{"metadata": {"mergekit_version": "0.0.3.2"}, "weight_map": {"transformer.embd.wte.weight": "model-00001-of-00002.safetensors", "transformer.h.0.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.32.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.0.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.32.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.0.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.32.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.0.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.32.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.0.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.32.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.0.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.32.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.0.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.32.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.0.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.32.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.0.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.32.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.0.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.32.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.1.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.33.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.1.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.33.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.1.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.33.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.1.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.33.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.1.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.33.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.1.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.33.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.1.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.33.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.1.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.33.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.1.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.33.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.1.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.33.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.10.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.42.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.10.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.42.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.10.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.42.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.10.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.42.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.10.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.42.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.10.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.42.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.10.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.42.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.10.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.42.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.10.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.42.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.10.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.42.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.11.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.43.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.11.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.43.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.11.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.43.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.11.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.43.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.11.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.43.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.11.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.43.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.11.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.43.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.11.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.43.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.11.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.43.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.11.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.43.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.12.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.44.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.12.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.44.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.12.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.44.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.12.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.44.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.12.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.44.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.12.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.44.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.12.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.44.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.12.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.44.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.12.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.44.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.12.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.44.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.13.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.45.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.13.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.45.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.13.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.45.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.13.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.45.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.13.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.45.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.13.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.45.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.13.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.45.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.13.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.45.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.13.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.45.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.13.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.45.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.14.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.46.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.14.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.46.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.14.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.46.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.14.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.46.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.14.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.46.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.14.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.46.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.14.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.46.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.14.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.46.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.14.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.46.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.14.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.46.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.15.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.47.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.15.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.47.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.15.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.47.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.15.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.47.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.15.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.47.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.15.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.47.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.15.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.47.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.15.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.47.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.15.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.47.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.15.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.47.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.16.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.48.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.16.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.48.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.16.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.48.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.16.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.48.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.16.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.48.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.16.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.48.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.16.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.48.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.16.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.48.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.16.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.48.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.16.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.48.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.17.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.49.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.17.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.49.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.17.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.49.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.17.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.49.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.17.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.49.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.17.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.49.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.17.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.49.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.17.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.49.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.17.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.49.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.17.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.49.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.18.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.50.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.18.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.50.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.18.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.50.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.18.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.50.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.18.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.50.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.18.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.50.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.18.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.50.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.18.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.50.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.18.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.50.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.18.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.50.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.19.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.51.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.19.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.51.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.19.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.51.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.19.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.51.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.19.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.51.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.19.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.51.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.19.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.51.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.19.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.51.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.19.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.51.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.19.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.51.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.2.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.34.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.2.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.34.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.2.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.34.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.2.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.34.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.2.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.34.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.2.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.34.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.2.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.34.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.2.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.34.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.2.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.34.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.2.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.34.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.20.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.52.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.20.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.52.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.20.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.52.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.20.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.52.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.20.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.52.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.20.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.52.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.20.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.52.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.20.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.52.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.20.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.52.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.20.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.52.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.21.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.53.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.21.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.53.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.21.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.53.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.21.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.53.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.21.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.53.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.21.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.53.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.21.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.53.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.21.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.53.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.21.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.53.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.21.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.53.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.22.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.54.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.22.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.54.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.22.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.54.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.22.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.54.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.22.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.54.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.22.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.54.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.22.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.54.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.22.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.54.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.22.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.54.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.22.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.54.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.23.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.55.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.23.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.55.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.23.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.55.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.23.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.55.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.23.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.55.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.23.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.55.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.23.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.55.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.23.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.55.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.23.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.55.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.23.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.55.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.24.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.56.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.24.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.56.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.24.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.56.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.24.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.56.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.24.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.56.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.24.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.56.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.24.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.56.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.24.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.56.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.24.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.56.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.24.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.56.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.25.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.57.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.25.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.57.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.25.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.57.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.25.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.57.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.25.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.57.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.25.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.57.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.25.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.57.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.25.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.57.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.25.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.57.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.25.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.57.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.26.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.58.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.26.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.58.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.26.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.58.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.26.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.58.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.26.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.58.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.26.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.58.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.26.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.58.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.26.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.58.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.26.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.58.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.26.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.58.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.27.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.59.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.27.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.59.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.27.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.59.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.27.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.59.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.27.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.59.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.27.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.59.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.27.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.59.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.27.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.59.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.27.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.59.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.27.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.59.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.28.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.60.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.28.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.60.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.28.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.60.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.28.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.60.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.28.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.60.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.28.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.60.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.28.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.60.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.28.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.60.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.28.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.60.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.28.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.60.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.29.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.61.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.29.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.61.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.29.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.61.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.29.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.61.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.29.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.61.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.29.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.61.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.29.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.61.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.29.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.61.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.29.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.61.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.29.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.61.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.3.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.35.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.3.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.35.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.3.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.35.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.3.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.35.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.3.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.35.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.3.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.35.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.3.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.35.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.3.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.35.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.3.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.35.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.3.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.35.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.30.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.62.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.30.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.62.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.4.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.36.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.4.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.36.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.4.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.36.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.4.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.36.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.4.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.36.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.4.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.36.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.4.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.36.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.4.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.36.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.4.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.36.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.4.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.36.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.5.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.37.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.5.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.37.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.5.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.37.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.5.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.37.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.5.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.37.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.5.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.37.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.5.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.37.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.5.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.37.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.5.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.37.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.5.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.37.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.6.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.38.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.6.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.38.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.6.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.38.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.6.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.38.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.6.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.38.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.6.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.38.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.6.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.38.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.6.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.38.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.6.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.38.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.6.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.38.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.7.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.39.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.7.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.39.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.7.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.39.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.7.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.39.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.7.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.39.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.7.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.39.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.7.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.39.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.7.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.39.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.7.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.39.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.7.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.39.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.8.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.40.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.8.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.40.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.8.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.40.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.8.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.40.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.8.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.40.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.8.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.40.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.8.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.40.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.8.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.40.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.8.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.40.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.8.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.40.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.9.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.41.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.9.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.41.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.9.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.41.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.9.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.41.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.9.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.41.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.9.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.41.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.9.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.41.mlp.fc1.bias": "model-00001-of-00002.safetensors", "transformer.h.9.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.41.mlp.fc1.weight": "model-00001-of-00002.safetensors", "transformer.h.9.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.41.mlp.fc2.bias": "model-00001-of-00002.safetensors", "transformer.h.9.mlp.fc2.weight": "model-00001-of-00002.safetensors", "transformer.h.41.mlp.fc2.weight": "model-00001-of-00002.safetensors", "lm_head.linear.bias": "model-00001-of-00002.safetensors", "lm_head.linear.weight": "model-00001-of-00002.safetensors", "lm_head.ln.bias": "model-00001-of-00002.safetensors", "lm_head.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.30.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.62.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.30.mixer.Wqkv.weight": "model-00002-of-00002.safetensors", "transformer.h.62.mixer.Wqkv.weight": "model-00002-of-00002.safetensors", "transformer.h.30.mixer.out_proj.bias": "model-00002-of-00002.safetensors", "transformer.h.62.mixer.out_proj.bias": "model-00002-of-00002.safetensors", "transformer.h.30.mixer.out_proj.weight": "model-00002-of-00002.safetensors", "transformer.h.62.mixer.out_proj.weight": "model-00002-of-00002.safetensors", "transformer.h.30.mlp.fc1.bias": "model-00002-of-00002.safetensors", "transformer.h.62.mlp.fc1.bias": "model-00002-of-00002.safetensors", "transformer.h.30.mlp.fc1.weight": "model-00002-of-00002.safetensors", "transformer.h.62.mlp.fc1.weight": "model-00002-of-00002.safetensors", "transformer.h.30.mlp.fc2.bias": "model-00002-of-00002.safetensors", "transformer.h.62.mlp.fc2.bias": "model-00002-of-00002.safetensors", "transformer.h.30.mlp.fc2.weight": "model-00002-of-00002.safetensors", "transformer.h.62.mlp.fc2.weight": "model-00002-of-00002.safetensors", "transformer.h.31.ln.bias": "model-00002-of-00002.safetensors", "transformer.h.63.ln.bias": "model-00002-of-00002.safetensors", "transformer.h.31.ln.weight": "model-00002-of-00002.safetensors", "transformer.h.63.ln.weight": "model-00002-of-00002.safetensors", "transformer.h.31.mixer.Wqkv.bias": "model-00002-of-00002.safetensors", "transformer.h.63.mixer.Wqkv.bias": "model-00002-of-00002.safetensors", "transformer.h.31.mixer.Wqkv.weight": "model-00002-of-00002.safetensors", "transformer.h.63.mixer.Wqkv.weight": "model-00002-of-00002.safetensors", "transformer.h.31.mixer.out_proj.bias": "model-00002-of-00002.safetensors", "transformer.h.63.mixer.out_proj.bias": "model-00002-of-00002.safetensors", "transformer.h.31.mixer.out_proj.weight": "model-00002-of-00002.safetensors", "transformer.h.63.mixer.out_proj.weight": "model-00002-of-00002.safetensors", "transformer.h.31.mlp.fc1.bias": "model-00002-of-00002.safetensors", "transformer.h.63.mlp.fc1.bias": "model-00002-of-00002.safetensors", "transformer.h.31.mlp.fc1.weight": "model-00002-of-00002.safetensors", "transformer.h.63.mlp.fc1.weight": "model-00002-of-00002.safetensors", "transformer.h.31.mlp.fc2.bias": "model-00002-of-00002.safetensors", "transformer.h.63.mlp.fc2.bias": "model-00002-of-00002.safetensors", "transformer.h.31.mlp.fc2.weight": "model-00002-of-00002.safetensors", "transformer.h.63.mlp.fc2.weight": "model-00002-of-00002.safetensors"}}