{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00025.safetensors", "model.norm.weight": "model-00001-of-00025.safetensors", "lm_head.weight": "model-00001-of-00025.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.0.moe.mlp.0.down_proj.weight": "model-00001-of-00025.safetensors", "model.layers.0.moe.mlp.1.down_proj.weight": "model-00001-of-00025.safetensors", "model.layers.0.moe.mlp.0.gate_proj.weight": "model-00001-of-00025.safetensors", "model.layers.0.moe.mlp.1.gate_proj.weight": "model-00001-of-00025.safetensors", "model.layers.0.moe.mlp.0.up_proj.weight": "model-00001-of-00025.safetensors", "model.layers.0.moe.mlp.1.up_proj.weight": "model-00001-of-00025.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00025.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00025.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00025.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00025.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00025.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00025.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00025.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.1.moe.mlp.0.down_proj.weight": "model-00001-of-00025.safetensors", "model.layers.1.moe.mlp.1.down_proj.weight": "model-00001-of-00025.safetensors", "model.layers.1.moe.mlp.0.gate_proj.weight": "model-00001-of-00025.safetensors", "model.layers.1.moe.mlp.1.gate_proj.weight": "model-00001-of-00025.safetensors", "model.layers.1.moe.mlp.0.up_proj.weight": "model-00001-of-00025.safetensors", "model.layers.1.moe.mlp.1.up_proj.weight": "model-00002-of-00025.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00025.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00025.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00025.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00025.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00025.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00025.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00025.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00025.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00025.safetensors", "model.layers.2.moe.mlp.0.down_proj.weight": "model-00002-of-00025.safetensors", "model.layers.2.moe.mlp.1.down_proj.weight": "model-00002-of-00025.safetensors", "model.layers.2.moe.mlp.0.gate_proj.weight": "model-00002-of-00025.safetensors", "model.layers.2.moe.mlp.1.gate_proj.weight": "model-00002-of-00025.safetensors", "model.layers.2.moe.mlp.0.up_proj.weight": "model-00002-of-00025.safetensors", "model.layers.2.moe.mlp.1.up_proj.weight": "model-00002-of-00025.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00025.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00025.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00025.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00025.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00025.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00025.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00025.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00025.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00025.safetensors", "model.layers.3.moe.mlp.0.down_proj.weight": "model-00002-of-00025.safetensors", "model.layers.3.moe.mlp.1.down_proj.weight": "model-00002-of-00025.safetensors", "model.layers.3.moe.mlp.0.gate_proj.weight": "model-00002-of-00025.safetensors", "model.layers.3.moe.mlp.1.gate_proj.weight": "model-00002-of-00025.safetensors", "model.layers.3.moe.mlp.0.up_proj.weight": "model-00002-of-00025.safetensors", "model.layers.3.moe.mlp.1.up_proj.weight": "model-00002-of-00025.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00025.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00025.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00025.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00025.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00025.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00025.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00025.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00025.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00025.safetensors", "model.layers.4.moe.mlp.0.down_proj.weight": "model-00002-of-00025.safetensors", "model.layers.4.moe.mlp.1.down_proj.weight": "model-00002-of-00025.safetensors", "model.layers.4.moe.mlp.0.gate_proj.weight": "model-00002-of-00025.safetensors", "model.layers.4.moe.mlp.1.gate_proj.weight": "model-00002-of-00025.safetensors", "model.layers.4.moe.mlp.0.up_proj.weight": "model-00002-of-00025.safetensors", "model.layers.4.moe.mlp.1.up_proj.weight": "model-00002-of-00025.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00025.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00025.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00025.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00025.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00025.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00025.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00025.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00025.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00025.safetensors", "model.layers.5.moe.mlp.0.down_proj.weight": "model-00003-of-00025.safetensors", "model.layers.5.moe.mlp.1.down_proj.weight": "model-00003-of-00025.safetensors", "model.layers.5.moe.mlp.0.gate_proj.weight": "model-00003-of-00025.safetensors", "model.layers.5.moe.mlp.1.gate_proj.weight": "model-00003-of-00025.safetensors", "model.layers.5.moe.mlp.0.up_proj.weight": "model-00003-of-00025.safetensors", "model.layers.5.moe.mlp.1.up_proj.weight": "model-00003-of-00025.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00025.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00003-of-00025.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00025.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00025.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00003-of-00025.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00025.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00003-of-00025.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00025.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00025.safetensors", "model.layers.6.moe.mlp.0.down_proj.weight": "model-00003-of-00025.safetensors", "model.layers.6.moe.mlp.1.down_proj.weight": "model-00003-of-00025.safetensors", "model.layers.6.moe.mlp.0.gate_proj.weight": "model-00003-of-00025.safetensors", "model.layers.6.moe.mlp.1.gate_proj.weight": "model-00003-of-00025.safetensors", "model.layers.6.moe.mlp.0.up_proj.weight": "model-00003-of-00025.safetensors", "model.layers.6.moe.mlp.1.up_proj.weight": "model-00003-of-00025.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00025.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00003-of-00025.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00025.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00025.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00003-of-00025.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00025.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00003-of-00025.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00025.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00025.safetensors", "model.layers.7.moe.mlp.0.down_proj.weight": "model-00003-of-00025.safetensors", "model.layers.7.moe.mlp.1.down_proj.weight": "model-00003-of-00025.safetensors", "model.layers.7.moe.mlp.0.gate_proj.weight": "model-00003-of-00025.safetensors", "model.layers.7.moe.mlp.1.gate_proj.weight": "model-00003-of-00025.safetensors", "model.layers.7.moe.mlp.0.up_proj.weight": "model-00003-of-00025.safetensors", "model.layers.7.moe.mlp.1.up_proj.weight": "model-00003-of-00025.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00025.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00003-of-00025.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00025.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00025.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00003-of-00025.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00025.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00003-of-00025.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00025.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00025.safetensors", "model.layers.8.moe.mlp.0.down_proj.weight": "model-00003-of-00025.safetensors", "model.layers.8.moe.mlp.1.down_proj.weight": "model-00003-of-00025.safetensors", "model.layers.8.moe.mlp.0.gate_proj.weight": "model-00004-of-00025.safetensors", "model.layers.8.moe.mlp.1.gate_proj.weight": "model-00004-of-00025.safetensors", "model.layers.8.moe.mlp.0.up_proj.weight": "model-00004-of-00025.safetensors", "model.layers.8.moe.mlp.1.up_proj.weight": "model-00004-of-00025.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00025.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00004-of-00025.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00025.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00025.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00004-of-00025.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00025.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00004-of-00025.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00025.safetensors", "model.layers.9.input_layernorm.weight": "model-00004-of-00025.safetensors", "model.layers.9.moe.mlp.0.down_proj.weight": "model-00004-of-00025.safetensors", "model.layers.9.moe.mlp.1.down_proj.weight": "model-00004-of-00025.safetensors", "model.layers.9.moe.mlp.0.gate_proj.weight": "model-00004-of-00025.safetensors", "model.layers.9.moe.mlp.1.gate_proj.weight": "model-00004-of-00025.safetensors", "model.layers.9.moe.mlp.0.up_proj.weight": "model-00004-of-00025.safetensors", "model.layers.9.moe.mlp.1.up_proj.weight": "model-00004-of-00025.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00025.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00004-of-00025.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00025.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00025.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00004-of-00025.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00025.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00004-of-00025.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00025.safetensors", "model.layers.10.input_layernorm.weight": "model-00004-of-00025.safetensors", "model.layers.10.moe.mlp.0.down_proj.weight": "model-00004-of-00025.safetensors", "model.layers.10.moe.mlp.1.down_proj.weight": "model-00004-of-00025.safetensors", "model.layers.10.moe.mlp.0.gate_proj.weight": "model-00004-of-00025.safetensors", "model.layers.10.moe.mlp.1.gate_proj.weight": "model-00004-of-00025.safetensors", "model.layers.10.moe.mlp.0.up_proj.weight": "model-00004-of-00025.safetensors", "model.layers.10.moe.mlp.1.up_proj.weight": "model-00004-of-00025.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00025.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00004-of-00025.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00025.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00025.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00004-of-00025.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00025.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00004-of-00025.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00025.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00025.safetensors", "model.layers.11.moe.mlp.0.down_proj.weight": "model-00004-of-00025.safetensors", "model.layers.11.moe.mlp.1.down_proj.weight": "model-00004-of-00025.safetensors", "model.layers.11.moe.mlp.0.gate_proj.weight": "model-00004-of-00025.safetensors", "model.layers.11.moe.mlp.1.gate_proj.weight": "model-00004-of-00025.safetensors", "model.layers.11.moe.mlp.0.up_proj.weight": "model-00005-of-00025.safetensors", "model.layers.11.moe.mlp.1.up_proj.weight": "model-00005-of-00025.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00005-of-00025.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00025.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00025.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00005-of-00025.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00025.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00005-of-00025.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.12.moe.mlp.0.down_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.moe.mlp.1.down_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.moe.mlp.0.gate_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.moe.mlp.1.gate_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.moe.mlp.0.up_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.moe.mlp.1.up_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00005-of-00025.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00005-of-00025.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00005-of-00025.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00025.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.13.moe.mlp.0.down_proj.weight": "model-00005-of-00025.safetensors", "model.layers.13.moe.mlp.1.down_proj.weight": "model-00005-of-00025.safetensors", "model.layers.13.moe.mlp.0.gate_proj.weight": "model-00005-of-00025.safetensors", "model.layers.13.moe.mlp.1.gate_proj.weight": "model-00005-of-00025.safetensors", "model.layers.13.moe.mlp.0.up_proj.weight": "model-00005-of-00025.safetensors", "model.layers.13.moe.mlp.1.up_proj.weight": "model-00005-of-00025.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00005-of-00025.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00025.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00025.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00005-of-00025.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00025.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00005-of-00025.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00025.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.14.moe.mlp.0.down_proj.weight": "model-00005-of-00025.safetensors", "model.layers.14.moe.mlp.1.down_proj.weight": "model-00005-of-00025.safetensors", "model.layers.14.moe.mlp.0.gate_proj.weight": "model-00005-of-00025.safetensors", "model.layers.14.moe.mlp.1.gate_proj.weight": "model-00005-of-00025.safetensors", "model.layers.14.moe.mlp.0.up_proj.weight": "model-00005-of-00025.safetensors", "model.layers.14.moe.mlp.1.up_proj.weight": "model-00005-of-00025.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00005-of-00025.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00025.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00025.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00005-of-00025.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00025.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00006-of-00025.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00025.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00025.safetensors", "model.layers.15.moe.mlp.0.down_proj.weight": "model-00006-of-00025.safetensors", "model.layers.15.moe.mlp.1.down_proj.weight": "model-00006-of-00025.safetensors", "model.layers.15.moe.mlp.0.gate_proj.weight": "model-00006-of-00025.safetensors", "model.layers.15.moe.mlp.1.gate_proj.weight": "model-00006-of-00025.safetensors", "model.layers.15.moe.mlp.0.up_proj.weight": "model-00006-of-00025.safetensors", "model.layers.15.moe.mlp.1.up_proj.weight": "model-00006-of-00025.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00025.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00006-of-00025.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00025.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00025.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00006-of-00025.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00025.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00006-of-00025.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00025.safetensors", "model.layers.16.input_layernorm.weight": "model-00006-of-00025.safetensors", "model.layers.16.moe.mlp.0.down_proj.weight": "model-00006-of-00025.safetensors", "model.layers.16.moe.mlp.1.down_proj.weight": "model-00006-of-00025.safetensors", "model.layers.16.moe.mlp.0.gate_proj.weight": "model-00006-of-00025.safetensors", "model.layers.16.moe.mlp.1.gate_proj.weight": "model-00006-of-00025.safetensors", "model.layers.16.moe.mlp.0.up_proj.weight": "model-00006-of-00025.safetensors", "model.layers.16.moe.mlp.1.up_proj.weight": "model-00006-of-00025.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00025.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00006-of-00025.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00025.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00025.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00006-of-00025.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00025.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00006-of-00025.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00025.safetensors", "model.layers.17.input_layernorm.weight": "model-00006-of-00025.safetensors", "model.layers.17.moe.mlp.0.down_proj.weight": "model-00006-of-00025.safetensors", "model.layers.17.moe.mlp.1.down_proj.weight": "model-00006-of-00025.safetensors", "model.layers.17.moe.mlp.0.gate_proj.weight": "model-00006-of-00025.safetensors", "model.layers.17.moe.mlp.1.gate_proj.weight": "model-00006-of-00025.safetensors", "model.layers.17.moe.mlp.0.up_proj.weight": "model-00006-of-00025.safetensors", "model.layers.17.moe.mlp.1.up_proj.weight": "model-00006-of-00025.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00025.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00006-of-00025.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00025.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00025.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00006-of-00025.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00025.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00006-of-00025.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00025.safetensors", "model.layers.18.input_layernorm.weight": "model-00006-of-00025.safetensors", "model.layers.18.moe.mlp.0.down_proj.weight": "model-00006-of-00025.safetensors", "model.layers.18.moe.mlp.1.down_proj.weight": "model-00006-of-00025.safetensors", "model.layers.18.moe.mlp.0.gate_proj.weight": "model-00007-of-00025.safetensors", "model.layers.18.moe.mlp.1.gate_proj.weight": "model-00007-of-00025.safetensors", "model.layers.18.moe.mlp.0.up_proj.weight": "model-00007-of-00025.safetensors", "model.layers.18.moe.mlp.1.up_proj.weight": "model-00007-of-00025.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00025.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00007-of-00025.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00025.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00025.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00007-of-00025.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00025.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00007-of-00025.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00025.safetensors", "model.layers.19.input_layernorm.weight": "model-00007-of-00025.safetensors", "model.layers.19.moe.mlp.0.down_proj.weight": "model-00007-of-00025.safetensors", "model.layers.19.moe.mlp.1.down_proj.weight": "model-00007-of-00025.safetensors", "model.layers.19.moe.mlp.0.gate_proj.weight": "model-00007-of-00025.safetensors", "model.layers.19.moe.mlp.1.gate_proj.weight": "model-00007-of-00025.safetensors", "model.layers.19.moe.mlp.0.up_proj.weight": "model-00007-of-00025.safetensors", "model.layers.19.moe.mlp.1.up_proj.weight": "model-00007-of-00025.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00025.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00007-of-00025.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00025.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00025.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00007-of-00025.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00025.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00007-of-00025.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00025.safetensors", "model.layers.20.input_layernorm.weight": "model-00007-of-00025.safetensors", "model.layers.20.moe.mlp.0.down_proj.weight": "model-00007-of-00025.safetensors", "model.layers.20.moe.mlp.1.down_proj.weight": "model-00007-of-00025.safetensors", "model.layers.20.moe.mlp.0.gate_proj.weight": "model-00007-of-00025.safetensors", "model.layers.20.moe.mlp.1.gate_proj.weight": "model-00007-of-00025.safetensors", "model.layers.20.moe.mlp.0.up_proj.weight": "model-00007-of-00025.safetensors", "model.layers.20.moe.mlp.1.up_proj.weight": "model-00007-of-00025.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00025.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00007-of-00025.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00025.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00025.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00007-of-00025.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00025.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00007-of-00025.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00025.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00025.safetensors", "model.layers.21.moe.mlp.0.down_proj.weight": "model-00007-of-00025.safetensors", "model.layers.21.moe.mlp.1.down_proj.weight": "model-00007-of-00025.safetensors", "model.layers.21.moe.mlp.0.gate_proj.weight": "model-00007-of-00025.safetensors", "model.layers.21.moe.mlp.1.gate_proj.weight": "model-00007-of-00025.safetensors", "model.layers.21.moe.mlp.0.up_proj.weight": "model-00008-of-00025.safetensors", "model.layers.21.moe.mlp.1.up_proj.weight": "model-00008-of-00025.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00025.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00008-of-00025.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00025.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00025.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00008-of-00025.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00025.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00008-of-00025.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00025.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00025.safetensors", "model.layers.22.moe.mlp.0.down_proj.weight": "model-00008-of-00025.safetensors", "model.layers.22.moe.mlp.1.down_proj.weight": "model-00008-of-00025.safetensors", "model.layers.22.moe.mlp.0.gate_proj.weight": "model-00008-of-00025.safetensors", "model.layers.22.moe.mlp.1.gate_proj.weight": "model-00008-of-00025.safetensors", "model.layers.22.moe.mlp.0.up_proj.weight": "model-00008-of-00025.safetensors", "model.layers.22.moe.mlp.1.up_proj.weight": "model-00008-of-00025.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00025.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00008-of-00025.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00025.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00025.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00008-of-00025.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00025.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00008-of-00025.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00025.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00025.safetensors", "model.layers.23.moe.mlp.0.down_proj.weight": "model-00008-of-00025.safetensors", "model.layers.23.moe.mlp.1.down_proj.weight": "model-00008-of-00025.safetensors", "model.layers.23.moe.mlp.0.gate_proj.weight": "model-00008-of-00025.safetensors", "model.layers.23.moe.mlp.1.gate_proj.weight": "model-00008-of-00025.safetensors", "model.layers.23.moe.mlp.0.up_proj.weight": "model-00008-of-00025.safetensors", "model.layers.23.moe.mlp.1.up_proj.weight": "model-00008-of-00025.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00025.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00008-of-00025.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00025.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00025.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00008-of-00025.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00025.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00008-of-00025.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00025.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00025.safetensors", "model.layers.24.moe.mlp.0.down_proj.weight": "model-00008-of-00025.safetensors", "model.layers.24.moe.mlp.1.down_proj.weight": "model-00008-of-00025.safetensors", "model.layers.24.moe.mlp.0.gate_proj.weight": "model-00008-of-00025.safetensors", "model.layers.24.moe.mlp.1.gate_proj.weight": "model-00008-of-00025.safetensors", "model.layers.24.moe.mlp.0.up_proj.weight": "model-00008-of-00025.safetensors", "model.layers.24.moe.mlp.1.up_proj.weight": "model-00008-of-00025.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00025.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00008-of-00025.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00025.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00025.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00008-of-00025.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00025.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00009-of-00025.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00025.safetensors", "model.layers.25.input_layernorm.weight": "model-00009-of-00025.safetensors", "model.layers.25.moe.mlp.0.down_proj.weight": "model-00009-of-00025.safetensors", "model.layers.25.moe.mlp.1.down_proj.weight": "model-00009-of-00025.safetensors", "model.layers.25.moe.mlp.0.gate_proj.weight": "model-00009-of-00025.safetensors", "model.layers.25.moe.mlp.1.gate_proj.weight": "model-00009-of-00025.safetensors", "model.layers.25.moe.mlp.0.up_proj.weight": "model-00009-of-00025.safetensors", "model.layers.25.moe.mlp.1.up_proj.weight": "model-00009-of-00025.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00025.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00009-of-00025.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00025.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00025.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00009-of-00025.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00025.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00009-of-00025.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00025.safetensors", "model.layers.26.input_layernorm.weight": "model-00009-of-00025.safetensors", "model.layers.26.moe.mlp.0.down_proj.weight": "model-00009-of-00025.safetensors", "model.layers.26.moe.mlp.1.down_proj.weight": "model-00009-of-00025.safetensors", "model.layers.26.moe.mlp.0.gate_proj.weight": "model-00009-of-00025.safetensors", "model.layers.26.moe.mlp.1.gate_proj.weight": "model-00009-of-00025.safetensors", "model.layers.26.moe.mlp.0.up_proj.weight": "model-00009-of-00025.safetensors", "model.layers.26.moe.mlp.1.up_proj.weight": "model-00009-of-00025.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00025.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00009-of-00025.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00025.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00025.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00009-of-00025.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00025.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00009-of-00025.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00025.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00025.safetensors", "model.layers.27.moe.mlp.0.down_proj.weight": "model-00009-of-00025.safetensors", "model.layers.27.moe.mlp.1.down_proj.weight": "model-00009-of-00025.safetensors", "model.layers.27.moe.mlp.0.gate_proj.weight": "model-00009-of-00025.safetensors", "model.layers.27.moe.mlp.1.gate_proj.weight": "model-00009-of-00025.safetensors", "model.layers.27.moe.mlp.0.up_proj.weight": "model-00009-of-00025.safetensors", "model.layers.27.moe.mlp.1.up_proj.weight": "model-00009-of-00025.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00025.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00009-of-00025.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00025.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00025.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00009-of-00025.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00025.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00009-of-00025.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00025.safetensors", "model.layers.28.input_layernorm.weight": "model-00009-of-00025.safetensors", "model.layers.28.moe.mlp.0.down_proj.weight": "model-00009-of-00025.safetensors", "model.layers.28.moe.mlp.1.down_proj.weight": "model-00009-of-00025.safetensors", "model.layers.28.moe.mlp.0.gate_proj.weight": "model-00010-of-00025.safetensors", "model.layers.28.moe.mlp.1.gate_proj.weight": "model-00010-of-00025.safetensors", "model.layers.28.moe.mlp.0.up_proj.weight": "model-00010-of-00025.safetensors", "model.layers.28.moe.mlp.1.up_proj.weight": "model-00010-of-00025.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00010-of-00025.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00010-of-00025.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00010-of-00025.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00010-of-00025.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00010-of-00025.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00010-of-00025.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00010-of-00025.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00010-of-00025.safetensors", "model.layers.29.input_layernorm.weight": "model-00010-of-00025.safetensors", "model.layers.29.moe.mlp.0.down_proj.weight": "model-00010-of-00025.safetensors", "model.layers.29.moe.mlp.1.down_proj.weight": "model-00010-of-00025.safetensors", "model.layers.29.moe.mlp.0.gate_proj.weight": "model-00010-of-00025.safetensors", "model.layers.29.moe.mlp.1.gate_proj.weight": "model-00010-of-00025.safetensors", "model.layers.29.moe.mlp.0.up_proj.weight": "model-00010-of-00025.safetensors", "model.layers.29.moe.mlp.1.up_proj.weight": "model-00010-of-00025.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00025.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00010-of-00025.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00025.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00025.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00010-of-00025.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00025.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00010-of-00025.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00025.safetensors", "model.layers.30.input_layernorm.weight": "model-00010-of-00025.safetensors", "model.layers.30.moe.mlp.0.down_proj.weight": "model-00010-of-00025.safetensors", "model.layers.30.moe.mlp.1.down_proj.weight": "model-00010-of-00025.safetensors", "model.layers.30.moe.mlp.0.gate_proj.weight": "model-00010-of-00025.safetensors", "model.layers.30.moe.mlp.1.gate_proj.weight": "model-00010-of-00025.safetensors", "model.layers.30.moe.mlp.0.up_proj.weight": "model-00010-of-00025.safetensors", "model.layers.30.moe.mlp.1.up_proj.weight": "model-00010-of-00025.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00025.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00010-of-00025.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00025.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00010-of-00025.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00010-of-00025.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00010-of-00025.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00010-of-00025.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00010-of-00025.safetensors", "model.layers.31.input_layernorm.weight": "model-00010-of-00025.safetensors", "model.layers.31.moe.mlp.0.down_proj.weight": "model-00010-of-00025.safetensors", "model.layers.31.moe.mlp.1.down_proj.weight": "model-00010-of-00025.safetensors", "model.layers.31.moe.mlp.0.gate_proj.weight": "model-00010-of-00025.safetensors", "model.layers.31.moe.mlp.1.gate_proj.weight": "model-00010-of-00025.safetensors", "model.layers.31.moe.mlp.0.up_proj.weight": "model-00011-of-00025.safetensors", "model.layers.31.moe.mlp.1.up_proj.weight": "model-00011-of-00025.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00025.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00011-of-00025.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00025.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00025.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00011-of-00025.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00025.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00011-of-00025.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00025.safetensors", "model.layers.32.input_layernorm.weight": "model-00011-of-00025.safetensors", "model.layers.32.moe.mlp.0.down_proj.weight": "model-00011-of-00025.safetensors", "model.layers.32.moe.mlp.1.down_proj.weight": "model-00011-of-00025.safetensors", "model.layers.32.moe.mlp.0.gate_proj.weight": "model-00011-of-00025.safetensors", "model.layers.32.moe.mlp.1.gate_proj.weight": "model-00011-of-00025.safetensors", "model.layers.32.moe.mlp.0.up_proj.weight": "model-00011-of-00025.safetensors", "model.layers.32.moe.mlp.1.up_proj.weight": "model-00011-of-00025.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00011-of-00025.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00011-of-00025.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00011-of-00025.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00011-of-00025.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00011-of-00025.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00011-of-00025.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00011-of-00025.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00011-of-00025.safetensors", "model.layers.33.input_layernorm.weight": "model-00011-of-00025.safetensors", "model.layers.33.moe.mlp.0.down_proj.weight": "model-00011-of-00025.safetensors", "model.layers.33.moe.mlp.1.down_proj.weight": "model-00011-of-00025.safetensors", "model.layers.33.moe.mlp.0.gate_proj.weight": "model-00011-of-00025.safetensors", "model.layers.33.moe.mlp.1.gate_proj.weight": "model-00011-of-00025.safetensors", "model.layers.33.moe.mlp.0.up_proj.weight": "model-00011-of-00025.safetensors", "model.layers.33.moe.mlp.1.up_proj.weight": "model-00011-of-00025.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00011-of-00025.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00011-of-00025.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00011-of-00025.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00011-of-00025.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00011-of-00025.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00011-of-00025.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00011-of-00025.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00011-of-00025.safetensors", "model.layers.34.input_layernorm.weight": "model-00011-of-00025.safetensors", "model.layers.34.moe.mlp.0.down_proj.weight": "model-00011-of-00025.safetensors", "model.layers.34.moe.mlp.1.down_proj.weight": "model-00011-of-00025.safetensors", "model.layers.34.moe.mlp.0.gate_proj.weight": "model-00011-of-00025.safetensors", "model.layers.34.moe.mlp.1.gate_proj.weight": "model-00011-of-00025.safetensors", "model.layers.34.moe.mlp.0.up_proj.weight": "model-00011-of-00025.safetensors", "model.layers.34.moe.mlp.1.up_proj.weight": "model-00011-of-00025.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00011-of-00025.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00011-of-00025.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00011-of-00025.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00011-of-00025.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00011-of-00025.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00012-of-00025.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00012-of-00025.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00012-of-00025.safetensors", "model.layers.35.input_layernorm.weight": "model-00012-of-00025.safetensors", "model.layers.35.moe.mlp.0.down_proj.weight": "model-00012-of-00025.safetensors", "model.layers.35.moe.mlp.1.down_proj.weight": "model-00012-of-00025.safetensors", "model.layers.35.moe.mlp.0.gate_proj.weight": "model-00012-of-00025.safetensors", "model.layers.35.moe.mlp.1.gate_proj.weight": "model-00012-of-00025.safetensors", "model.layers.35.moe.mlp.0.up_proj.weight": "model-00012-of-00025.safetensors", "model.layers.35.moe.mlp.1.up_proj.weight": "model-00012-of-00025.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00012-of-00025.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00012-of-00025.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00025.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00025.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00012-of-00025.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00025.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00012-of-00025.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00025.safetensors", "model.layers.36.input_layernorm.weight": "model-00012-of-00025.safetensors", "model.layers.36.moe.mlp.0.down_proj.weight": "model-00012-of-00025.safetensors", "model.layers.36.moe.mlp.1.down_proj.weight": "model-00012-of-00025.safetensors", "model.layers.36.moe.mlp.0.gate_proj.weight": "model-00012-of-00025.safetensors", "model.layers.36.moe.mlp.1.gate_proj.weight": "model-00012-of-00025.safetensors", "model.layers.36.moe.mlp.0.up_proj.weight": "model-00012-of-00025.safetensors", "model.layers.36.moe.mlp.1.up_proj.weight": "model-00012-of-00025.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00012-of-00025.safetensors", "model.layers.36.self_attn.k_proj.bias": "model-00012-of-00025.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00012-of-00025.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00012-of-00025.safetensors", "model.layers.36.self_attn.q_proj.bias": "model-00012-of-00025.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00012-of-00025.safetensors", "model.layers.36.self_attn.v_proj.bias": "model-00012-of-00025.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00012-of-00025.safetensors", "model.layers.37.input_layernorm.weight": "model-00012-of-00025.safetensors", "model.layers.37.moe.mlp.0.down_proj.weight": "model-00012-of-00025.safetensors", "model.layers.37.moe.mlp.1.down_proj.weight": "model-00012-of-00025.safetensors", "model.layers.37.moe.mlp.0.gate_proj.weight": "model-00012-of-00025.safetensors", "model.layers.37.moe.mlp.1.gate_proj.weight": "model-00012-of-00025.safetensors", "model.layers.37.moe.mlp.0.up_proj.weight": "model-00012-of-00025.safetensors", "model.layers.37.moe.mlp.1.up_proj.weight": "model-00012-of-00025.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00012-of-00025.safetensors", "model.layers.37.self_attn.k_proj.bias": "model-00012-of-00025.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00012-of-00025.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00012-of-00025.safetensors", "model.layers.37.self_attn.q_proj.bias": "model-00012-of-00025.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00012-of-00025.safetensors", "model.layers.37.self_attn.v_proj.bias": "model-00012-of-00025.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00012-of-00025.safetensors", "model.layers.38.input_layernorm.weight": "model-00012-of-00025.safetensors", "model.layers.38.moe.mlp.0.down_proj.weight": "model-00012-of-00025.safetensors", "model.layers.38.moe.mlp.1.down_proj.weight": "model-00012-of-00025.safetensors", "model.layers.38.moe.mlp.0.gate_proj.weight": "model-00013-of-00025.safetensors", "model.layers.38.moe.mlp.1.gate_proj.weight": "model-00013-of-00025.safetensors", "model.layers.38.moe.mlp.0.up_proj.weight": "model-00013-of-00025.safetensors", "model.layers.38.moe.mlp.1.up_proj.weight": "model-00013-of-00025.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00013-of-00025.safetensors", "model.layers.38.self_attn.k_proj.bias": "model-00013-of-00025.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00013-of-00025.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00013-of-00025.safetensors", "model.layers.38.self_attn.q_proj.bias": "model-00013-of-00025.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00013-of-00025.safetensors", "model.layers.38.self_attn.v_proj.bias": "model-00013-of-00025.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00013-of-00025.safetensors", "model.layers.39.input_layernorm.weight": "model-00013-of-00025.safetensors", "model.layers.39.moe.mlp.0.down_proj.weight": "model-00013-of-00025.safetensors", "model.layers.39.moe.mlp.1.down_proj.weight": "model-00013-of-00025.safetensors", "model.layers.39.moe.mlp.0.gate_proj.weight": "model-00013-of-00025.safetensors", "model.layers.39.moe.mlp.1.gate_proj.weight": "model-00013-of-00025.safetensors", "model.layers.39.moe.mlp.0.up_proj.weight": "model-00013-of-00025.safetensors", "model.layers.39.moe.mlp.1.up_proj.weight": "model-00013-of-00025.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00013-of-00025.safetensors", "model.layers.39.self_attn.k_proj.bias": "model-00013-of-00025.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00013-of-00025.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00013-of-00025.safetensors", "model.layers.39.self_attn.q_proj.bias": "model-00013-of-00025.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00013-of-00025.safetensors", "model.layers.39.self_attn.v_proj.bias": "model-00013-of-00025.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00013-of-00025.safetensors", "model.layers.40.input_layernorm.weight": "model-00013-of-00025.safetensors", "model.layers.40.moe.mlp.0.down_proj.weight": "model-00013-of-00025.safetensors", "model.layers.40.moe.mlp.1.down_proj.weight": "model-00013-of-00025.safetensors", "model.layers.40.moe.mlp.0.gate_proj.weight": "model-00013-of-00025.safetensors", "model.layers.40.moe.mlp.1.gate_proj.weight": "model-00013-of-00025.safetensors", "model.layers.40.moe.mlp.0.up_proj.weight": "model-00013-of-00025.safetensors", "model.layers.40.moe.mlp.1.up_proj.weight": "model-00013-of-00025.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00013-of-00025.safetensors", "model.layers.40.self_attn.k_proj.bias": "model-00013-of-00025.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00013-of-00025.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00013-of-00025.safetensors", "model.layers.40.self_attn.q_proj.bias": "model-00013-of-00025.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00013-of-00025.safetensors", "model.layers.40.self_attn.v_proj.bias": "model-00013-of-00025.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00013-of-00025.safetensors", "model.layers.41.input_layernorm.weight": "model-00013-of-00025.safetensors", "model.layers.41.moe.mlp.0.down_proj.weight": "model-00013-of-00025.safetensors", "model.layers.41.moe.mlp.1.down_proj.weight": "model-00013-of-00025.safetensors", "model.layers.41.moe.mlp.0.gate_proj.weight": "model-00013-of-00025.safetensors", "model.layers.41.moe.mlp.1.gate_proj.weight": "model-00013-of-00025.safetensors", "model.layers.41.moe.mlp.0.up_proj.weight": "model-00014-of-00025.safetensors", "model.layers.41.moe.mlp.1.up_proj.weight": "model-00014-of-00025.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00014-of-00025.safetensors", "model.layers.41.self_attn.k_proj.bias": "model-00014-of-00025.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00014-of-00025.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00014-of-00025.safetensors", "model.layers.41.self_attn.q_proj.bias": "model-00014-of-00025.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00014-of-00025.safetensors", "model.layers.41.self_attn.v_proj.bias": "model-00014-of-00025.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00014-of-00025.safetensors", "model.layers.42.input_layernorm.weight": "model-00014-of-00025.safetensors", "model.layers.42.moe.mlp.0.down_proj.weight": "model-00014-of-00025.safetensors", "model.layers.42.moe.mlp.1.down_proj.weight": "model-00014-of-00025.safetensors", "model.layers.42.moe.mlp.0.gate_proj.weight": "model-00014-of-00025.safetensors", "model.layers.42.moe.mlp.1.gate_proj.weight": "model-00014-of-00025.safetensors", "model.layers.42.moe.mlp.0.up_proj.weight": "model-00014-of-00025.safetensors", "model.layers.42.moe.mlp.1.up_proj.weight": "model-00014-of-00025.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00014-of-00025.safetensors", "model.layers.42.self_attn.k_proj.bias": "model-00014-of-00025.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00014-of-00025.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00014-of-00025.safetensors", "model.layers.42.self_attn.q_proj.bias": "model-00014-of-00025.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00014-of-00025.safetensors", "model.layers.42.self_attn.v_proj.bias": "model-00014-of-00025.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00014-of-00025.safetensors", "model.layers.43.input_layernorm.weight": "model-00014-of-00025.safetensors", "model.layers.43.moe.mlp.0.down_proj.weight": "model-00014-of-00025.safetensors", "model.layers.43.moe.mlp.1.down_proj.weight": "model-00014-of-00025.safetensors", "model.layers.43.moe.mlp.0.gate_proj.weight": "model-00014-of-00025.safetensors", "model.layers.43.moe.mlp.1.gate_proj.weight": "model-00014-of-00025.safetensors", "model.layers.43.moe.mlp.0.up_proj.weight": "model-00014-of-00025.safetensors", "model.layers.43.moe.mlp.1.up_proj.weight": "model-00014-of-00025.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00014-of-00025.safetensors", "model.layers.43.self_attn.k_proj.bias": "model-00014-of-00025.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00014-of-00025.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00014-of-00025.safetensors", "model.layers.43.self_attn.q_proj.bias": "model-00014-of-00025.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00014-of-00025.safetensors", "model.layers.43.self_attn.v_proj.bias": "model-00014-of-00025.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00014-of-00025.safetensors", "model.layers.44.input_layernorm.weight": "model-00014-of-00025.safetensors", "model.layers.44.moe.mlp.0.down_proj.weight": "model-00014-of-00025.safetensors", "model.layers.44.moe.mlp.1.down_proj.weight": "model-00014-of-00025.safetensors", "model.layers.44.moe.mlp.0.gate_proj.weight": "model-00014-of-00025.safetensors", "model.layers.44.moe.mlp.1.gate_proj.weight": "model-00014-of-00025.safetensors", "model.layers.44.moe.mlp.0.up_proj.weight": "model-00014-of-00025.safetensors", "model.layers.44.moe.mlp.1.up_proj.weight": "model-00014-of-00025.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00014-of-00025.safetensors", "model.layers.44.self_attn.k_proj.bias": "model-00014-of-00025.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00014-of-00025.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00014-of-00025.safetensors", "model.layers.44.self_attn.q_proj.bias": "model-00014-of-00025.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00015-of-00025.safetensors", "model.layers.44.self_attn.v_proj.bias": "model-00015-of-00025.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00015-of-00025.safetensors", "model.layers.45.input_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.45.moe.mlp.0.down_proj.weight": "model-00015-of-00025.safetensors", "model.layers.45.moe.mlp.1.down_proj.weight": "model-00015-of-00025.safetensors", "model.layers.45.moe.mlp.0.gate_proj.weight": "model-00015-of-00025.safetensors", "model.layers.45.moe.mlp.1.gate_proj.weight": "model-00015-of-00025.safetensors", "model.layers.45.moe.mlp.0.up_proj.weight": "model-00015-of-00025.safetensors", "model.layers.45.moe.mlp.1.up_proj.weight": "model-00015-of-00025.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.45.self_attn.k_proj.bias": "model-00015-of-00025.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00015-of-00025.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00015-of-00025.safetensors", "model.layers.45.self_attn.q_proj.bias": "model-00015-of-00025.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00015-of-00025.safetensors", "model.layers.45.self_attn.v_proj.bias": "model-00015-of-00025.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00015-of-00025.safetensors", "model.layers.46.input_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.46.moe.mlp.0.down_proj.weight": "model-00015-of-00025.safetensors", "model.layers.46.moe.mlp.1.down_proj.weight": "model-00015-of-00025.safetensors", "model.layers.46.moe.mlp.0.gate_proj.weight": "model-00015-of-00025.safetensors", "model.layers.46.moe.mlp.1.gate_proj.weight": "model-00015-of-00025.safetensors", "model.layers.46.moe.mlp.0.up_proj.weight": "model-00015-of-00025.safetensors", "model.layers.46.moe.mlp.1.up_proj.weight": "model-00015-of-00025.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.46.self_attn.k_proj.bias": "model-00015-of-00025.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00015-of-00025.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00015-of-00025.safetensors", "model.layers.46.self_attn.q_proj.bias": "model-00015-of-00025.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00015-of-00025.safetensors", "model.layers.46.self_attn.v_proj.bias": "model-00015-of-00025.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00015-of-00025.safetensors", "model.layers.47.input_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.47.moe.mlp.0.down_proj.weight": "model-00015-of-00025.safetensors", "model.layers.47.moe.mlp.1.down_proj.weight": "model-00015-of-00025.safetensors", "model.layers.47.moe.mlp.0.gate_proj.weight": "model-00015-of-00025.safetensors", "model.layers.47.moe.mlp.1.gate_proj.weight": "model-00015-of-00025.safetensors", "model.layers.47.moe.mlp.0.up_proj.weight": "model-00015-of-00025.safetensors", "model.layers.47.moe.mlp.1.up_proj.weight": "model-00015-of-00025.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.47.self_attn.k_proj.bias": "model-00015-of-00025.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00015-of-00025.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00015-of-00025.safetensors", "model.layers.47.self_attn.q_proj.bias": "model-00015-of-00025.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00015-of-00025.safetensors", "model.layers.47.self_attn.v_proj.bias": "model-00015-of-00025.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00015-of-00025.safetensors", "model.layers.48.input_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.48.moe.mlp.0.down_proj.weight": "model-00015-of-00025.safetensors", "model.layers.48.moe.mlp.1.down_proj.weight": "model-00015-of-00025.safetensors", "model.layers.48.moe.mlp.0.gate_proj.weight": "model-00016-of-00025.safetensors", "model.layers.48.moe.mlp.1.gate_proj.weight": "model-00016-of-00025.safetensors", "model.layers.48.moe.mlp.0.up_proj.weight": "model-00016-of-00025.safetensors", "model.layers.48.moe.mlp.1.up_proj.weight": "model-00016-of-00025.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00016-of-00025.safetensors", "model.layers.48.self_attn.k_proj.bias": "model-00016-of-00025.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00016-of-00025.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00016-of-00025.safetensors", "model.layers.48.self_attn.q_proj.bias": "model-00016-of-00025.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00016-of-00025.safetensors", "model.layers.48.self_attn.v_proj.bias": "model-00016-of-00025.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00016-of-00025.safetensors", "model.layers.49.input_layernorm.weight": "model-00016-of-00025.safetensors", "model.layers.49.moe.mlp.0.down_proj.weight": "model-00016-of-00025.safetensors", "model.layers.49.moe.mlp.1.down_proj.weight": "model-00016-of-00025.safetensors", "model.layers.49.moe.mlp.0.gate_proj.weight": "model-00016-of-00025.safetensors", "model.layers.49.moe.mlp.1.gate_proj.weight": "model-00016-of-00025.safetensors", "model.layers.49.moe.mlp.0.up_proj.weight": "model-00016-of-00025.safetensors", "model.layers.49.moe.mlp.1.up_proj.weight": "model-00016-of-00025.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00016-of-00025.safetensors", "model.layers.49.self_attn.k_proj.bias": "model-00016-of-00025.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00016-of-00025.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00016-of-00025.safetensors", "model.layers.49.self_attn.q_proj.bias": "model-00016-of-00025.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00016-of-00025.safetensors", "model.layers.49.self_attn.v_proj.bias": "model-00016-of-00025.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00016-of-00025.safetensors", "model.layers.50.input_layernorm.weight": "model-00016-of-00025.safetensors", "model.layers.50.moe.mlp.0.down_proj.weight": "model-00016-of-00025.safetensors", "model.layers.50.moe.mlp.1.down_proj.weight": "model-00016-of-00025.safetensors", "model.layers.50.moe.mlp.0.gate_proj.weight": "model-00016-of-00025.safetensors", "model.layers.50.moe.mlp.1.gate_proj.weight": "model-00016-of-00025.safetensors", "model.layers.50.moe.mlp.0.up_proj.weight": "model-00016-of-00025.safetensors", "model.layers.50.moe.mlp.1.up_proj.weight": "model-00016-of-00025.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00016-of-00025.safetensors", "model.layers.50.self_attn.k_proj.bias": "model-00016-of-00025.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00016-of-00025.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00016-of-00025.safetensors", "model.layers.50.self_attn.q_proj.bias": "model-00016-of-00025.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00016-of-00025.safetensors", "model.layers.50.self_attn.v_proj.bias": "model-00016-of-00025.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00016-of-00025.safetensors", "model.layers.51.input_layernorm.weight": "model-00016-of-00025.safetensors", "model.layers.51.moe.mlp.0.down_proj.weight": "model-00016-of-00025.safetensors", "model.layers.51.moe.mlp.1.down_proj.weight": "model-00016-of-00025.safetensors", "model.layers.51.moe.mlp.0.gate_proj.weight": "model-00016-of-00025.safetensors", "model.layers.51.moe.mlp.1.gate_proj.weight": "model-00016-of-00025.safetensors", "model.layers.51.moe.mlp.0.up_proj.weight": "model-00017-of-00025.safetensors", "model.layers.51.moe.mlp.1.up_proj.weight": "model-00017-of-00025.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00017-of-00025.safetensors", "model.layers.51.self_attn.k_proj.bias": "model-00017-of-00025.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00017-of-00025.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00017-of-00025.safetensors", "model.layers.51.self_attn.q_proj.bias": "model-00017-of-00025.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00017-of-00025.safetensors", "model.layers.51.self_attn.v_proj.bias": "model-00017-of-00025.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00017-of-00025.safetensors", "model.layers.52.input_layernorm.weight": "model-00017-of-00025.safetensors", "model.layers.52.moe.mlp.0.down_proj.weight": "model-00017-of-00025.safetensors", "model.layers.52.moe.mlp.1.down_proj.weight": "model-00017-of-00025.safetensors", "model.layers.52.moe.mlp.0.gate_proj.weight": "model-00017-of-00025.safetensors", "model.layers.52.moe.mlp.1.gate_proj.weight": "model-00017-of-00025.safetensors", "model.layers.52.moe.mlp.0.up_proj.weight": "model-00017-of-00025.safetensors", "model.layers.52.moe.mlp.1.up_proj.weight": "model-00017-of-00025.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00017-of-00025.safetensors", "model.layers.52.self_attn.k_proj.bias": "model-00017-of-00025.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00017-of-00025.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00017-of-00025.safetensors", "model.layers.52.self_attn.q_proj.bias": "model-00017-of-00025.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00017-of-00025.safetensors", "model.layers.52.self_attn.v_proj.bias": "model-00017-of-00025.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00017-of-00025.safetensors", "model.layers.53.input_layernorm.weight": "model-00017-of-00025.safetensors", "model.layers.53.moe.mlp.0.down_proj.weight": "model-00017-of-00025.safetensors", "model.layers.53.moe.mlp.1.down_proj.weight": "model-00017-of-00025.safetensors", "model.layers.53.moe.mlp.0.gate_proj.weight": "model-00017-of-00025.safetensors", "model.layers.53.moe.mlp.1.gate_proj.weight": "model-00017-of-00025.safetensors", "model.layers.53.moe.mlp.0.up_proj.weight": "model-00017-of-00025.safetensors", "model.layers.53.moe.mlp.1.up_proj.weight": "model-00017-of-00025.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00017-of-00025.safetensors", "model.layers.53.self_attn.k_proj.bias": "model-00017-of-00025.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00017-of-00025.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00017-of-00025.safetensors", "model.layers.53.self_attn.q_proj.bias": "model-00017-of-00025.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00017-of-00025.safetensors", "model.layers.53.self_attn.v_proj.bias": "model-00017-of-00025.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00017-of-00025.safetensors", "model.layers.54.input_layernorm.weight": "model-00017-of-00025.safetensors", "model.layers.54.moe.mlp.0.down_proj.weight": "model-00017-of-00025.safetensors", "model.layers.54.moe.mlp.1.down_proj.weight": "model-00017-of-00025.safetensors", "model.layers.54.moe.mlp.0.gate_proj.weight": "model-00017-of-00025.safetensors", "model.layers.54.moe.mlp.1.gate_proj.weight": "model-00017-of-00025.safetensors", "model.layers.54.moe.mlp.0.up_proj.weight": "model-00017-of-00025.safetensors", "model.layers.54.moe.mlp.1.up_proj.weight": "model-00017-of-00025.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00017-of-00025.safetensors", "model.layers.54.self_attn.k_proj.bias": "model-00017-of-00025.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00017-of-00025.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00017-of-00025.safetensors", "model.layers.54.self_attn.q_proj.bias": "model-00017-of-00025.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00018-of-00025.safetensors", "model.layers.54.self_attn.v_proj.bias": "model-00018-of-00025.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00018-of-00025.safetensors", "model.layers.55.input_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.55.moe.mlp.0.down_proj.weight": "model-00018-of-00025.safetensors", "model.layers.55.moe.mlp.1.down_proj.weight": "model-00018-of-00025.safetensors", "model.layers.55.moe.mlp.0.gate_proj.weight": "model-00018-of-00025.safetensors", "model.layers.55.moe.mlp.1.gate_proj.weight": "model-00018-of-00025.safetensors", "model.layers.55.moe.mlp.0.up_proj.weight": "model-00018-of-00025.safetensors", "model.layers.55.moe.mlp.1.up_proj.weight": "model-00018-of-00025.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.55.self_attn.k_proj.bias": "model-00018-of-00025.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00018-of-00025.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00018-of-00025.safetensors", "model.layers.55.self_attn.q_proj.bias": "model-00018-of-00025.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00018-of-00025.safetensors", "model.layers.55.self_attn.v_proj.bias": "model-00018-of-00025.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00018-of-00025.safetensors", "model.layers.56.input_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.56.moe.mlp.0.down_proj.weight": "model-00018-of-00025.safetensors", "model.layers.56.moe.mlp.1.down_proj.weight": "model-00018-of-00025.safetensors", "model.layers.56.moe.mlp.0.gate_proj.weight": "model-00018-of-00025.safetensors", "model.layers.56.moe.mlp.1.gate_proj.weight": "model-00018-of-00025.safetensors", "model.layers.56.moe.mlp.0.up_proj.weight": "model-00018-of-00025.safetensors", "model.layers.56.moe.mlp.1.up_proj.weight": "model-00018-of-00025.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.56.self_attn.k_proj.bias": "model-00018-of-00025.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00018-of-00025.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00018-of-00025.safetensors", "model.layers.56.self_attn.q_proj.bias": "model-00018-of-00025.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00018-of-00025.safetensors", "model.layers.56.self_attn.v_proj.bias": "model-00018-of-00025.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00018-of-00025.safetensors", "model.layers.57.input_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.57.moe.mlp.0.down_proj.weight": "model-00018-of-00025.safetensors", "model.layers.57.moe.mlp.1.down_proj.weight": "model-00018-of-00025.safetensors", "model.layers.57.moe.mlp.0.gate_proj.weight": "model-00018-of-00025.safetensors", "model.layers.57.moe.mlp.1.gate_proj.weight": "model-00018-of-00025.safetensors", "model.layers.57.moe.mlp.0.up_proj.weight": "model-00018-of-00025.safetensors", "model.layers.57.moe.mlp.1.up_proj.weight": "model-00018-of-00025.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.57.self_attn.k_proj.bias": "model-00018-of-00025.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00018-of-00025.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00018-of-00025.safetensors", "model.layers.57.self_attn.q_proj.bias": "model-00018-of-00025.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00018-of-00025.safetensors", "model.layers.57.self_attn.v_proj.bias": "model-00018-of-00025.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00018-of-00025.safetensors", "model.layers.58.input_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.58.moe.mlp.0.down_proj.weight": "model-00018-of-00025.safetensors", "model.layers.58.moe.mlp.1.down_proj.weight": "model-00018-of-00025.safetensors", "model.layers.58.moe.mlp.0.gate_proj.weight": "model-00019-of-00025.safetensors", "model.layers.58.moe.mlp.1.gate_proj.weight": "model-00019-of-00025.safetensors", "model.layers.58.moe.mlp.0.up_proj.weight": "model-00019-of-00025.safetensors", "model.layers.58.moe.mlp.1.up_proj.weight": "model-00019-of-00025.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00019-of-00025.safetensors", "model.layers.58.self_attn.k_proj.bias": "model-00019-of-00025.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00019-of-00025.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00019-of-00025.safetensors", "model.layers.58.self_attn.q_proj.bias": "model-00019-of-00025.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00019-of-00025.safetensors", "model.layers.58.self_attn.v_proj.bias": "model-00019-of-00025.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00019-of-00025.safetensors", "model.layers.59.input_layernorm.weight": "model-00019-of-00025.safetensors", "model.layers.59.moe.mlp.0.down_proj.weight": "model-00019-of-00025.safetensors", "model.layers.59.moe.mlp.1.down_proj.weight": "model-00019-of-00025.safetensors", "model.layers.59.moe.mlp.0.gate_proj.weight": "model-00019-of-00025.safetensors", "model.layers.59.moe.mlp.1.gate_proj.weight": "model-00019-of-00025.safetensors", "model.layers.59.moe.mlp.0.up_proj.weight": "model-00019-of-00025.safetensors", "model.layers.59.moe.mlp.1.up_proj.weight": "model-00019-of-00025.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00019-of-00025.safetensors", "model.layers.59.self_attn.k_proj.bias": "model-00019-of-00025.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00019-of-00025.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00019-of-00025.safetensors", "model.layers.59.self_attn.q_proj.bias": "model-00019-of-00025.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00019-of-00025.safetensors", "model.layers.59.self_attn.v_proj.bias": "model-00019-of-00025.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00019-of-00025.safetensors", "model.layers.60.input_layernorm.weight": "model-00019-of-00025.safetensors", "model.layers.60.moe.mlp.0.down_proj.weight": "model-00019-of-00025.safetensors", "model.layers.60.moe.mlp.1.down_proj.weight": "model-00019-of-00025.safetensors", "model.layers.60.moe.mlp.0.gate_proj.weight": "model-00019-of-00025.safetensors", "model.layers.60.moe.mlp.1.gate_proj.weight": "model-00019-of-00025.safetensors", "model.layers.60.moe.mlp.0.up_proj.weight": "model-00019-of-00025.safetensors", "model.layers.60.moe.mlp.1.up_proj.weight": "model-00019-of-00025.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00019-of-00025.safetensors", "model.layers.60.self_attn.k_proj.bias": "model-00019-of-00025.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00019-of-00025.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00019-of-00025.safetensors", "model.layers.60.self_attn.q_proj.bias": "model-00019-of-00025.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00019-of-00025.safetensors", "model.layers.60.self_attn.v_proj.bias": "model-00019-of-00025.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00019-of-00025.safetensors", "model.layers.61.input_layernorm.weight": "model-00019-of-00025.safetensors", "model.layers.61.moe.mlp.0.down_proj.weight": "model-00019-of-00025.safetensors", "model.layers.61.moe.mlp.1.down_proj.weight": "model-00019-of-00025.safetensors", "model.layers.61.moe.mlp.0.gate_proj.weight": "model-00019-of-00025.safetensors", "model.layers.61.moe.mlp.1.gate_proj.weight": "model-00019-of-00025.safetensors", "model.layers.61.moe.mlp.0.up_proj.weight": "model-00020-of-00025.safetensors", "model.layers.61.moe.mlp.1.up_proj.weight": "model-00020-of-00025.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00020-of-00025.safetensors", "model.layers.61.self_attn.k_proj.bias": "model-00020-of-00025.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00020-of-00025.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00020-of-00025.safetensors", "model.layers.61.self_attn.q_proj.bias": "model-00020-of-00025.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00020-of-00025.safetensors", "model.layers.61.self_attn.v_proj.bias": "model-00020-of-00025.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00020-of-00025.safetensors", "model.layers.62.input_layernorm.weight": "model-00020-of-00025.safetensors", "model.layers.62.moe.mlp.0.down_proj.weight": "model-00020-of-00025.safetensors", "model.layers.62.moe.mlp.1.down_proj.weight": "model-00020-of-00025.safetensors", "model.layers.62.moe.mlp.0.gate_proj.weight": "model-00020-of-00025.safetensors", "model.layers.62.moe.mlp.1.gate_proj.weight": "model-00020-of-00025.safetensors", "model.layers.62.moe.mlp.0.up_proj.weight": "model-00020-of-00025.safetensors", "model.layers.62.moe.mlp.1.up_proj.weight": "model-00020-of-00025.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00020-of-00025.safetensors", "model.layers.62.self_attn.k_proj.bias": "model-00020-of-00025.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00020-of-00025.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00020-of-00025.safetensors", "model.layers.62.self_attn.q_proj.bias": "model-00020-of-00025.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00020-of-00025.safetensors", "model.layers.62.self_attn.v_proj.bias": "model-00020-of-00025.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00020-of-00025.safetensors", "model.layers.63.input_layernorm.weight": "model-00020-of-00025.safetensors", "model.layers.63.moe.mlp.0.down_proj.weight": "model-00020-of-00025.safetensors", "model.layers.63.moe.mlp.1.down_proj.weight": "model-00020-of-00025.safetensors", "model.layers.63.moe.mlp.0.gate_proj.weight": "model-00020-of-00025.safetensors", "model.layers.63.moe.mlp.1.gate_proj.weight": "model-00020-of-00025.safetensors", "model.layers.63.moe.mlp.0.up_proj.weight": "model-00020-of-00025.safetensors", "model.layers.63.moe.mlp.1.up_proj.weight": "model-00020-of-00025.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00020-of-00025.safetensors", "model.layers.63.self_attn.k_proj.bias": "model-00020-of-00025.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00020-of-00025.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00020-of-00025.safetensors", "model.layers.63.self_attn.q_proj.bias": "model-00020-of-00025.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00020-of-00025.safetensors", "model.layers.63.self_attn.v_proj.bias": "model-00020-of-00025.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00020-of-00025.safetensors", "model.layers.64.input_layernorm.weight": "model-00020-of-00025.safetensors", "model.layers.64.moe.mlp.0.down_proj.weight": "model-00020-of-00025.safetensors", "model.layers.64.moe.mlp.1.down_proj.weight": "model-00020-of-00025.safetensors", "model.layers.64.moe.mlp.0.gate_proj.weight": "model-00020-of-00025.safetensors", "model.layers.64.moe.mlp.1.gate_proj.weight": "model-00020-of-00025.safetensors", "model.layers.64.moe.mlp.0.up_proj.weight": "model-00020-of-00025.safetensors", "model.layers.64.moe.mlp.1.up_proj.weight": "model-00020-of-00025.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00020-of-00025.safetensors", "model.layers.64.self_attn.k_proj.bias": "model-00020-of-00025.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00020-of-00025.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00020-of-00025.safetensors", "model.layers.64.self_attn.q_proj.bias": "model-00020-of-00025.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00021-of-00025.safetensors", "model.layers.64.self_attn.v_proj.bias": "model-00021-of-00025.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00021-of-00025.safetensors", "model.layers.65.input_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.65.moe.mlp.0.down_proj.weight": "model-00021-of-00025.safetensors", "model.layers.65.moe.mlp.1.down_proj.weight": "model-00021-of-00025.safetensors", "model.layers.65.moe.mlp.0.gate_proj.weight": "model-00021-of-00025.safetensors", "model.layers.65.moe.mlp.1.gate_proj.weight": "model-00021-of-00025.safetensors", "model.layers.65.moe.mlp.0.up_proj.weight": "model-00021-of-00025.safetensors", "model.layers.65.moe.mlp.1.up_proj.weight": "model-00021-of-00025.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.65.self_attn.k_proj.bias": "model-00021-of-00025.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00021-of-00025.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00021-of-00025.safetensors", "model.layers.65.self_attn.q_proj.bias": "model-00021-of-00025.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00021-of-00025.safetensors", "model.layers.65.self_attn.v_proj.bias": "model-00021-of-00025.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00021-of-00025.safetensors", "model.layers.66.input_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.66.moe.mlp.0.down_proj.weight": "model-00021-of-00025.safetensors", "model.layers.66.moe.mlp.1.down_proj.weight": "model-00021-of-00025.safetensors", "model.layers.66.moe.mlp.0.gate_proj.weight": "model-00021-of-00025.safetensors", "model.layers.66.moe.mlp.1.gate_proj.weight": "model-00021-of-00025.safetensors", "model.layers.66.moe.mlp.0.up_proj.weight": "model-00021-of-00025.safetensors", "model.layers.66.moe.mlp.1.up_proj.weight": "model-00021-of-00025.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.66.self_attn.k_proj.bias": "model-00021-of-00025.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00021-of-00025.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00021-of-00025.safetensors", "model.layers.66.self_attn.q_proj.bias": "model-00021-of-00025.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00021-of-00025.safetensors", "model.layers.66.self_attn.v_proj.bias": "model-00021-of-00025.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00021-of-00025.safetensors", "model.layers.67.input_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.67.moe.mlp.0.down_proj.weight": "model-00021-of-00025.safetensors", "model.layers.67.moe.mlp.1.down_proj.weight": "model-00021-of-00025.safetensors", "model.layers.67.moe.mlp.0.gate_proj.weight": "model-00021-of-00025.safetensors", "model.layers.67.moe.mlp.1.gate_proj.weight": "model-00021-of-00025.safetensors", "model.layers.67.moe.mlp.0.up_proj.weight": "model-00021-of-00025.safetensors", "model.layers.67.moe.mlp.1.up_proj.weight": "model-00021-of-00025.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.67.self_attn.k_proj.bias": "model-00021-of-00025.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00021-of-00025.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00021-of-00025.safetensors", "model.layers.67.self_attn.q_proj.bias": "model-00021-of-00025.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00021-of-00025.safetensors", "model.layers.67.self_attn.v_proj.bias": "model-00021-of-00025.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00021-of-00025.safetensors", "model.layers.68.input_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.68.moe.mlp.0.down_proj.weight": "model-00021-of-00025.safetensors", "model.layers.68.moe.mlp.1.down_proj.weight": "model-00021-of-00025.safetensors", "model.layers.68.moe.mlp.0.gate_proj.weight": "model-00022-of-00025.safetensors", "model.layers.68.moe.mlp.1.gate_proj.weight": "model-00022-of-00025.safetensors", "model.layers.68.moe.mlp.0.up_proj.weight": "model-00022-of-00025.safetensors", "model.layers.68.moe.mlp.1.up_proj.weight": "model-00022-of-00025.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00022-of-00025.safetensors", "model.layers.68.self_attn.k_proj.bias": "model-00022-of-00025.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00022-of-00025.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00022-of-00025.safetensors", "model.layers.68.self_attn.q_proj.bias": "model-00022-of-00025.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00022-of-00025.safetensors", "model.layers.68.self_attn.v_proj.bias": "model-00022-of-00025.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00022-of-00025.safetensors", "model.layers.69.input_layernorm.weight": "model-00022-of-00025.safetensors", "model.layers.69.moe.mlp.0.down_proj.weight": "model-00022-of-00025.safetensors", "model.layers.69.moe.mlp.1.down_proj.weight": "model-00022-of-00025.safetensors", "model.layers.69.moe.mlp.0.gate_proj.weight": "model-00022-of-00025.safetensors", "model.layers.69.moe.mlp.1.gate_proj.weight": "model-00022-of-00025.safetensors", "model.layers.69.moe.mlp.0.up_proj.weight": "model-00022-of-00025.safetensors", "model.layers.69.moe.mlp.1.up_proj.weight": "model-00022-of-00025.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00022-of-00025.safetensors", "model.layers.69.self_attn.k_proj.bias": "model-00022-of-00025.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00022-of-00025.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00022-of-00025.safetensors", "model.layers.69.self_attn.q_proj.bias": "model-00022-of-00025.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00022-of-00025.safetensors", "model.layers.69.self_attn.v_proj.bias": "model-00022-of-00025.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00022-of-00025.safetensors", "model.layers.70.input_layernorm.weight": "model-00022-of-00025.safetensors", "model.layers.70.moe.mlp.0.down_proj.weight": "model-00022-of-00025.safetensors", "model.layers.70.moe.mlp.1.down_proj.weight": "model-00022-of-00025.safetensors", "model.layers.70.moe.mlp.0.gate_proj.weight": "model-00022-of-00025.safetensors", "model.layers.70.moe.mlp.1.gate_proj.weight": "model-00022-of-00025.safetensors", "model.layers.70.moe.mlp.0.up_proj.weight": "model-00022-of-00025.safetensors", "model.layers.70.moe.mlp.1.up_proj.weight": "model-00022-of-00025.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00022-of-00025.safetensors", "model.layers.70.self_attn.k_proj.bias": "model-00022-of-00025.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00022-of-00025.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00022-of-00025.safetensors", "model.layers.70.self_attn.q_proj.bias": "model-00022-of-00025.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00022-of-00025.safetensors", "model.layers.70.self_attn.v_proj.bias": "model-00022-of-00025.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00022-of-00025.safetensors", "model.layers.71.input_layernorm.weight": "model-00022-of-00025.safetensors", "model.layers.71.moe.mlp.0.down_proj.weight": "model-00022-of-00025.safetensors", "model.layers.71.moe.mlp.1.down_proj.weight": "model-00022-of-00025.safetensors", "model.layers.71.moe.mlp.0.gate_proj.weight": "model-00022-of-00025.safetensors", "model.layers.71.moe.mlp.1.gate_proj.weight": "model-00022-of-00025.safetensors", "model.layers.71.moe.mlp.0.up_proj.weight": "model-00023-of-00025.safetensors", "model.layers.71.moe.mlp.1.up_proj.weight": "model-00023-of-00025.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.71.self_attn.k_proj.bias": "model-00023-of-00025.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00023-of-00025.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00023-of-00025.safetensors", "model.layers.71.self_attn.q_proj.bias": "model-00023-of-00025.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00023-of-00025.safetensors", "model.layers.71.self_attn.v_proj.bias": "model-00023-of-00025.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00023-of-00025.safetensors", "model.layers.72.input_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.72.moe.mlp.0.down_proj.weight": "model-00023-of-00025.safetensors", "model.layers.72.moe.mlp.1.down_proj.weight": "model-00023-of-00025.safetensors", "model.layers.72.moe.mlp.0.gate_proj.weight": "model-00023-of-00025.safetensors", "model.layers.72.moe.mlp.1.gate_proj.weight": "model-00023-of-00025.safetensors", "model.layers.72.moe.mlp.0.up_proj.weight": "model-00023-of-00025.safetensors", "model.layers.72.moe.mlp.1.up_proj.weight": "model-00023-of-00025.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.72.self_attn.k_proj.bias": "model-00023-of-00025.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00023-of-00025.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00023-of-00025.safetensors", "model.layers.72.self_attn.q_proj.bias": "model-00023-of-00025.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00023-of-00025.safetensors", "model.layers.72.self_attn.v_proj.bias": "model-00023-of-00025.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00023-of-00025.safetensors", "model.layers.73.input_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.73.moe.mlp.0.down_proj.weight": "model-00023-of-00025.safetensors", "model.layers.73.moe.mlp.1.down_proj.weight": "model-00023-of-00025.safetensors", "model.layers.73.moe.mlp.0.gate_proj.weight": "model-00023-of-00025.safetensors", "model.layers.73.moe.mlp.1.gate_proj.weight": "model-00023-of-00025.safetensors", "model.layers.73.moe.mlp.0.up_proj.weight": "model-00023-of-00025.safetensors", "model.layers.73.moe.mlp.1.up_proj.weight": "model-00023-of-00025.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.73.self_attn.k_proj.bias": "model-00023-of-00025.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00023-of-00025.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00023-of-00025.safetensors", "model.layers.73.self_attn.q_proj.bias": "model-00023-of-00025.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00023-of-00025.safetensors", "model.layers.73.self_attn.v_proj.bias": "model-00023-of-00025.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00023-of-00025.safetensors", "model.layers.74.input_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.74.moe.mlp.0.down_proj.weight": "model-00023-of-00025.safetensors", "model.layers.74.moe.mlp.1.down_proj.weight": "model-00023-of-00025.safetensors", "model.layers.74.moe.mlp.0.gate_proj.weight": "model-00023-of-00025.safetensors", "model.layers.74.moe.mlp.1.gate_proj.weight": "model-00023-of-00025.safetensors", "model.layers.74.moe.mlp.0.up_proj.weight": "model-00023-of-00025.safetensors", "model.layers.74.moe.mlp.1.up_proj.weight": "model-00023-of-00025.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.74.self_attn.k_proj.bias": "model-00023-of-00025.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00023-of-00025.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00023-of-00025.safetensors", "model.layers.74.self_attn.q_proj.bias": "model-00023-of-00025.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.74.self_attn.v_proj.bias": "model-00024-of-00025.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.75.input_layernorm.weight": "model-00024-of-00025.safetensors", "model.layers.75.moe.mlp.0.down_proj.weight": "model-00024-of-00025.safetensors", "model.layers.75.moe.mlp.1.down_proj.weight": "model-00024-of-00025.safetensors", "model.layers.75.moe.mlp.0.gate_proj.weight": "model-00024-of-00025.safetensors", "model.layers.75.moe.mlp.1.gate_proj.weight": "model-00024-of-00025.safetensors", "model.layers.75.moe.mlp.0.up_proj.weight": "model-00024-of-00025.safetensors", "model.layers.75.moe.mlp.1.up_proj.weight": "model-00024-of-00025.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00024-of-00025.safetensors", "model.layers.75.self_attn.k_proj.bias": "model-00024-of-00025.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.75.self_attn.q_proj.bias": "model-00024-of-00025.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.75.self_attn.v_proj.bias": "model-00024-of-00025.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.76.input_layernorm.weight": "model-00024-of-00025.safetensors", "model.layers.76.moe.mlp.0.down_proj.weight": "model-00024-of-00025.safetensors", "model.layers.76.moe.mlp.1.down_proj.weight": "model-00024-of-00025.safetensors", "model.layers.76.moe.mlp.0.gate_proj.weight": "model-00024-of-00025.safetensors", "model.layers.76.moe.mlp.1.gate_proj.weight": "model-00024-of-00025.safetensors", "model.layers.76.moe.mlp.0.up_proj.weight": "model-00024-of-00025.safetensors", "model.layers.76.moe.mlp.1.up_proj.weight": "model-00024-of-00025.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00024-of-00025.safetensors", "model.layers.76.self_attn.k_proj.bias": "model-00024-of-00025.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.76.self_attn.q_proj.bias": "model-00024-of-00025.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.76.self_attn.v_proj.bias": "model-00024-of-00025.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.77.input_layernorm.weight": "model-00024-of-00025.safetensors", "model.layers.77.moe.mlp.0.down_proj.weight": "model-00024-of-00025.safetensors", "model.layers.77.moe.mlp.1.down_proj.weight": "model-00024-of-00025.safetensors", "model.layers.77.moe.mlp.0.gate_proj.weight": "model-00024-of-00025.safetensors", "model.layers.77.moe.mlp.1.gate_proj.weight": "model-00024-of-00025.safetensors", "model.layers.77.moe.mlp.0.up_proj.weight": "model-00024-of-00025.safetensors", "model.layers.77.moe.mlp.1.up_proj.weight": "model-00024-of-00025.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00024-of-00025.safetensors", "model.layers.77.self_attn.k_proj.bias": "model-00024-of-00025.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.77.self_attn.q_proj.bias": "model-00024-of-00025.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.77.self_attn.v_proj.bias": "model-00024-of-00025.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.78.input_layernorm.weight": "model-00024-of-00025.safetensors", "model.layers.78.moe.mlp.0.down_proj.weight": "model-00024-of-00025.safetensors", "model.layers.78.moe.mlp.1.down_proj.weight": "model-00024-of-00025.safetensors", "model.layers.78.moe.mlp.0.gate_proj.weight": "model-00025-of-00025.safetensors", "model.layers.78.moe.mlp.1.gate_proj.weight": "model-00025-of-00025.safetensors", "model.layers.78.moe.mlp.0.up_proj.weight": "model-00025-of-00025.safetensors", "model.layers.78.moe.mlp.1.up_proj.weight": "model-00025-of-00025.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00025-of-00025.safetensors", "model.layers.78.self_attn.k_proj.bias": "model-00025-of-00025.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00025-of-00025.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.78.self_attn.q_proj.bias": "model-00025-of-00025.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00025-of-00025.safetensors", "model.layers.78.self_attn.v_proj.bias": "model-00025-of-00025.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00025-of-00025.safetensors", "model.layers.79.input_layernorm.weight": "model-00025-of-00025.safetensors", "model.layers.79.moe.mlp.0.down_proj.weight": "model-00025-of-00025.safetensors", "model.layers.79.moe.mlp.1.down_proj.weight": "model-00025-of-00025.safetensors", "model.layers.79.moe.mlp.0.gate_proj.weight": "model-00025-of-00025.safetensors", "model.layers.79.moe.mlp.1.gate_proj.weight": "model-00025-of-00025.safetensors", "model.layers.79.moe.mlp.0.up_proj.weight": "model-00025-of-00025.safetensors", "model.layers.79.moe.mlp.1.up_proj.weight": "model-00025-of-00025.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00025-of-00025.safetensors", "model.layers.79.self_attn.k_proj.bias": "model-00025-of-00025.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00025-of-00025.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.79.self_attn.q_proj.bias": "model-00025-of-00025.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00025-of-00025.safetensors", "model.layers.79.self_attn.v_proj.bias": "model-00025-of-00025.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00025-of-00025.safetensors", "model.layers.0.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.1.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.2.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.3.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.4.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.5.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.6.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.7.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.8.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.9.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.10.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.11.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.12.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.13.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.14.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.15.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.16.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.17.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.18.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.19.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.20.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.21.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.22.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.23.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.24.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.25.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.26.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.27.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.28.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.29.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.30.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.31.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.32.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.33.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.34.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.35.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.36.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.37.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.38.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.39.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.40.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.41.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.42.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.43.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.44.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.45.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.46.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.47.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.48.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.49.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.50.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.51.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.52.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.53.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.54.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.55.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.56.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.57.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.58.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.59.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.60.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.61.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.62.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.63.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.64.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.65.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.66.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.67.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.68.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.69.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.70.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.71.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.72.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.73.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.74.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.75.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.76.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.77.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.78.moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.79.moe.gate.weight": "model-00025-of-00025.safetensors"}}