.experts.down_proj.weight": "model-00002-of-00006.safetensors", |
| "model.layers.9.mlp.experts.gate_proj.biases": "model-00002-of-00006.safetensors", |
| "model.layers.9.mlp.experts.gate_proj.scales": "model-00002-of-00006.safetensors", |
| "model.layers.9.mlp.experts.gate_proj.weight": "model-00002-of-00006.safetensors", |
| "model.layers.9.mlp.experts.up_proj.biases": "model-00002-of-00006.safetensors", |
| "model.layers.9.mlp.experts.up_proj.scales": "model-00002-of-00006.safetensors", |
| "model.layers.9.mlp.experts.up_proj.weight": "model-00002-of-00006.safetensors", |
| "model.layers.9.mlp.router.gate.weight": "model-00001-of-00006.safetensors", |
| "model.layers.9.mlp.shared_experts.down_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.9.mlp.shared_experts.down_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.9.mlp.shared_experts.down_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.9.mlp.shared_experts.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.9.mlp.shared_experts.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.9.mlp.shared_experts.up_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.9.mlp.shared_experts.up_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.9.mlp.shared_experts.up_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.9.post_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.9.pre_mlp_layernorm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.9.self_attn.gate_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.9.self_attn.gate_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.9.self_attn.gate_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", |
| "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", |
| "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00006.safetensors", |
| "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00006.safetensors", |
| "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", |
| "model.norm.weight": "model-00001-of-00006.safetensors" |
| } |
| } |
