| { |
| "metadata": { |
| "total_size": 15694781568, |
| "total_parameters": 20914755648 |
| }, |
| "weight_map": { |
| "lm_head.biases": "model-00003-of-00003.safetensors", |
| "lm_head.scales": "model-00003-of-00003.safetensors", |
| "lm_head.weight": "model-00003-of-00003.safetensors", |
| "model.embed_tokens.biases": "model-00001-of-00003.safetensors", |
| "model.embed_tokens.scales": "model-00001-of-00003.safetensors", |
| "model.embed_tokens.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.experts.down_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.experts.down_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.experts.down_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.experts.down_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.experts.gate_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.experts.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.experts.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.experts.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.experts.up_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.experts.up_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.experts.up_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.experts.up_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.router.bias": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.router.biases": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.router.scales": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.router.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.o_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.sinks": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.1.mlp.experts.down_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.1.mlp.experts.down_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.1.mlp.experts.down_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.1.mlp.experts.down_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.1.mlp.experts.gate_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.1.mlp.experts.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.1.mlp.experts.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.1.mlp.experts.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.1.mlp.experts.up_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.1.mlp.experts.up_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.1.mlp.experts.up_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.1.mlp.experts.up_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.1.mlp.router.bias": "model-00001-of-00003.safetensors", |
| "model.layers.1.mlp.router.biases": "model-00001-of-00003.safetensors", |
| "model.layers.1.mlp.router.scales": "model-00001-of-00003.safetensors", |
| "model.layers.1.mlp.router.weight": "model-00001-of-00003.safetensors", |
| "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.1.self_attn.o_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.1.self_attn.sinks": "model-00001-of-00003.safetensors", |
| "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.10.mlp.experts.down_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.10.mlp.experts.down_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.10.mlp.experts.down_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.10.mlp.experts.down_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.10.mlp.experts.gate_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.10.mlp.experts.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.10.mlp.experts.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.10.mlp.experts.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.10.mlp.experts.up_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.10.mlp.experts.up_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.10.mlp.experts.up_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.10.mlp.experts.up_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.10.mlp.router.bias": "model-00002-of-00003.safetensors", |
| "model.layers.10.mlp.router.biases": "model-00002-of-00003.safetensors", |
| "model.layers.10.mlp.router.scales": "model-00002-of-00003.safetensors", |
| "model.layers.10.mlp.router.weight": "model-00002-of-00003.safetensors", |
| "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.10.self_attn.k_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.10.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.10.self_attn.o_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.10.self_attn.o_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.10.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.10.self_attn.q_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.10.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.10.self_attn.sinks": "model-00002-of-00003.safetensors", |
| "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.10.self_attn.v_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.10.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.11.mlp.experts.down_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.11.mlp.experts.down_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.11.mlp.experts.down_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.11.mlp.experts.down_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.11.mlp.experts.gate_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.11.mlp.experts.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.11.mlp.experts.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.11.mlp.experts.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.11.mlp.experts.up_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.11.mlp.experts.up_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.11.mlp.experts.up_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.11.mlp.experts.up_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.11.mlp.router.bias": "model-00002-of-00003.safetensors", |
| "model.layers.11.mlp.router.biases": "model-00002-of-00003.safetensors", |
| "model.layers.11.mlp.router.scales": "model-00002-of-00003.safetensors", |
| "model.layers.11.mlp.router.weight": "model-00002-of-00003.safetensors", |
| "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.11.self_attn.k_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.11.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.11.self_attn.o_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.11.self_attn.o_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.11.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.11.self_attn.q_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.11.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.11.self_attn.sinks": "model-00002-of-00003.safetensors", |
| "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.11.self_attn.v_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.11.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.12.mlp.experts.down_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.12.mlp.experts.down_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.12.mlp.experts.down_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.12.mlp.experts.down_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.12.mlp.experts.gate_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.12.mlp.experts.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.12.mlp.experts.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.12.mlp.experts.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.12.mlp.experts.up_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.12.mlp.experts.up_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.12.mlp.experts.up_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.12.mlp.experts.up_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.12.mlp.router.bias": "model-00002-of-00003.safetensors", |
| "model.layers.12.mlp.router.biases": "model-00002-of-00003.safetensors", |
| "model.layers.12.mlp.router.scales": "model-00002-of-00003.safetensors", |
| "model.layers.12.mlp.router.weight": "model-00002-of-00003.safetensors", |
| "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.12.self_attn.k_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.12.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.12.self_attn.o_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.12.self_attn.o_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.12.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.12.self_attn.q_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.12.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.12.self_attn.sinks": "model-00002-of-00003.safetensors", |
| "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.12.self_attn.v_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.12.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.13.mlp.experts.down_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.13.mlp.experts.down_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.13.mlp.experts.down_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.13.mlp.experts.down_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.13.mlp.experts.gate_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.13.mlp.experts.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.13.mlp.experts.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.13.mlp.experts.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.13.mlp.experts.up_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.13.mlp.experts.up_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.13.mlp.experts.up_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.13.mlp.experts.up_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.13.mlp.router.bias": "model-00002-of-00003.safetensors", |
| "model.layers.13.mlp.router.biases": "model-00002-of-00003.safetensors", |
| "model.layers.13.mlp.router.scales": "model-00002-of-00003.safetensors", |
| "model.layers.13.mlp.router.weight": "model-00002-of-00003.safetensors", |
| "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.13.self_attn.k_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.13.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.13.self_attn.o_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.13.self_attn.o_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.13.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.13.self_attn.q_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.13.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.13.self_attn.sinks": "model-00002-of-00003.safetensors", |
| "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.13.self_attn.v_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.13.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.14.mlp.experts.down_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.14.mlp.experts.down_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.14.mlp.experts.down_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.14.mlp.experts.down_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.14.mlp.experts.gate_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.14.mlp.experts.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.14.mlp.experts.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.14.mlp.experts.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.14.mlp.experts.up_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.14.mlp.experts.up_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.14.mlp.experts.up_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.14.mlp.experts.up_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.14.mlp.router.bias": "model-00002-of-00003.safetensors", |
| "model.layers.14.mlp.router.biases": "model-00002-of-00003.safetensors", |
| "model.layers.14.mlp.router.scales": "model-00002-of-00003.safetensors", |
| "model.layers.14.mlp.router.weight": "model-00002-of-00003.safetensors", |
| "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.14.self_attn.k_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.14.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.14.self_attn.o_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.14.self_attn.o_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.14.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.14.self_attn.q_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.14.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.14.self_attn.sinks": "model-00002-of-00003.safetensors", |
| "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.14.self_attn.v_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.14.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.15.mlp.experts.down_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.15.mlp.experts.down_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.15.mlp.experts.down_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.15.mlp.experts.down_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.15.mlp.experts.gate_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.15.mlp.experts.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.15.mlp.experts.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.15.mlp.experts.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.15.mlp.experts.up_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.15.mlp.experts.up_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.15.mlp.experts.up_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.15.mlp.experts.up_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.15.mlp.router.bias": "model-00002-of-00003.safetensors", |
| "model.layers.15.mlp.router.biases": "model-00002-of-00003.safetensors", |
| "model.layers.15.mlp.router.scales": "model-00002-of-00003.safetensors", |
| "model.layers.15.mlp.router.weight": "model-00002-of-00003.safetensors", |
| "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.15.self_attn.k_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.15.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.15.self_attn.o_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.15.self_attn.o_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.15.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.15.self_attn.q_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.15.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.15.self_attn.sinks": "model-00002-of-00003.safetensors", |
| "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.15.self_attn.v_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.15.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.16.input_layernorm.weight": "model-00003-of-00003.safetensors", |
| "model.layers.16.mlp.experts.down_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.16.mlp.experts.down_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.16.mlp.experts.down_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.16.mlp.experts.down_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.16.mlp.experts.gate_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.16.mlp.experts.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.16.mlp.experts.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.16.mlp.experts.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.16.mlp.experts.up_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.16.mlp.experts.up_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.16.mlp.experts.up_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.16.mlp.experts.up_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.16.mlp.router.bias": "model-00003-of-00003.safetensors", |
| "model.layers.16.mlp.router.biases": "model-00003-of-00003.safetensors", |
| "model.layers.16.mlp.router.scales": "model-00003-of-00003.safetensors", |
| "model.layers.16.mlp.router.weight": "model-00003-of-00003.safetensors", |
| "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", |
| "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.16.self_attn.k_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.16.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.16.self_attn.o_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.16.self_attn.o_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.16.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.16.self_attn.q_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.16.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.16.self_attn.sinks": "model-00002-of-00003.safetensors", |
| "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.16.self_attn.v_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.16.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.17.input_layernorm.weight": "model-00003-of-00003.safetensors", |
| "model.layers.17.mlp.experts.down_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.17.mlp.experts.down_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.17.mlp.experts.down_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.17.mlp.experts.down_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.17.mlp.experts.gate_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.17.mlp.experts.gate_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.17.mlp.experts.gate_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.17.mlp.experts.gate_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.17.mlp.experts.up_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.17.mlp.experts.up_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.17.mlp.experts.up_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.17.mlp.experts.up_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.17.mlp.router.bias": "model-00003-of-00003.safetensors", |
| "model.layers.17.mlp.router.biases": "model-00003-of-00003.safetensors", |
| "model.layers.17.mlp.router.scales": "model-00003-of-00003.safetensors", |
| "model.layers.17.mlp.router.weight": "model-00003-of-00003.safetensors", |
| "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", |
| "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.17.self_attn.k_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.17.self_attn.k_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.17.self_attn.o_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.17.self_attn.o_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.17.self_attn.o_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.17.self_attn.q_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.17.self_attn.q_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.17.self_attn.sinks": "model-00003-of-00003.safetensors", |
| "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.17.self_attn.v_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.17.self_attn.v_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.18.input_layernorm.weight": "model-00003-of-00003.safetensors", |
| "model.layers.18.mlp.experts.down_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.18.mlp.experts.down_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.18.mlp.experts.down_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.18.mlp.experts.down_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.18.mlp.experts.gate_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.18.mlp.experts.gate_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.18.mlp.experts.gate_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.18.mlp.experts.gate_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.18.mlp.experts.up_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.18.mlp.experts.up_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.18.mlp.experts.up_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.18.mlp.experts.up_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.18.mlp.router.bias": "model-00003-of-00003.safetensors", |
| "model.layers.18.mlp.router.biases": "model-00003-of-00003.safetensors", |
| "model.layers.18.mlp.router.scales": "model-00003-of-00003.safetensors", |
| "model.layers.18.mlp.router.weight": "model-00003-of-00003.safetensors", |
| "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", |
| "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.18.self_attn.k_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.18.self_attn.k_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.18.self_attn.o_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.18.self_attn.o_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.18.self_attn.o_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.18.self_attn.q_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.18.self_attn.q_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.18.self_attn.sinks": "model-00003-of-00003.safetensors", |
| "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.18.self_attn.v_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.18.self_attn.v_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.19.input_layernorm.weight": "model-00003-of-00003.safetensors", |
| "model.layers.19.mlp.experts.down_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.19.mlp.experts.down_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.19.mlp.experts.down_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.19.mlp.experts.down_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.19.mlp.experts.gate_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.19.mlp.experts.gate_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.19.mlp.experts.gate_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.19.mlp.experts.gate_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.19.mlp.experts.up_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.19.mlp.experts.up_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.19.mlp.experts.up_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.19.mlp.experts.up_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.19.mlp.router.bias": "model-00003-of-00003.safetensors", |
| "model.layers.19.mlp.router.biases": "model-00003-of-00003.safetensors", |
| "model.layers.19.mlp.router.scales": "model-00003-of-00003.safetensors", |
| "model.layers.19.mlp.router.weight": "model-00003-of-00003.safetensors", |
| "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", |
| "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.19.self_attn.k_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.19.self_attn.k_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.19.self_attn.o_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.19.self_attn.o_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.19.self_attn.o_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.19.self_attn.q_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.19.self_attn.q_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.19.self_attn.sinks": "model-00003-of-00003.safetensors", |
| "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.19.self_attn.v_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.19.self_attn.v_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.2.mlp.experts.down_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.2.mlp.experts.down_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.2.mlp.experts.down_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.2.mlp.experts.down_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.2.mlp.experts.gate_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.2.mlp.experts.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.2.mlp.experts.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.2.mlp.experts.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.2.mlp.experts.up_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.2.mlp.experts.up_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.2.mlp.experts.up_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.2.mlp.experts.up_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.2.mlp.router.bias": "model-00001-of-00003.safetensors", |
| "model.layers.2.mlp.router.biases": "model-00001-of-00003.safetensors", |
| "model.layers.2.mlp.router.scales": "model-00001-of-00003.safetensors", |
| "model.layers.2.mlp.router.weight": "model-00001-of-00003.safetensors", |
| "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.2.self_attn.o_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.2.self_attn.sinks": "model-00001-of-00003.safetensors", |
| "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.20.input_layernorm.weight": "model-00003-of-00003.safetensors", |
| "model.layers.20.mlp.experts.down_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.20.mlp.experts.down_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.20.mlp.experts.down_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.20.mlp.experts.down_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.20.mlp.experts.gate_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.20.mlp.experts.gate_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.20.mlp.experts.gate_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.20.mlp.experts.gate_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.20.mlp.experts.up_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.20.mlp.experts.up_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.20.mlp.experts.up_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.20.mlp.experts.up_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.20.mlp.router.bias": "model-00003-of-00003.safetensors", |
| "model.layers.20.mlp.router.biases": "model-00003-of-00003.safetensors", |
| "model.layers.20.mlp.router.scales": "model-00003-of-00003.safetensors", |
| "model.layers.20.mlp.router.weight": "model-00003-of-00003.safetensors", |
| "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", |
| "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.20.self_attn.k_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.20.self_attn.k_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.20.self_attn.o_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.20.self_attn.o_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.20.self_attn.o_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.20.self_attn.q_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.20.self_attn.q_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.20.self_attn.sinks": "model-00003-of-00003.safetensors", |
| "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.20.self_attn.v_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.20.self_attn.v_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors", |
| "model.layers.21.mlp.experts.down_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.21.mlp.experts.down_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.21.mlp.experts.down_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.21.mlp.experts.down_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.21.mlp.experts.gate_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.21.mlp.experts.gate_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.21.mlp.experts.gate_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.21.mlp.experts.gate_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.21.mlp.experts.up_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.21.mlp.experts.up_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.21.mlp.experts.up_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.21.mlp.experts.up_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.21.mlp.router.bias": "model-00003-of-00003.safetensors", |
| "model.layers.21.mlp.router.biases": "model-00003-of-00003.safetensors", |
| "model.layers.21.mlp.router.scales": "model-00003-of-00003.safetensors", |
| "model.layers.21.mlp.router.weight": "model-00003-of-00003.safetensors", |
| "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", |
| "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.21.self_attn.k_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.21.self_attn.k_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.21.self_attn.o_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.21.self_attn.o_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.21.self_attn.o_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.21.self_attn.q_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.21.self_attn.q_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.21.self_attn.sinks": "model-00003-of-00003.safetensors", |
| "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.21.self_attn.v_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.21.self_attn.v_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors", |
| "model.layers.22.mlp.experts.down_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.22.mlp.experts.down_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.22.mlp.experts.down_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.22.mlp.experts.down_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.22.mlp.experts.gate_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.22.mlp.experts.gate_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.22.mlp.experts.gate_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.22.mlp.experts.gate_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.22.mlp.experts.up_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.22.mlp.experts.up_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.22.mlp.experts.up_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.22.mlp.experts.up_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.22.mlp.router.bias": "model-00003-of-00003.safetensors", |
| "model.layers.22.mlp.router.biases": "model-00003-of-00003.safetensors", |
| "model.layers.22.mlp.router.scales": "model-00003-of-00003.safetensors", |
| "model.layers.22.mlp.router.weight": "model-00003-of-00003.safetensors", |
| "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", |
| "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.22.self_attn.k_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.22.self_attn.k_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.22.self_attn.o_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.22.self_attn.o_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.22.self_attn.o_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.22.self_attn.q_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.22.self_attn.q_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.22.self_attn.sinks": "model-00003-of-00003.safetensors", |
| "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.22.self_attn.v_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.22.self_attn.v_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors", |
| "model.layers.23.mlp.experts.down_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.23.mlp.experts.down_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.23.mlp.experts.down_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.23.mlp.experts.down_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.23.mlp.experts.gate_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.23.mlp.experts.gate_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.23.mlp.experts.gate_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.23.mlp.experts.gate_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.23.mlp.experts.up_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.23.mlp.experts.up_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.23.mlp.experts.up_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.23.mlp.experts.up_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.23.mlp.router.bias": "model-00003-of-00003.safetensors", |
| "model.layers.23.mlp.router.biases": "model-00003-of-00003.safetensors", |
| "model.layers.23.mlp.router.scales": "model-00003-of-00003.safetensors", |
| "model.layers.23.mlp.router.weight": "model-00003-of-00003.safetensors", |
| "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", |
| "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.23.self_attn.k_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.23.self_attn.k_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.23.self_attn.o_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.23.self_attn.o_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.23.self_attn.o_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.23.self_attn.q_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.23.self_attn.q_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.23.self_attn.sinks": "model-00003-of-00003.safetensors", |
| "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", |
| "model.layers.23.self_attn.v_proj.biases": "model-00003-of-00003.safetensors", |
| "model.layers.23.self_attn.v_proj.scales": "model-00003-of-00003.safetensors", |
| "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.3.mlp.experts.down_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.3.mlp.experts.down_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.3.mlp.experts.down_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.3.mlp.experts.down_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.3.mlp.experts.gate_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.3.mlp.experts.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.3.mlp.experts.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.3.mlp.experts.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.3.mlp.experts.up_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.3.mlp.experts.up_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.3.mlp.experts.up_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.3.mlp.experts.up_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.3.mlp.router.bias": "model-00001-of-00003.safetensors", |
| "model.layers.3.mlp.router.biases": "model-00001-of-00003.safetensors", |
| "model.layers.3.mlp.router.scales": "model-00001-of-00003.safetensors", |
| "model.layers.3.mlp.router.weight": "model-00001-of-00003.safetensors", |
| "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.3.self_attn.o_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.3.self_attn.sinks": "model-00001-of-00003.safetensors", |
| "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.4.mlp.experts.down_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.4.mlp.experts.down_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.4.mlp.experts.down_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.4.mlp.experts.down_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.4.mlp.experts.gate_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.4.mlp.experts.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.4.mlp.experts.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.4.mlp.experts.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.4.mlp.experts.up_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.4.mlp.experts.up_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.4.mlp.experts.up_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.4.mlp.experts.up_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.4.mlp.router.bias": "model-00001-of-00003.safetensors", |
| "model.layers.4.mlp.router.biases": "model-00001-of-00003.safetensors", |
| "model.layers.4.mlp.router.scales": "model-00001-of-00003.safetensors", |
| "model.layers.4.mlp.router.weight": "model-00001-of-00003.safetensors", |
| "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.4.self_attn.o_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.4.self_attn.sinks": "model-00001-of-00003.safetensors", |
| "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.5.mlp.experts.down_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.5.mlp.experts.down_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.5.mlp.experts.down_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.5.mlp.experts.down_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.5.mlp.experts.gate_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.5.mlp.experts.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.5.mlp.experts.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.5.mlp.experts.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.5.mlp.experts.up_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.5.mlp.experts.up_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.5.mlp.experts.up_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.5.mlp.experts.up_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.5.mlp.router.bias": "model-00001-of-00003.safetensors", |
| "model.layers.5.mlp.router.biases": "model-00001-of-00003.safetensors", |
| "model.layers.5.mlp.router.scales": "model-00001-of-00003.safetensors", |
| "model.layers.5.mlp.router.weight": "model-00001-of-00003.safetensors", |
| "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.5.self_attn.o_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.5.self_attn.sinks": "model-00001-of-00003.safetensors", |
| "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.6.mlp.experts.down_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.6.mlp.experts.down_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.6.mlp.experts.down_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.6.mlp.experts.down_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.6.mlp.experts.gate_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.6.mlp.experts.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.6.mlp.experts.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.6.mlp.experts.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.6.mlp.experts.up_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.6.mlp.experts.up_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.6.mlp.experts.up_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.6.mlp.experts.up_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.6.mlp.router.bias": "model-00001-of-00003.safetensors", |
| "model.layers.6.mlp.router.biases": "model-00001-of-00003.safetensors", |
| "model.layers.6.mlp.router.scales": "model-00001-of-00003.safetensors", |
| "model.layers.6.mlp.router.weight": "model-00001-of-00003.safetensors", |
| "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.6.self_attn.o_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.6.self_attn.sinks": "model-00001-of-00003.safetensors", |
| "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.7.mlp.experts.down_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.7.mlp.experts.down_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.7.mlp.experts.down_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.7.mlp.experts.down_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.7.mlp.experts.gate_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.7.mlp.experts.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.7.mlp.experts.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.7.mlp.experts.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.7.mlp.experts.up_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.7.mlp.experts.up_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.7.mlp.experts.up_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.7.mlp.experts.up_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.7.mlp.router.bias": "model-00002-of-00003.safetensors", |
| "model.layers.7.mlp.router.biases": "model-00002-of-00003.safetensors", |
| "model.layers.7.mlp.router.scales": "model-00002-of-00003.safetensors", |
| "model.layers.7.mlp.router.weight": "model-00002-of-00003.safetensors", |
| "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.7.self_attn.o_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.7.self_attn.sinks": "model-00001-of-00003.safetensors", |
| "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", |
| "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00003.safetensors", |
| "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", |
| "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.8.mlp.experts.down_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.8.mlp.experts.down_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.8.mlp.experts.down_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.8.mlp.experts.down_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.8.mlp.experts.gate_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.8.mlp.experts.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.8.mlp.experts.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.8.mlp.experts.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.8.mlp.experts.up_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.8.mlp.experts.up_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.8.mlp.experts.up_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.8.mlp.experts.up_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.8.mlp.router.bias": "model-00002-of-00003.safetensors", |
| "model.layers.8.mlp.router.biases": "model-00002-of-00003.safetensors", |
| "model.layers.8.mlp.router.scales": "model-00002-of-00003.safetensors", |
| "model.layers.8.mlp.router.weight": "model-00002-of-00003.safetensors", |
| "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.8.self_attn.k_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.8.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.8.self_attn.o_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.8.self_attn.o_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.8.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.8.self_attn.q_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.8.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.8.self_attn.sinks": "model-00002-of-00003.safetensors", |
| "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.8.self_attn.v_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.8.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.9.mlp.experts.down_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.9.mlp.experts.down_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.9.mlp.experts.down_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.9.mlp.experts.down_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.9.mlp.experts.gate_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.9.mlp.experts.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.9.mlp.experts.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.9.mlp.experts.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.9.mlp.experts.up_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.9.mlp.experts.up_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.9.mlp.experts.up_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.9.mlp.experts.up_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.9.mlp.router.bias": "model-00002-of-00003.safetensors", |
| "model.layers.9.mlp.router.biases": "model-00002-of-00003.safetensors", |
| "model.layers.9.mlp.router.scales": "model-00002-of-00003.safetensors", |
| "model.layers.9.mlp.router.weight": "model-00002-of-00003.safetensors", |
| "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.9.self_attn.k_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.9.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.9.self_attn.o_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.9.self_attn.o_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.9.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.9.self_attn.q_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.9.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.9.self_attn.sinks": "model-00002-of-00003.safetensors", |
| "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", |
| "model.layers.9.self_attn.v_proj.biases": "model-00002-of-00003.safetensors", |
| "model.layers.9.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", |
| "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", |
| "model.norm.weight": "model-00001-of-00003.safetensors" |
| } |
| } |
