| { | |
| "metadata": { | |
| "total_size": 400100480, | |
| "total_parameters": 354823168 | |
| }, | |
| "weight_map": { | |
| "model.h.0.attn.c_attn.bias": "model.safetensors", | |
| "model.h.0.attn.c_attn.biases": "model.safetensors", | |
| "model.h.0.attn.c_attn.scales": "model.safetensors", | |
| "model.h.0.attn.c_attn.weight": "model.safetensors", | |
| "model.h.0.attn.c_proj.bias": "model.safetensors", | |
| "model.h.0.attn.c_proj.biases": "model.safetensors", | |
| "model.h.0.attn.c_proj.scales": "model.safetensors", | |
| "model.h.0.attn.c_proj.weight": "model.safetensors", | |
| "model.h.0.ln_1.bias": "model.safetensors", | |
| "model.h.0.ln_1.weight": "model.safetensors", | |
| "model.h.0.ln_2.bias": "model.safetensors", | |
| "model.h.0.ln_2.weight": "model.safetensors", | |
| "model.h.0.mlp.c_fc.bias": "model.safetensors", | |
| "model.h.0.mlp.c_fc.biases": "model.safetensors", | |
| "model.h.0.mlp.c_fc.scales": "model.safetensors", | |
| "model.h.0.mlp.c_fc.weight": "model.safetensors", | |
| "model.h.0.mlp.c_proj.bias": "model.safetensors", | |
| "model.h.0.mlp.c_proj.biases": "model.safetensors", | |
| "model.h.0.mlp.c_proj.scales": "model.safetensors", | |
| "model.h.0.mlp.c_proj.weight": "model.safetensors", | |
| "model.h.1.attn.c_attn.bias": "model.safetensors", | |
| "model.h.1.attn.c_attn.biases": "model.safetensors", | |
| "model.h.1.attn.c_attn.scales": "model.safetensors", | |
| "model.h.1.attn.c_attn.weight": "model.safetensors", | |
| "model.h.1.attn.c_proj.bias": "model.safetensors", | |
| "model.h.1.attn.c_proj.biases": "model.safetensors", | |
| "model.h.1.attn.c_proj.scales": "model.safetensors", | |
| "model.h.1.attn.c_proj.weight": "model.safetensors", | |
| "model.h.1.ln_1.bias": "model.safetensors", | |
| "model.h.1.ln_1.weight": "model.safetensors", | |
| "model.h.1.ln_2.bias": "model.safetensors", | |
| "model.h.1.ln_2.weight": "model.safetensors", | |
| "model.h.1.mlp.c_fc.bias": "model.safetensors", | |
| "model.h.1.mlp.c_fc.biases": "model.safetensors", | |
| "model.h.1.mlp.c_fc.scales": "model.safetensors", | |
| "model.h.1.mlp.c_fc.weight": "model.safetensors", | |
| "model.h.1.mlp.c_proj.bias": "model.safetensors", | |
| "model.h.1.mlp.c_proj.biases": "model.safetensors", | |
| "model.h.1.mlp.c_proj.scales": "model.safetensors", | |
| "model.h.1.mlp.c_proj.weight": "model.safetensors", | |
| "model.h.10.attn.c_attn.bias": "model.safetensors", | |
| "model.h.10.attn.c_attn.biases": "model.safetensors", | |
| "model.h.10.attn.c_attn.scales": "model.safetensors", | |
| "model.h.10.attn.c_attn.weight": "model.safetensors", | |
| "model.h.10.attn.c_proj.bias": "model.safetensors", | |
| "model.h.10.attn.c_proj.biases": "model.safetensors", | |
| "model.h.10.attn.c_proj.scales": "model.safetensors", | |
| "model.h.10.attn.c_proj.weight": "model.safetensors", | |
| "model.h.10.ln_1.bias": "model.safetensors", | |
| "model.h.10.ln_1.weight": "model.safetensors", | |
| "model.h.10.ln_2.bias": "model.safetensors", | |
| "model.h.10.ln_2.weight": "model.safetensors", | |
| "model.h.10.mlp.c_fc.bias": "model.safetensors", | |
| "model.h.10.mlp.c_fc.biases": "model.safetensors", | |
| "model.h.10.mlp.c_fc.scales": "model.safetensors", | |
| "model.h.10.mlp.c_fc.weight": "model.safetensors", | |
| "model.h.10.mlp.c_proj.bias": "model.safetensors", | |
| "model.h.10.mlp.c_proj.biases": "model.safetensors", | |
| "model.h.10.mlp.c_proj.scales": "model.safetensors", | |
| "model.h.10.mlp.c_proj.weight": "model.safetensors", | |
| "model.h.11.attn.c_attn.bias": "model.safetensors", | |
| "model.h.11.attn.c_attn.biases": "model.safetensors", | |
| "model.h.11.attn.c_attn.scales": "model.safetensors", | |
| "model.h.11.attn.c_attn.weight": "model.safetensors", | |
| "model.h.11.attn.c_proj.bias": "model.safetensors", | |
| "model.h.11.attn.c_proj.biases": "model.safetensors", | |
| "model.h.11.attn.c_proj.scales": "model.safetensors", | |
| "model.h.11.attn.c_proj.weight": "model.safetensors", | |
| "model.h.11.ln_1.bias": "model.safetensors", | |
| "model.h.11.ln_1.weight": "model.safetensors", | |
| "model.h.11.ln_2.bias": "model.safetensors", | |
| "model.h.11.ln_2.weight": "model.safetensors", | |
| "model.h.11.mlp.c_fc.bias": "model.safetensors", | |
| "model.h.11.mlp.c_fc.biases": "model.safetensors", | |
| "model.h.11.mlp.c_fc.scales": "model.safetensors", | |
| "model.h.11.mlp.c_fc.weight": "model.safetensors", | |
| "model.h.11.mlp.c_proj.bias": "model.safetensors", | |
| "model.h.11.mlp.c_proj.biases": "model.safetensors", | |
| "model.h.11.mlp.c_proj.scales": "model.safetensors", | |
| "model.h.11.mlp.c_proj.weight": "model.safetensors", | |
| "model.h.12.attn.c_attn.bias": "model.safetensors", | |
| "model.h.12.attn.c_attn.biases": "model.safetensors", | |
| "model.h.12.attn.c_attn.scales": "model.safetensors", | |
| "model.h.12.attn.c_attn.weight": "model.safetensors", | |
| "model.h.12.attn.c_proj.bias": "model.safetensors", | |
| "model.h.12.attn.c_proj.biases": "model.safetensors", | |
| "model.h.12.attn.c_proj.scales": "model.safetensors", | |
| "model.h.12.attn.c_proj.weight": "model.safetensors", | |
| "model.h.12.ln_1.bias": "model.safetensors", | |
| "model.h.12.ln_1.weight": "model.safetensors", | |
| "model.h.12.ln_2.bias": "model.safetensors", | |
| "model.h.12.ln_2.weight": "model.safetensors", | |
| "model.h.12.mlp.c_fc.bias": "model.safetensors", | |
| "model.h.12.mlp.c_fc.biases": "model.safetensors", | |
| "model.h.12.mlp.c_fc.scales": "model.safetensors", | |
| "model.h.12.mlp.c_fc.weight": "model.safetensors", | |
| "model.h.12.mlp.c_proj.bias": "model.safetensors", | |
| "model.h.12.mlp.c_proj.biases": "model.safetensors", | |
| "model.h.12.mlp.c_proj.scales": "model.safetensors", | |
| "model.h.12.mlp.c_proj.weight": "model.safetensors", | |
| "model.h.13.attn.c_attn.bias": "model.safetensors", | |
| "model.h.13.attn.c_attn.biases": "model.safetensors", | |
| "model.h.13.attn.c_attn.scales": "model.safetensors", | |
| "model.h.13.attn.c_attn.weight": "model.safetensors", | |
| "model.h.13.attn.c_proj.bias": "model.safetensors", | |
| "model.h.13.attn.c_proj.biases": "model.safetensors", | |
| "model.h.13.attn.c_proj.scales": "model.safetensors", | |
| "model.h.13.attn.c_proj.weight": "model.safetensors", | |
| "model.h.13.ln_1.bias": "model.safetensors", | |
| "model.h.13.ln_1.weight": "model.safetensors", | |
| "model.h.13.ln_2.bias": "model.safetensors", | |
| "model.h.13.ln_2.weight": "model.safetensors", | |
| "model.h.13.mlp.c_fc.bias": "model.safetensors", | |
| "model.h.13.mlp.c_fc.biases": "model.safetensors", | |
| "model.h.13.mlp.c_fc.scales": "model.safetensors", | |
| "model.h.13.mlp.c_fc.weight": "model.safetensors", | |
| "model.h.13.mlp.c_proj.bias": "model.safetensors", | |
| "model.h.13.mlp.c_proj.biases": "model.safetensors", | |
| "model.h.13.mlp.c_proj.scales": "model.safetensors", | |
| "model.h.13.mlp.c_proj.weight": "model.safetensors", | |
| "model.h.14.attn.c_attn.bias": "model.safetensors", | |
| "model.h.14.attn.c_attn.biases": "model.safetensors", | |
| "model.h.14.attn.c_attn.scales": "model.safetensors", | |
| "model.h.14.attn.c_attn.weight": "model.safetensors", | |
| "model.h.14.attn.c_proj.bias": "model.safetensors", | |
| "model.h.14.attn.c_proj.biases": "model.safetensors", | |
| "model.h.14.attn.c_proj.scales": "model.safetensors", | |
| "model.h.14.attn.c_proj.weight": "model.safetensors", | |
| "model.h.14.ln_1.bias": "model.safetensors", | |
| "model.h.14.ln_1.weight": "model.safetensors", | |
| "model.h.14.ln_2.bias": "model.safetensors", | |
| "model.h.14.ln_2.weight": "model.safetensors", | |
| "model.h.14.mlp.c_fc.bias": "model.safetensors", | |
| "model.h.14.mlp.c_fc.biases": "model.safetensors", | |
| "model.h.14.mlp.c_fc.scales": "model.safetensors", | |
| "model.h.14.mlp.c_fc.weight": "model.safetensors", | |
| "model.h.14.mlp.c_proj.bias": "model.safetensors", | |
| "model.h.14.mlp.c_proj.biases": "model.safetensors", | |
| "model.h.14.mlp.c_proj.scales": "model.safetensors", | |
| "model.h.14.mlp.c_proj.weight": "model.safetensors", | |
| "model.h.15.attn.c_attn.bias": "model.safetensors", | |
| "model.h.15.attn.c_attn.biases": "model.safetensors", | |
| "model.h.15.attn.c_attn.scales": "model.safetensors", | |
| "model.h.15.attn.c_attn.weight": "model.safetensors", | |
| "model.h.15.attn.c_proj.bias": "model.safetensors", | |
| "model.h.15.attn.c_proj.biases": "model.safetensors", | |
| "model.h.15.attn.c_proj.scales": "model.safetensors", | |
| "model.h.15.attn.c_proj.weight": "model.safetensors", | |
| "model.h.15.ln_1.bias": "model.safetensors", | |
| "model.h.15.ln_1.weight": "model.safetensors", | |
| "model.h.15.ln_2.bias": "model.safetensors", | |
| "model.h.15.ln_2.weight": "model.safetensors", | |
| "model.h.15.mlp.c_fc.bias": "model.safetensors", | |
| "model.h.15.mlp.c_fc.biases": "model.safetensors", | |
| "model.h.15.mlp.c_fc.scales": "model.safetensors", | |
| "model.h.15.mlp.c_fc.weight": "model.safetensors", | |
| "model.h.15.mlp.c_proj.bias": "model.safetensors", | |
| "model.h.15.mlp.c_proj.biases": "model.safetensors", | |
| "model.h.15.mlp.c_proj.scales": "model.safetensors", | |
| "model.h.15.mlp.c_proj.weight": "model.safetensors", | |
| "model.h.16.attn.c_attn.bias": "model.safetensors", | |
| "model.h.16.attn.c_attn.biases": "model.safetensors", | |
| "model.h.16.attn.c_attn.scales": "model.safetensors", | |
| "model.h.16.attn.c_attn.weight": "model.safetensors", | |
| "model.h.16.attn.c_proj.bias": "model.safetensors", | |
| "model.h.16.attn.c_proj.biases": "model.safetensors", | |
| "model.h.16.attn.c_proj.scales": "model.safetensors", | |
| "model.h.16.attn.c_proj.weight": "model.safetensors", | |
| "model.h.16.ln_1.bias": "model.safetensors", | |
| "model.h.16.ln_1.weight": "model.safetensors", | |
| "model.h.16.ln_2.bias": "model.safetensors", | |
| "model.h.16.ln_2.weight": "model.safetensors", | |
| "model.h.16.mlp.c_fc.bias": "model.safetensors", | |
| "model.h.16.mlp.c_fc.biases": "model.safetensors", | |
| "model.h.16.mlp.c_fc.scales": "model.safetensors", | |
| "model.h.16.mlp.c_fc.weight": "model.safetensors", | |
| "model.h.16.mlp.c_proj.bias": "model.safetensors", | |
| "model.h.16.mlp.c_proj.biases": "model.safetensors", | |
| "model.h.16.mlp.c_proj.scales": "model.safetensors", | |
| "model.h.16.mlp.c_proj.weight": "model.safetensors", | |
| "model.h.17.attn.c_attn.bias": "model.safetensors", | |
| "model.h.17.attn.c_attn.biases": "model.safetensors", | |
| "model.h.17.attn.c_attn.scales": "model.safetensors", | |
| "model.h.17.attn.c_attn.weight": "model.safetensors", | |
| "model.h.17.attn.c_proj.bias": "model.safetensors", | |
| "model.h.17.attn.c_proj.biases": "model.safetensors", | |
| "model.h.17.attn.c_proj.scales": "model.safetensors", | |
| "model.h.17.attn.c_proj.weight": "model.safetensors", | |
| "model.h.17.ln_1.bias": "model.safetensors", | |
| "model.h.17.ln_1.weight": "model.safetensors", | |
| "model.h.17.ln_2.bias": "model.safetensors", | |
| "model.h.17.ln_2.weight": "model.safetensors", | |
| "model.h.17.mlp.c_fc.bias": "model.safetensors", | |
| "model.h.17.mlp.c_fc.biases": "model.safetensors", | |
| "model.h.17.mlp.c_fc.scales": "model.safetensors", | |
| "model.h.17.mlp.c_fc.weight": "model.safetensors", | |
| "model.h.17.mlp.c_proj.bias": "model.safetensors", | |
| "model.h.17.mlp.c_proj.biases": "model.safetensors", | |
| "model.h.17.mlp.c_proj.scales": "model.safetensors", | |
| "model.h.17.mlp.c_proj.weight": "model.safetensors", | |
| "model.h.18.attn.c_attn.bias": "model.safetensors", | |
| "model.h.18.attn.c_attn.biases": "model.safetensors", | |
| "model.h.18.attn.c_attn.scales": "model.safetensors", | |
| "model.h.18.attn.c_attn.weight": "model.safetensors", | |
| "model.h.18.attn.c_proj.bias": "model.safetensors", | |
| "model.h.18.attn.c_proj.biases": "model.safetensors", | |
| "model.h.18.attn.c_proj.scales": "model.safetensors", | |
| "model.h.18.attn.c_proj.weight": "model.safetensors", | |
| "model.h.18.ln_1.bias": "model.safetensors", | |
| "model.h.18.ln_1.weight": "model.safetensors", | |
| "model.h.18.ln_2.bias": "model.safetensors", | |
| "model.h.18.ln_2.weight": "model.safetensors", | |
| "model.h.18.mlp.c_fc.bias": "model.safetensors", | |
| "model.h.18.mlp.c_fc.biases": "model.safetensors", | |
| "model.h.18.mlp.c_fc.scales": "model.safetensors", | |
| "model.h.18.mlp.c_fc.weight": "model.safetensors", | |
| "model.h.18.mlp.c_proj.bias": "model.safetensors", | |
| "model.h.18.mlp.c_proj.biases": "model.safetensors", | |
| "model.h.18.mlp.c_proj.scales": "model.safetensors", | |
| "model.h.18.mlp.c_proj.weight": "model.safetensors", | |
| "model.h.19.attn.c_attn.bias": "model.safetensors", | |
| "model.h.19.attn.c_attn.biases": "model.safetensors", | |
| "model.h.19.attn.c_attn.scales": "model.safetensors", | |
| "model.h.19.attn.c_attn.weight": "model.safetensors", | |
| "model.h.19.attn.c_proj.bias": "model.safetensors", | |
| "model.h.19.attn.c_proj.biases": "model.safetensors", | |
| "model.h.19.attn.c_proj.scales": "model.safetensors", | |
| "model.h.19.attn.c_proj.weight": "model.safetensors", | |
| "model.h.19.ln_1.bias": "model.safetensors", | |
| "model.h.19.ln_1.weight": "model.safetensors", | |
| "model.h.19.ln_2.bias": "model.safetensors", | |
| "model.h.19.ln_2.weight": "model.safetensors", | |
| "model.h.19.mlp.c_fc.bias": "model.safetensors", | |
| "model.h.19.mlp.c_fc.biases": "model.safetensors", | |
| "model.h.19.mlp.c_fc.scales": "model.safetensors", | |
| "model.h.19.mlp.c_fc.weight": "model.safetensors", | |
| "model.h.19.mlp.c_proj.bias": "model.safetensors", | |
| "model.h.19.mlp.c_proj.biases": "model.safetensors", | |
| "model.h.19.mlp.c_proj.scales": "model.safetensors", | |
| "model.h.19.mlp.c_proj.weight": "model.safetensors", | |
| "model.h.2.attn.c_attn.bias": "model.safetensors", | |
| "model.h.2.attn.c_attn.biases": "model.safetensors", | |
| "model.h.2.attn.c_attn.scales": "model.safetensors", | |
| "model.h.2.attn.c_attn.weight": "model.safetensors", | |
| "model.h.2.attn.c_proj.bias": "model.safetensors", | |
| "model.h.2.attn.c_proj.biases": "model.safetensors", | |
| "model.h.2.attn.c_proj.scales": "model.safetensors", | |
| "model.h.2.attn.c_proj.weight": "model.safetensors", | |
| "model.h.2.ln_1.bias": "model.safetensors", | |
| "model.h.2.ln_1.weight": "model.safetensors", | |
| "model.h.2.ln_2.bias": "model.safetensors", | |
| "model.h.2.ln_2.weight": "model.safetensors", | |
| "model.h.2.mlp.c_fc.bias": "model.safetensors", | |
| "model.h.2.mlp.c_fc.biases": "model.safetensors", | |
| "model.h.2.mlp.c_fc.scales": "model.safetensors", | |
| "model.h.2.mlp.c_fc.weight": "model.safetensors", | |
| "model.h.2.mlp.c_proj.bias": "model.safetensors", | |
| "model.h.2.mlp.c_proj.biases": "model.safetensors", | |
| "model.h.2.mlp.c_proj.scales": "model.safetensors", | |
| "model.h.2.mlp.c_proj.weight": "model.safetensors", | |
| "model.h.20.attn.c_attn.bias": "model.safetensors", | |
| "model.h.20.attn.c_attn.biases": "model.safetensors", | |
| "model.h.20.attn.c_attn.scales": "model.safetensors", | |
| "model.h.20.attn.c_attn.weight": "model.safetensors", | |
| "model.h.20.attn.c_proj.bias": "model.safetensors", | |
| "model.h.20.attn.c_proj.biases": "model.safetensors", | |
| "model.h.20.attn.c_proj.scales": "model.safetensors", | |
| "model.h.20.attn.c_proj.weight": "model.safetensors", | |
| "model.h.20.ln_1.bias": "model.safetensors", | |
| "model.h.20.ln_1.weight": "model.safetensors", | |
| "model.h.20.ln_2.bias": "model.safetensors", | |
| "model.h.20.ln_2.weight": "model.safetensors", | |
| "model.h.20.mlp.c_fc.bias": "model.safetensors", | |
| "model.h.20.mlp.c_fc.biases": "model.safetensors", | |
| "model.h.20.mlp.c_fc.scales": "model.safetensors", | |
| "model.h.20.mlp.c_fc.weight": "model.safetensors", | |
| "model.h.20.mlp.c_proj.bias": "model.safetensors", | |
| "model.h.20.mlp.c_proj.biases": "model.safetensors", | |
| "model.h.20.mlp.c_proj.scales": "model.safetensors", | |
| "model.h.20.mlp.c_proj.weight": "model.safetensors", | |
| "model.h.21.attn.c_attn.bias": "model.safetensors", | |
| "model.h.21.attn.c_attn.biases": "model.safetensors", | |
| "model.h.21.attn.c_attn.scales": "model.safetensors", | |
| "model.h.21.attn.c_attn.weight": "model.safetensors", | |
| "model.h.21.attn.c_proj.bias": "model.safetensors", | |
| "model.h.21.attn.c_proj.biases": "model.safetensors", | |
| "model.h.21.attn.c_proj.scales": "model.safetensors", | |
| "model.h.21.attn.c_proj.weight": "model.safetensors", | |
| "model.h.21.ln_1.bias": "model.safetensors", | |
| "model.h.21.ln_1.weight": "model.safetensors", | |
| "model.h.21.ln_2.bias": "model.safetensors", | |
| "model.h.21.ln_2.weight": "model.safetensors", | |
| "model.h.21.mlp.c_fc.bias": "model.safetensors", | |
| "model.h.21.mlp.c_fc.biases": "model.safetensors", | |
| "model.h.21.mlp.c_fc.scales": "model.safetensors", | |
| "model.h.21.mlp.c_fc.weight": "model.safetensors", | |
| "model.h.21.mlp.c_proj.bias": "model.safetensors", | |
| "model.h.21.mlp.c_proj.biases": "model.safetensors", | |
| "model.h.21.mlp.c_proj.scales": "model.safetensors", | |
| "model.h.21.mlp.c_proj.weight": "model.safetensors", | |
| "model.h.22.attn.c_attn.bias": "model.safetensors", | |
| "model.h.22.attn.c_attn.biases": "model.safetensors", | |
| "model.h.22.attn.c_attn.scales": "model.safetensors", | |
| "model.h.22.attn.c_attn.weight": "model.safetensors", | |
| "model.h.22.attn.c_proj.bias": "model.safetensors", | |
| "model.h.22.attn.c_proj.biases": "model.safetensors", | |
| "model.h.22.attn.c_proj.scales": "model.safetensors", | |
| "model.h.22.attn.c_proj.weight": "model.safetensors", | |
| "model.h.22.ln_1.bias": "model.safetensors", | |
| "model.h.22.ln_1.weight": "model.safetensors", | |
| "model.h.22.ln_2.bias": "model.safetensors", | |
| "model.h.22.ln_2.weight": "model.safetensors", | |
| "model.h.22.mlp.c_fc.bias": "model.safetensors", | |
| "model.h.22.mlp.c_fc.biases": "model.safetensors", | |
| "model.h.22.mlp.c_fc.scales": "model.safetensors", | |
| "model.h.22.mlp.c_fc.weight": "model.safetensors", | |
| "model.h.22.mlp.c_proj.bias": "model.safetensors", | |
| "model.h.22.mlp.c_proj.biases": "model.safetensors", | |
| "model.h.22.mlp.c_proj.scales": "model.safetensors", | |
| "model.h.22.mlp.c_proj.weight": "model.safetensors", | |
| "model.h.23.attn.c_attn.bias": "model.safetensors", | |
| "model.h.23.attn.c_attn.biases": "model.safetensors", | |
| "model.h.23.attn.c_attn.scales": "model.safetensors", | |
| "model.h.23.attn.c_attn.weight": "model.safetensors", | |
| "model.h.23.attn.c_proj.bias": "model.safetensors", | |
| "model.h.23.attn.c_proj.biases": "model.safetensors", | |
| "model.h.23.attn.c_proj.scales": "model.safetensors", | |
| "model.h.23.attn.c_proj.weight": "model.safetensors", | |
| "model.h.23.ln_1.bias": "model.safetensors", | |
| "model.h.23.ln_1.weight": "model.safetensors", | |
| "model.h.23.ln_2.bias": "model.safetensors", | |
| "model.h.23.ln_2.weight": "model.safetensors", | |
| "model.h.23.mlp.c_fc.bias": "model.safetensors", | |
| "model.h.23.mlp.c_fc.biases": "model.safetensors", | |
| "model.h.23.mlp.c_fc.scales": "model.safetensors", | |
| "model.h.23.mlp.c_fc.weight": "model.safetensors", | |
| "model.h.23.mlp.c_proj.bias": "model.safetensors", | |
| "model.h.23.mlp.c_proj.biases": "model.safetensors", | |
| "model.h.23.mlp.c_proj.scales": "model.safetensors", | |
| "model.h.23.mlp.c_proj.weight": "model.safetensors", | |
| "model.h.3.attn.c_attn.bias": "model.safetensors", | |
| "model.h.3.attn.c_attn.biases": "model.safetensors", | |
| "model.h.3.attn.c_attn.scales": "model.safetensors", | |
| "model.h.3.attn.c_attn.weight": "model.safetensors", | |
| "model.h.3.attn.c_proj.bias": "model.safetensors", | |
| "model.h.3.attn.c_proj.biases": "model.safetensors", | |
| "model.h.3.attn.c_proj.scales": "model.safetensors", | |
| "model.h.3.attn.c_proj.weight": "model.safetensors", | |
| "model.h.3.ln_1.bias": "model.safetensors", | |
| "model.h.3.ln_1.weight": "model.safetensors", | |
| "model.h.3.ln_2.bias": "model.safetensors", | |
| "model.h.3.ln_2.weight": "model.safetensors", | |
| "model.h.3.mlp.c_fc.bias": "model.safetensors", | |
| "model.h.3.mlp.c_fc.biases": "model.safetensors", | |
| "model.h.3.mlp.c_fc.scales": "model.safetensors", | |
| "model.h.3.mlp.c_fc.weight": "model.safetensors", | |
| "model.h.3.mlp.c_proj.bias": "model.safetensors", | |
| "model.h.3.mlp.c_proj.biases": "model.safetensors", | |
| "model.h.3.mlp.c_proj.scales": "model.safetensors", | |
| "model.h.3.mlp.c_proj.weight": "model.safetensors", | |
| "model.h.4.attn.c_attn.bias": "model.safetensors", | |
| "model.h.4.attn.c_attn.biases": "model.safetensors", | |
| "model.h.4.attn.c_attn.scales": "model.safetensors", | |
| "model.h.4.attn.c_attn.weight": "model.safetensors", | |
| "model.h.4.attn.c_proj.bias": "model.safetensors", | |
| "model.h.4.attn.c_proj.biases": "model.safetensors", | |
| "model.h.4.attn.c_proj.scales": "model.safetensors", | |
| "model.h.4.attn.c_proj.weight": "model.safetensors", | |
| "model.h.4.ln_1.bias": "model.safetensors", | |
| "model.h.4.ln_1.weight": "model.safetensors", | |
| "model.h.4.ln_2.bias": "model.safetensors", | |
| "model.h.4.ln_2.weight": "model.safetensors", | |
| "model.h.4.mlp.c_fc.bias": "model.safetensors", | |
| "model.h.4.mlp.c_fc.biases": "model.safetensors", | |
| "model.h.4.mlp.c_fc.scales": "model.safetensors", | |
| "model.h.4.mlp.c_fc.weight": "model.safetensors", | |
| "model.h.4.mlp.c_proj.bias": "model.safetensors", | |
| "model.h.4.mlp.c_proj.biases": "model.safetensors", | |
| "model.h.4.mlp.c_proj.scales": "model.safetensors", | |
| "model.h.4.mlp.c_proj.weight": "model.safetensors", | |
| "model.h.5.attn.c_attn.bias": "model.safetensors", | |
| "model.h.5.attn.c_attn.biases": "model.safetensors", | |
| "model.h.5.attn.c_attn.scales": "model.safetensors", | |
| "model.h.5.attn.c_attn.weight": "model.safetensors", | |
| "model.h.5.attn.c_proj.bias": "model.safetensors", | |
| "model.h.5.attn.c_proj.biases": "model.safetensors", | |
| "model.h.5.attn.c_proj.scales": "model.safetensors", | |
| "model.h.5.attn.c_proj.weight": "model.safetensors", | |
| "model.h.5.ln_1.bias": "model.safetensors", | |
| "model.h.5.ln_1.weight": "model.safetensors", | |
| "model.h.5.ln_2.bias": "model.safetensors", | |
| "model.h.5.ln_2.weight": "model.safetensors", | |
| "model.h.5.mlp.c_fc.bias": "model.safetensors", | |
| "model.h.5.mlp.c_fc.biases": "model.safetensors", | |
| "model.h.5.mlp.c_fc.scales": "model.safetensors", | |
| "model.h.5.mlp.c_fc.weight": "model.safetensors", | |
| "model.h.5.mlp.c_proj.bias": "model.safetensors", | |
| "model.h.5.mlp.c_proj.biases": "model.safetensors", | |
| "model.h.5.mlp.c_proj.scales": "model.safetensors", | |
| "model.h.5.mlp.c_proj.weight": "model.safetensors", | |
| "model.h.6.attn.c_attn.bias": "model.safetensors", | |
| "model.h.6.attn.c_attn.biases": "model.safetensors", | |
| "model.h.6.attn.c_attn.scales": "model.safetensors", | |
| "model.h.6.attn.c_attn.weight": "model.safetensors", | |
| "model.h.6.attn.c_proj.bias": "model.safetensors", | |
| "model.h.6.attn.c_proj.biases": "model.safetensors", | |
| "model.h.6.attn.c_proj.scales": "model.safetensors", | |
| "model.h.6.attn.c_proj.weight": "model.safetensors", | |
| "model.h.6.ln_1.bias": "model.safetensors", | |
| "model.h.6.ln_1.weight": "model.safetensors", | |
| "model.h.6.ln_2.bias": "model.safetensors", | |
| "model.h.6.ln_2.weight": "model.safetensors", | |
| "model.h.6.mlp.c_fc.bias": "model.safetensors", | |
| "model.h.6.mlp.c_fc.biases": "model.safetensors", | |
| "model.h.6.mlp.c_fc.scales": "model.safetensors", | |
| "model.h.6.mlp.c_fc.weight": "model.safetensors", | |
| "model.h.6.mlp.c_proj.bias": "model.safetensors", | |
| "model.h.6.mlp.c_proj.biases": "model.safetensors", | |
| "model.h.6.mlp.c_proj.scales": "model.safetensors", | |
| "model.h.6.mlp.c_proj.weight": "model.safetensors", | |
| "model.h.7.attn.c_attn.bias": "model.safetensors", | |
| "model.h.7.attn.c_attn.biases": "model.safetensors", | |
| "model.h.7.attn.c_attn.scales": "model.safetensors", | |
| "model.h.7.attn.c_attn.weight": "model.safetensors", | |
| "model.h.7.attn.c_proj.bias": "model.safetensors", | |
| "model.h.7.attn.c_proj.biases": "model.safetensors", | |
| "model.h.7.attn.c_proj.scales": "model.safetensors", | |
| "model.h.7.attn.c_proj.weight": "model.safetensors", | |
| "model.h.7.ln_1.bias": "model.safetensors", | |
| "model.h.7.ln_1.weight": "model.safetensors", | |
| "model.h.7.ln_2.bias": "model.safetensors", | |
| "model.h.7.ln_2.weight": "model.safetensors", | |
| "model.h.7.mlp.c_fc.bias": "model.safetensors", | |
| "model.h.7.mlp.c_fc.biases": "model.safetensors", | |
| "model.h.7.mlp.c_fc.scales": "model.safetensors", | |
| "model.h.7.mlp.c_fc.weight": "model.safetensors", | |
| "model.h.7.mlp.c_proj.bias": "model.safetensors", | |
| "model.h.7.mlp.c_proj.biases": "model.safetensors", | |
| "model.h.7.mlp.c_proj.scales": "model.safetensors", | |
| "model.h.7.mlp.c_proj.weight": "model.safetensors", | |
| "model.h.8.attn.c_attn.bias": "model.safetensors", | |
| "model.h.8.attn.c_attn.biases": "model.safetensors", | |
| "model.h.8.attn.c_attn.scales": "model.safetensors", | |
| "model.h.8.attn.c_attn.weight": "model.safetensors", | |
| "model.h.8.attn.c_proj.bias": "model.safetensors", | |
| "model.h.8.attn.c_proj.biases": "model.safetensors", | |
| "model.h.8.attn.c_proj.scales": "model.safetensors", | |
| "model.h.8.attn.c_proj.weight": "model.safetensors", | |
| "model.h.8.ln_1.bias": "model.safetensors", | |
| "model.h.8.ln_1.weight": "model.safetensors", | |
| "model.h.8.ln_2.bias": "model.safetensors", | |
| "model.h.8.ln_2.weight": "model.safetensors", | |
| "model.h.8.mlp.c_fc.bias": "model.safetensors", | |
| "model.h.8.mlp.c_fc.biases": "model.safetensors", | |
| "model.h.8.mlp.c_fc.scales": "model.safetensors", | |
| "model.h.8.mlp.c_fc.weight": "model.safetensors", | |
| "model.h.8.mlp.c_proj.bias": "model.safetensors", | |
| "model.h.8.mlp.c_proj.biases": "model.safetensors", | |
| "model.h.8.mlp.c_proj.scales": "model.safetensors", | |
| "model.h.8.mlp.c_proj.weight": "model.safetensors", | |
| "model.h.9.attn.c_attn.bias": "model.safetensors", | |
| "model.h.9.attn.c_attn.biases": "model.safetensors", | |
| "model.h.9.attn.c_attn.scales": "model.safetensors", | |
| "model.h.9.attn.c_attn.weight": "model.safetensors", | |
| "model.h.9.attn.c_proj.bias": "model.safetensors", | |
| "model.h.9.attn.c_proj.biases": "model.safetensors", | |
| "model.h.9.attn.c_proj.scales": "model.safetensors", | |
| "model.h.9.attn.c_proj.weight": "model.safetensors", | |
| "model.h.9.ln_1.bias": "model.safetensors", | |
| "model.h.9.ln_1.weight": "model.safetensors", | |
| "model.h.9.ln_2.bias": "model.safetensors", | |
| "model.h.9.ln_2.weight": "model.safetensors", | |
| "model.h.9.mlp.c_fc.bias": "model.safetensors", | |
| "model.h.9.mlp.c_fc.biases": "model.safetensors", | |
| "model.h.9.mlp.c_fc.scales": "model.safetensors", | |
| "model.h.9.mlp.c_fc.weight": "model.safetensors", | |
| "model.h.9.mlp.c_proj.bias": "model.safetensors", | |
| "model.h.9.mlp.c_proj.biases": "model.safetensors", | |
| "model.h.9.mlp.c_proj.scales": "model.safetensors", | |
| "model.h.9.mlp.c_proj.weight": "model.safetensors", | |
| "model.ln_f.bias": "model.safetensors", | |
| "model.ln_f.weight": "model.safetensors", | |
| "model.wpe.biases": "model.safetensors", | |
| "model.wpe.scales": "model.safetensors", | |
| "model.wpe.weight": "model.safetensors", | |
| "model.wte.biases": "model.safetensors", | |
| "model.wte.scales": "model.safetensors", | |
| "model.wte.weight": "model.safetensors" | |
| } | |
| } |