{ "metadata": { "total_size": 14631804928 }, "weight_map": { "lm_head.bias": "pytorch_model-00002-of-00002.bin", "lm_head.weight": "pytorch_model-00002-of-00002.bin", "transformer.h.0.attn.causal_mask": "pytorch_model-00001-of-00002.bin", "transformer.h.0.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.0.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00002.bin", "transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.0.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin", "transformer.h.0.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.0.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin", "transformer.h.0.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.1.attn.causal_mask": "pytorch_model-00001-of-00002.bin", "transformer.h.1.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.1.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00002.bin", "transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.1.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin", "transformer.h.1.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.1.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin", "transformer.h.1.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.10.attn.causal_mask": "pytorch_model-00001-of-00002.bin", "transformer.h.10.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.10.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.10.ln_1.bias": "pytorch_model-00001-of-00002.bin", "transformer.h.10.ln_1.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.10.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin", "transformer.h.10.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.10.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin", "transformer.h.10.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.11.attn.causal_mask": "pytorch_model-00001-of-00002.bin", "transformer.h.11.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin", "transformer.h.11.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.11.ln_1.bias": "pytorch_model-00001-of-00002.bin", "transformer.h.11.ln_1.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.11.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin", "transformer.h.11.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin", "transformer.h.11.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin", "transformer.h.11.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin", "transformer.h.12.attn.causal_mask": "pytorch_model-00002-of-00002.bin", "transformer.h.12.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin", "transformer.h.12.attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin", "transformer.h.12.ln_1.bias": "pytorch_model-00002-of-00002.bin", "transformer.h.12.ln_1.weight": "pytorch_model-00002-of-00002.bin", "transformer.h.12.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin", "transformer.h.12.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin", "transformer.h.12.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin", "transformer.h.12.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin", "transformer.h.13.attn.causal_mask": "pytorch_model-00002-of-00002.bin", "transformer.h.13.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin", "transformer.h.13.attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin", "transformer.h.13.ln_1.bias": "pytorch_model-00002-of-00002.bin", "transformer.h.13.ln_1.weight": "pytorch_model-00002-of-00002.bin", "transformer.h.13.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin", "transformer.h.13.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin", "transformer.h.13.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin", "transformer.h.13.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin", "transformer.h.14.attn.causal_mask": "pytorch_model-00002-of-00002.bin", "transformer.h.14.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin", "transformer.h.14.attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin", "transformer.h.14.ln_1.bias": "pytorch_model-00002-of-00002.bin", "transformer.h.14.ln_1.weight": "pytorch_model-00002-of-00002.bin", "transformer.h.14.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin", "transformer.h.14.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin", "transformer.h.14.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin", "transformer.h.14.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin", "transformer.h.15.attn.causal_mask": "pytorch_model-00002-of-00002.bin", "transformer.h.15.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin", "transformer.h.15.attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin", "transformer.h.15.ln_1.bias": "pytorch_model-00002-of-00002.bin", "transformer.h.15.ln_1.weight": "pytorch_model-00002-of-00002.bin", "transformer.h.15.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin", "transformer.h.15.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin", "transformer.h.15.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin", "transformer.h.15.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin", "transformer.h.2.attn.causal_mask": "pytorch_model-00001-of-00002.bin", "transformer.h.2.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.2.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00002.bin", "transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.2.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin", "transformer.h.2.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.2.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin", "transformer.h.2.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.3.attn.causal_mask": "pytorch_model-00001-of-00002.bin", "transformer.h.3.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.3.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00002.bin", "transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.3.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin", "transformer.h.3.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.3.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin", "transformer.h.3.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.4.attn.causal_mask": "pytorch_model-00001-of-00002.bin", "transformer.h.4.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.4.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00002.bin", "transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.4.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin", "transformer.h.4.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.4.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin", "transformer.h.4.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.5.attn.causal_mask": "pytorch_model-00001-of-00002.bin", "transformer.h.5.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.5.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00002.bin", "transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.5.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin", "transformer.h.5.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.5.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin", "transformer.h.5.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.6.attn.causal_mask": "pytorch_model-00001-of-00002.bin", "transformer.h.6.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.6.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00002.bin", "transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.6.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin", "transformer.h.6.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.6.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin", "transformer.h.6.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.7.attn.causal_mask": "pytorch_model-00001-of-00002.bin", "transformer.h.7.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.7.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00002.bin", "transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.7.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin", "transformer.h.7.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.7.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin", "transformer.h.7.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.8.attn.causal_mask": "pytorch_model-00001-of-00002.bin", "transformer.h.8.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.8.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.8.ln_1.bias": "pytorch_model-00001-of-00002.bin", "transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.8.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin", "transformer.h.8.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.8.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin", "transformer.h.8.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.9.attn.causal_mask": "pytorch_model-00001-of-00002.bin", "transformer.h.9.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.9.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.9.ln_1.bias": "pytorch_model-00001-of-00002.bin", "transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.9.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin", "transformer.h.9.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin", "transformer.h.9.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin", "transformer.h.9.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin", "transformer.ln_f.bias": "pytorch_model-00002-of-00002.bin", "transformer.ln_f.weight": "pytorch_model-00002-of-00002.bin", "transformer.wte.weight": "pytorch_model-00001-of-00002.bin" } }