QuadPhi / model.safetensors.index.json
mattshumer's picture
Upload folder using huggingface_hub
b46654a verified
{"metadata": {"mergekit_version": "0.0.3.2"}, "weight_map": {"lm_head.linear.bias": "model-00001-of-00003.safetensors", "lm_head.linear.weight": "model-00001-of-00003.safetensors", "lm_head.ln.bias": "model-00001-of-00003.safetensors", "lm_head.ln.weight": "model-00001-of-00003.safetensors", "transformer.embd.wte.weight": "model-00001-of-00003.safetensors", "transformer.h.0.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.64.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.0.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.64.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.0.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.64.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.0.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.64.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.0.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.64.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.0.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.64.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.0.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.64.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.0.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.64.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.0.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.64.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.0.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.64.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.1.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.65.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.1.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.65.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.1.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.65.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.1.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.65.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.1.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.65.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.1.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.65.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.1.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.65.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.1.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.65.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.1.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.65.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.1.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.65.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.10.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.74.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.10.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.74.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.10.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.74.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.10.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.74.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.10.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.74.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.10.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.74.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.10.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.74.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.10.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.74.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.10.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.74.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.10.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.74.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.11.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.75.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.11.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.75.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.11.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.75.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.11.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.75.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.11.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.75.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.11.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.75.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.11.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.75.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.11.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.75.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.11.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.75.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.11.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.75.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.12.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.76.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.12.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.76.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.12.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.76.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.12.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.76.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.12.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.76.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.12.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.76.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.12.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.76.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.12.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.76.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.12.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.76.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.12.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.76.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.13.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.77.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.13.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.77.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.13.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.77.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.13.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.77.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.13.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.77.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.13.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.77.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.13.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.77.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.13.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.77.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.13.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.77.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.13.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.77.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.14.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.78.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.14.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.78.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.14.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.78.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.14.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.78.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.14.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.78.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.14.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.78.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.14.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.78.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.14.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.78.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.14.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.78.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.14.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.78.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.15.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.79.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.15.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.79.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.15.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.79.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.15.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.79.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.15.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.79.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.15.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.79.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.15.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.79.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.15.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.79.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.15.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.79.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.15.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.79.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.16.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.80.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.16.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.80.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.16.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.80.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.16.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.80.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.16.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.80.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.16.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.80.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.16.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.80.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.16.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.80.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.16.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.80.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.16.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.80.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.17.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.81.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.17.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.81.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.17.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.81.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.17.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.81.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.17.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.81.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.17.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.81.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.17.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.81.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.17.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.81.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.17.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.81.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.17.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.81.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.18.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.82.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.18.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.82.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.18.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.82.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.18.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.82.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.18.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.82.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.18.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.82.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.18.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.82.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.18.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.82.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.18.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.82.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.18.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.82.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.19.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.83.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.19.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.83.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.19.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.83.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.19.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.83.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.19.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.83.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.19.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.83.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.19.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.83.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.19.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.83.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.19.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.83.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.19.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.83.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.2.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.66.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.2.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.66.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.2.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.66.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.2.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.66.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.2.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.66.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.2.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.66.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.2.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.66.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.2.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.66.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.2.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.66.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.2.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.66.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.20.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.84.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.20.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.84.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.20.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.84.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.20.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.84.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.20.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.84.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.20.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.84.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.20.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.84.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.20.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.84.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.20.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.84.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.20.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.84.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.21.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.85.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.21.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.85.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.21.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.85.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.21.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.85.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.21.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.85.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.21.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.85.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.21.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.85.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.21.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.85.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.21.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.85.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.21.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.85.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.22.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.86.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.22.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.86.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.22.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.86.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.22.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.86.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.22.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.86.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.22.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.86.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.22.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.86.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.22.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.86.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.22.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.86.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.22.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.86.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.23.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.87.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.23.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.87.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.23.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.87.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.23.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.87.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.23.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.87.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.23.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.87.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.23.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.87.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.23.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.87.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.23.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.87.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.23.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.87.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.24.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.88.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.24.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.88.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.24.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.88.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.24.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.88.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.24.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.88.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.24.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.88.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.24.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.88.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.24.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.88.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.24.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.88.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.24.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.88.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.25.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.89.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.25.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.89.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.25.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.89.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.25.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.89.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.25.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.89.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.25.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.89.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.25.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.89.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.25.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.89.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.25.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.89.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.25.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.89.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.26.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.90.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.26.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.90.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.26.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.90.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.26.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.90.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.26.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.90.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.26.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.90.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.26.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.90.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.26.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.90.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.26.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.90.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.26.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.90.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.27.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.91.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.27.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.91.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.27.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.91.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.27.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.91.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.27.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.91.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.27.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.91.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.27.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.91.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.27.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.91.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.27.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.91.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.27.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.91.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.28.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.92.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.28.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.92.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.28.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.92.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.28.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.92.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.28.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.92.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.28.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.92.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.28.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.92.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.28.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.92.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.28.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.92.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.28.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.92.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.29.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.93.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.29.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.93.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.29.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.93.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.29.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.93.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.29.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.93.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.29.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.93.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.29.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.93.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.29.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.93.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.29.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.93.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.29.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.93.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.3.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.67.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.3.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.67.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.3.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.67.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.3.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.67.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.3.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.67.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.3.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.67.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.3.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.67.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.3.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.67.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.3.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.67.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.3.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.67.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.30.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.94.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.30.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.94.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.30.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.94.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.32.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.96.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.32.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.96.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.32.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.96.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.32.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.96.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.32.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.96.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.32.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.96.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.32.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.96.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.32.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.96.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.32.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.96.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.32.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.96.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.33.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.97.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.33.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.97.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.33.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.97.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.33.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.97.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.33.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.97.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.33.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.97.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.33.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.97.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.33.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.97.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.33.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.97.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.33.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.97.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.34.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.98.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.34.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.98.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.34.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.98.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.34.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.98.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.34.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.98.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.34.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.98.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.34.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.98.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.34.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.98.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.34.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.98.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.34.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.98.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.35.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.99.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.35.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.99.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.35.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.99.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.35.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.99.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.35.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.99.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.35.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.99.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.35.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.99.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.35.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.99.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.35.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.99.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.35.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.99.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.36.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.100.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.36.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.100.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.36.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.100.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.36.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.100.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.36.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.100.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.36.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.100.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.36.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.100.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.36.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.100.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.36.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.100.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.36.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.100.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.37.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.101.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.37.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.101.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.37.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.101.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.37.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.101.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.37.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.101.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.37.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.101.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.37.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.101.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.37.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.101.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.37.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.101.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.37.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.101.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.38.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.102.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.38.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.102.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.38.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.102.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.38.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.102.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.38.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.102.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.38.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.102.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.38.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.102.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.38.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.102.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.38.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.102.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.38.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.102.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.39.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.103.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.39.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.103.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.39.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.103.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.39.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.103.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.39.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.103.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.39.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.103.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.39.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.103.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.39.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.103.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.39.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.103.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.39.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.103.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.4.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.68.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.4.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.68.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.4.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.68.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.4.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.68.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.4.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.68.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.4.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.68.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.4.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.68.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.4.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.68.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.4.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.68.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.4.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.68.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.40.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.104.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.40.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.104.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.40.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.104.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.40.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.104.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.40.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.104.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.40.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.104.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.40.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.104.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.40.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.104.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.40.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.104.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.40.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.104.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.41.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.105.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.41.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.105.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.41.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.105.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.41.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.105.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.41.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.105.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.41.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.105.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.41.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.105.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.41.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.105.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.41.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.105.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.41.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.105.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.42.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.106.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.42.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.106.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.42.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.106.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.42.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.106.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.42.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.106.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.42.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.106.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.42.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.106.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.42.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.106.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.42.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.106.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.42.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.106.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.43.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.107.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.43.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.107.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.43.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.107.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.43.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.107.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.43.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.107.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.43.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.107.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.43.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.107.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.43.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.107.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.43.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.107.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.43.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.107.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.44.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.108.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.44.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.108.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.44.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.108.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.44.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.108.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.44.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.108.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.44.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.108.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.44.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.108.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.44.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.108.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.44.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.108.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.44.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.108.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.45.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.109.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.45.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.109.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.45.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.109.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.45.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.109.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.45.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.109.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.45.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.109.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.45.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.109.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.45.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.109.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.45.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.109.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.45.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.109.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.46.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.110.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.46.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.110.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.46.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.110.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.46.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.110.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.46.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.110.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.46.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.110.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.46.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.110.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.46.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.110.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.46.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.110.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.46.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.110.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.47.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.111.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.47.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.111.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.47.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.111.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.47.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.111.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.47.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.111.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.47.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.111.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.47.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.111.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.47.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.111.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.47.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.111.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.47.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.111.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.48.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.112.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.48.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.112.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.48.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.112.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.48.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.112.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.48.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.112.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.48.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.112.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.48.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.112.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.48.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.112.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.48.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.112.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.48.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.112.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.49.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.113.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.49.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.113.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.49.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.113.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.49.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.113.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.49.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.113.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.49.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.113.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.49.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.113.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.49.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.113.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.49.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.113.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.49.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.113.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.5.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.69.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.5.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.69.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.5.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.69.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.5.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.69.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.5.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.69.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.5.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.69.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.5.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.69.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.5.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.69.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.5.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.69.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.5.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.69.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.50.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.114.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.50.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.114.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.50.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.114.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.50.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.114.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.50.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.114.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.50.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.114.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.50.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.114.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.50.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.114.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.50.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.114.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.50.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.114.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.51.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.115.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.51.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.115.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.51.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.115.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.51.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.115.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.51.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.115.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.51.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.115.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.51.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.115.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.51.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.115.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.51.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.115.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.51.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.115.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.52.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.116.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.52.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.116.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.52.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.116.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.52.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.116.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.52.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.116.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.52.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.116.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.52.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.116.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.52.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.116.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.52.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.116.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.52.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.116.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.53.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.117.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.53.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.117.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.53.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.117.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.53.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.117.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.53.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.117.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.53.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.117.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.53.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.117.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.53.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.117.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.53.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.117.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.53.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.117.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.54.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.118.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.54.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.118.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.54.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.118.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.54.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.118.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.54.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.118.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.54.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.118.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.54.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.118.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.54.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.118.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.54.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.118.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.54.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.118.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.55.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.119.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.55.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.119.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.55.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.119.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.55.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.119.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.55.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.119.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.55.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.119.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.55.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.119.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.55.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.119.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.55.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.119.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.55.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.119.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.56.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.120.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.56.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.120.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.56.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.120.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.56.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.120.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.56.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.120.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.56.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.120.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.56.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.120.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.56.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.120.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.56.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.120.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.56.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.120.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.57.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.121.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.57.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.121.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.57.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.121.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.57.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.121.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.57.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.121.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.57.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.121.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.57.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.121.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.57.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.121.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.57.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.121.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.57.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.121.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.58.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.122.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.58.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.122.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.58.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.122.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.58.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.122.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.58.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.122.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.58.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.122.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.58.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.122.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.58.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.122.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.58.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.122.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.58.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.122.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.59.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.123.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.59.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.123.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.59.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.123.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.59.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.123.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.59.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.123.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.59.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.123.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.59.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.123.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.59.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.123.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.59.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.123.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.59.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.123.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.6.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.70.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.6.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.70.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.6.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.70.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.6.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.70.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.6.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.70.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.6.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.70.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.6.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.70.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.6.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.70.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.6.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.70.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.6.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.70.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.60.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.124.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.60.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.124.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.60.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.124.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.60.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.124.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.60.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.124.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.60.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.124.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.60.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.124.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.60.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.124.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.60.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.124.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.60.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.124.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.61.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.125.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.61.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.125.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.61.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.125.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.61.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.125.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.61.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.125.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.61.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.125.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.61.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.125.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.61.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.125.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.61.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.125.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.61.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.125.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.62.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.126.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.62.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.126.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.62.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.126.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.7.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.71.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.7.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.71.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.7.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.71.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.7.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.71.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.7.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.71.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.7.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.71.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.7.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.71.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.7.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.71.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.7.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.71.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.7.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.71.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.8.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.72.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.8.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.72.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.8.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.72.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.8.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.72.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.8.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.72.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.8.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.72.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.8.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.72.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.8.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.72.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.8.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.72.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.8.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.72.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.9.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.73.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.9.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.73.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.9.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.73.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.9.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.73.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.9.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.73.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.9.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.73.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.9.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.73.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.9.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.73.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.9.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.73.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.9.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.73.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.30.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.94.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.30.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.94.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.30.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.94.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.30.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.94.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.30.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.94.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.30.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.94.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.30.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.94.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.31.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.95.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.31.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.95.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.31.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.95.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.31.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.95.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.31.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.95.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.31.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.95.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.31.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.95.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.31.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.95.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.31.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.95.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.31.mlp.fc2.weight": "model-00003-of-00003.safetensors", "transformer.h.95.mlp.fc2.weight": "model-00003-of-00003.safetensors", "transformer.h.62.mixer.Wqkv.weight": "model-00003-of-00003.safetensors", "transformer.h.126.mixer.Wqkv.weight": "model-00003-of-00003.safetensors", "transformer.h.62.mixer.out_proj.bias": "model-00003-of-00003.safetensors", "transformer.h.126.mixer.out_proj.bias": "model-00003-of-00003.safetensors", "transformer.h.62.mixer.out_proj.weight": "model-00003-of-00003.safetensors", "transformer.h.126.mixer.out_proj.weight": "model-00003-of-00003.safetensors", "transformer.h.62.mlp.fc1.bias": "model-00003-of-00003.safetensors", "transformer.h.126.mlp.fc1.bias": "model-00003-of-00003.safetensors", "transformer.h.62.mlp.fc1.weight": "model-00003-of-00003.safetensors", "transformer.h.126.mlp.fc1.weight": "model-00003-of-00003.safetensors", "transformer.h.62.mlp.fc2.bias": "model-00003-of-00003.safetensors", "transformer.h.126.mlp.fc2.bias": "model-00003-of-00003.safetensors", "transformer.h.62.mlp.fc2.weight": "model-00003-of-00003.safetensors", "transformer.h.126.mlp.fc2.weight": "model-00003-of-00003.safetensors", "transformer.h.63.ln.bias": "model-00003-of-00003.safetensors", "transformer.h.127.ln.bias": "model-00003-of-00003.safetensors", "transformer.h.63.ln.weight": "model-00003-of-00003.safetensors", "transformer.h.127.ln.weight": "model-00003-of-00003.safetensors", "transformer.h.63.mixer.Wqkv.bias": "model-00003-of-00003.safetensors", "transformer.h.127.mixer.Wqkv.bias": "model-00003-of-00003.safetensors", "transformer.h.63.mixer.Wqkv.weight": "model-00003-of-00003.safetensors", "transformer.h.127.mixer.Wqkv.weight": "model-00003-of-00003.safetensors", "transformer.h.63.mixer.out_proj.bias": "model-00003-of-00003.safetensors", "transformer.h.127.mixer.out_proj.bias": "model-00003-of-00003.safetensors", "transformer.h.63.mixer.out_proj.weight": "model-00003-of-00003.safetensors", "transformer.h.127.mixer.out_proj.weight": "model-00003-of-00003.safetensors", "transformer.h.63.mlp.fc1.bias": "model-00003-of-00003.safetensors", "transformer.h.127.mlp.fc1.bias": "model-00003-of-00003.safetensors", "transformer.h.63.mlp.fc1.weight": "model-00003-of-00003.safetensors", "transformer.h.127.mlp.fc1.weight": "model-00003-of-00003.safetensors", "transformer.h.63.mlp.fc2.bias": "model-00003-of-00003.safetensors", "transformer.h.127.mlp.fc2.bias": "model-00003-of-00003.safetensors", "transformer.h.63.mlp.fc2.weight": "model-00003-of-00003.safetensors", "transformer.h.127.mlp.fc2.weight": "model-00003-of-00003.safetensors"}}