{ "metadata": { "total_size": 5673084416 }, "weight_map": { "layers.0.wte.weight": "model-00001-of-00003.safetensors", "layers.1.ln.bias": "model-00001-of-00003.safetensors", "layers.1.ln.weight": "model-00001-of-00003.safetensors", "layers.1.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "layers.1.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "layers.1.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "layers.1.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "layers.1.mixer.rotary_emb.inv_freq": "model-00001-of-00003.safetensors", "layers.1.mlp.fc1.bias": "model-00001-of-00003.safetensors", "layers.1.mlp.fc1.weight": "model-00001-of-00003.safetensors", "layers.1.mlp.fc2.bias": "model-00001-of-00003.safetensors", "layers.1.mlp.fc2.weight": "model-00001-of-00003.safetensors", "layers.10.ln.bias": "model-00002-of-00003.safetensors", "layers.10.ln.weight": "model-00002-of-00003.safetensors", "layers.10.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "layers.10.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "layers.10.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "layers.10.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "layers.10.mixer.rotary_emb.inv_freq": "model-00002-of-00003.safetensors", "layers.10.mlp.fc1.bias": "model-00002-of-00003.safetensors", "layers.10.mlp.fc1.weight": "model-00002-of-00003.safetensors", "layers.10.mlp.fc2.bias": "model-00002-of-00003.safetensors", "layers.10.mlp.fc2.weight": "model-00002-of-00003.safetensors", "layers.11.ln.bias": "model-00002-of-00003.safetensors", "layers.11.ln.weight": "model-00002-of-00003.safetensors", "layers.11.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "layers.11.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "layers.11.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "layers.11.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "layers.11.mixer.rotary_emb.inv_freq": "model-00002-of-00003.safetensors", "layers.11.mlp.fc1.bias": "model-00002-of-00003.safetensors", "layers.11.mlp.fc1.weight": "model-00002-of-00003.safetensors", "layers.11.mlp.fc2.bias": "model-00002-of-00003.safetensors", "layers.11.mlp.fc2.weight": "model-00002-of-00003.safetensors", "layers.12.ln.bias": "model-00002-of-00003.safetensors", "layers.12.ln.weight": "model-00002-of-00003.safetensors", "layers.12.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "layers.12.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "layers.12.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "layers.12.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "layers.12.mixer.rotary_emb.inv_freq": "model-00002-of-00003.safetensors", "layers.12.mlp.fc1.bias": "model-00002-of-00003.safetensors", "layers.12.mlp.fc1.weight": "model-00002-of-00003.safetensors", "layers.12.mlp.fc2.bias": "model-00002-of-00003.safetensors", "layers.12.mlp.fc2.weight": "model-00002-of-00003.safetensors", "layers.13.ln.bias": "model-00002-of-00003.safetensors", "layers.13.ln.weight": "model-00002-of-00003.safetensors", "layers.13.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "layers.13.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "layers.13.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "layers.13.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "layers.13.mixer.rotary_emb.inv_freq": "model-00002-of-00003.safetensors", "layers.13.mlp.fc1.bias": "model-00002-of-00003.safetensors", "layers.13.mlp.fc1.weight": "model-00002-of-00003.safetensors", "layers.13.mlp.fc2.bias": "model-00002-of-00003.safetensors", "layers.13.mlp.fc2.weight": "model-00002-of-00003.safetensors", "layers.14.ln.bias": "model-00002-of-00003.safetensors", "layers.14.ln.weight": "model-00002-of-00003.safetensors", "layers.14.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "layers.14.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "layers.14.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "layers.14.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "layers.14.mixer.rotary_emb.inv_freq": "model-00002-of-00003.safetensors", "layers.14.mlp.fc1.bias": "model-00002-of-00003.safetensors", "layers.14.mlp.fc1.weight": "model-00002-of-00003.safetensors", "layers.14.mlp.fc2.bias": "model-00002-of-00003.safetensors", "layers.14.mlp.fc2.weight": "model-00002-of-00003.safetensors", "layers.15.ln.bias": "model-00002-of-00003.safetensors", "layers.15.ln.weight": "model-00002-of-00003.safetensors", "layers.15.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "layers.15.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "layers.15.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "layers.15.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "layers.15.mixer.rotary_emb.inv_freq": "model-00002-of-00003.safetensors", "layers.15.mlp.fc1.bias": "model-00002-of-00003.safetensors", "layers.15.mlp.fc1.weight": "model-00002-of-00003.safetensors", "layers.15.mlp.fc2.bias": "model-00002-of-00003.safetensors", "layers.15.mlp.fc2.weight": "model-00002-of-00003.safetensors", "layers.16.ln.bias": "model-00002-of-00003.safetensors", "layers.16.ln.weight": "model-00002-of-00003.safetensors", "layers.16.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "layers.16.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "layers.16.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "layers.16.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "layers.16.mixer.rotary_emb.inv_freq": "model-00002-of-00003.safetensors", "layers.16.mlp.fc1.bias": "model-00002-of-00003.safetensors", "layers.16.mlp.fc1.weight": "model-00002-of-00003.safetensors", "layers.16.mlp.fc2.bias": "model-00002-of-00003.safetensors", "layers.16.mlp.fc2.weight": "model-00002-of-00003.safetensors", "layers.17.ln.bias": "model-00002-of-00003.safetensors", "layers.17.ln.weight": "model-00002-of-00003.safetensors", "layers.17.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "layers.17.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "layers.17.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "layers.17.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "layers.17.mixer.rotary_emb.inv_freq": "model-00002-of-00003.safetensors", "layers.17.mlp.fc1.bias": "model-00002-of-00003.safetensors", "layers.17.mlp.fc1.weight": "model-00002-of-00003.safetensors", "layers.17.mlp.fc2.bias": "model-00002-of-00003.safetensors", "layers.17.mlp.fc2.weight": "model-00002-of-00003.safetensors", "layers.18.ln.bias": "model-00002-of-00003.safetensors", "layers.18.ln.weight": "model-00002-of-00003.safetensors", "layers.18.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "layers.18.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "layers.18.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "layers.18.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "layers.18.mixer.rotary_emb.inv_freq": "model-00002-of-00003.safetensors", "layers.18.mlp.fc1.bias": "model-00003-of-00003.safetensors", "layers.18.mlp.fc1.weight": "model-00003-of-00003.safetensors", "layers.18.mlp.fc2.bias": "model-00003-of-00003.safetensors", "layers.18.mlp.fc2.weight": "model-00003-of-00003.safetensors", "layers.19.ln.bias": "model-00003-of-00003.safetensors", "layers.19.ln.weight": "model-00003-of-00003.safetensors", "layers.19.mixer.Wqkv.bias": "model-00003-of-00003.safetensors", "layers.19.mixer.Wqkv.weight": "model-00003-of-00003.safetensors", "layers.19.mixer.out_proj.bias": "model-00003-of-00003.safetensors", "layers.19.mixer.out_proj.weight": "model-00003-of-00003.safetensors", "layers.19.mixer.rotary_emb.inv_freq": "model-00003-of-00003.safetensors", "layers.19.mlp.fc1.bias": "model-00003-of-00003.safetensors", "layers.19.mlp.fc1.weight": "model-00003-of-00003.safetensors", "layers.19.mlp.fc2.bias": "model-00003-of-00003.safetensors", "layers.19.mlp.fc2.weight": "model-00003-of-00003.safetensors", "layers.2.ln.bias": "model-00001-of-00003.safetensors", "layers.2.ln.weight": "model-00001-of-00003.safetensors", "layers.2.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "layers.2.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "layers.2.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "layers.2.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "layers.2.mixer.rotary_emb.inv_freq": "model-00001-of-00003.safetensors", "layers.2.mlp.fc1.bias": "model-00001-of-00003.safetensors", "layers.2.mlp.fc1.weight": "model-00001-of-00003.safetensors", "layers.2.mlp.fc2.bias": "model-00001-of-00003.safetensors", "layers.2.mlp.fc2.weight": "model-00001-of-00003.safetensors", "layers.20.ln.bias": "model-00003-of-00003.safetensors", "layers.20.ln.weight": "model-00003-of-00003.safetensors", "layers.20.mixer.Wqkv.bias": "model-00003-of-00003.safetensors", "layers.20.mixer.Wqkv.weight": "model-00003-of-00003.safetensors", "layers.20.mixer.out_proj.bias": "model-00003-of-00003.safetensors", "layers.20.mixer.out_proj.weight": "model-00003-of-00003.safetensors", "layers.20.mixer.rotary_emb.inv_freq": "model-00003-of-00003.safetensors", "layers.20.mlp.fc1.bias": "model-00003-of-00003.safetensors", "layers.20.mlp.fc1.weight": "model-00003-of-00003.safetensors", "layers.20.mlp.fc2.bias": "model-00003-of-00003.safetensors", "layers.20.mlp.fc2.weight": "model-00003-of-00003.safetensors", "layers.21.ln.bias": "model-00003-of-00003.safetensors", "layers.21.ln.weight": "model-00003-of-00003.safetensors", "layers.21.mixer.Wqkv.bias": "model-00003-of-00003.safetensors", "layers.21.mixer.Wqkv.weight": "model-00003-of-00003.safetensors", "layers.21.mixer.out_proj.bias": "model-00003-of-00003.safetensors", "layers.21.mixer.out_proj.weight": "model-00003-of-00003.safetensors", "layers.21.mixer.rotary_emb.inv_freq": "model-00003-of-00003.safetensors", "layers.21.mlp.fc1.bias": "model-00003-of-00003.safetensors", "layers.21.mlp.fc1.weight": "model-00003-of-00003.safetensors", "layers.21.mlp.fc2.bias": "model-00003-of-00003.safetensors", "layers.21.mlp.fc2.weight": "model-00003-of-00003.safetensors", "layers.22.ln.bias": "model-00003-of-00003.safetensors", "layers.22.ln.weight": "model-00003-of-00003.safetensors", "layers.22.mixer.Wqkv.bias": "model-00003-of-00003.safetensors", "layers.22.mixer.Wqkv.weight": "model-00003-of-00003.safetensors", "layers.22.mixer.out_proj.bias": "model-00003-of-00003.safetensors", "layers.22.mixer.out_proj.weight": "model-00003-of-00003.safetensors", "layers.22.mixer.rotary_emb.inv_freq": "model-00003-of-00003.safetensors", "layers.22.mlp.fc1.bias": "model-00003-of-00003.safetensors", "layers.22.mlp.fc1.weight": "model-00003-of-00003.safetensors", "layers.22.mlp.fc2.bias": "model-00003-of-00003.safetensors", "layers.22.mlp.fc2.weight": "model-00003-of-00003.safetensors", "layers.23.ln.bias": "model-00003-of-00003.safetensors", "layers.23.ln.weight": "model-00003-of-00003.safetensors", "layers.23.mixer.Wqkv.bias": "model-00003-of-00003.safetensors", "layers.23.mixer.Wqkv.weight": "model-00003-of-00003.safetensors", "layers.23.mixer.out_proj.bias": "model-00003-of-00003.safetensors", "layers.23.mixer.out_proj.weight": "model-00003-of-00003.safetensors", "layers.23.mixer.rotary_emb.inv_freq": "model-00003-of-00003.safetensors", "layers.23.mlp.fc1.bias": "model-00003-of-00003.safetensors", "layers.23.mlp.fc1.weight": "model-00003-of-00003.safetensors", "layers.23.mlp.fc2.bias": "model-00003-of-00003.safetensors", "layers.23.mlp.fc2.weight": "model-00003-of-00003.safetensors", "layers.24.ln.bias": "model-00003-of-00003.safetensors", "layers.24.ln.weight": "model-00003-of-00003.safetensors", "layers.24.mixer.Wqkv.bias": "model-00003-of-00003.safetensors", "layers.24.mixer.Wqkv.weight": "model-00003-of-00003.safetensors", "layers.24.mixer.out_proj.bias": "model-00003-of-00003.safetensors", "layers.24.mixer.out_proj.weight": "model-00003-of-00003.safetensors", "layers.24.mixer.rotary_emb.inv_freq": "model-00003-of-00003.safetensors", "layers.24.mlp.fc1.bias": "model-00003-of-00003.safetensors", "layers.24.mlp.fc1.weight": "model-00003-of-00003.safetensors", "layers.24.mlp.fc2.bias": "model-00003-of-00003.safetensors", "layers.24.mlp.fc2.weight": "model-00003-of-00003.safetensors", "layers.25.linear.bias": "model-00003-of-00003.safetensors", "layers.25.linear.weight": "model-00003-of-00003.safetensors", "layers.25.ln.bias": "model-00003-of-00003.safetensors", "layers.25.ln.weight": "model-00003-of-00003.safetensors", "layers.3.ln.bias": "model-00001-of-00003.safetensors", "layers.3.ln.weight": "model-00001-of-00003.safetensors", "layers.3.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "layers.3.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "layers.3.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "layers.3.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "layers.3.mixer.rotary_emb.inv_freq": "model-00001-of-00003.safetensors", "layers.3.mlp.fc1.bias": "model-00001-of-00003.safetensors", "layers.3.mlp.fc1.weight": "model-00001-of-00003.safetensors", "layers.3.mlp.fc2.bias": "model-00001-of-00003.safetensors", "layers.3.mlp.fc2.weight": "model-00001-of-00003.safetensors", "layers.4.ln.bias": "model-00001-of-00003.safetensors", "layers.4.ln.weight": "model-00001-of-00003.safetensors", "layers.4.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "layers.4.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "layers.4.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "layers.4.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "layers.4.mixer.rotary_emb.inv_freq": "model-00001-of-00003.safetensors", "layers.4.mlp.fc1.bias": "model-00001-of-00003.safetensors", "layers.4.mlp.fc1.weight": "model-00001-of-00003.safetensors", "layers.4.mlp.fc2.bias": "model-00001-of-00003.safetensors", "layers.4.mlp.fc2.weight": "model-00001-of-00003.safetensors", "layers.5.ln.bias": "model-00001-of-00003.safetensors", "layers.5.ln.weight": "model-00001-of-00003.safetensors", "layers.5.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "layers.5.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "layers.5.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "layers.5.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "layers.5.mixer.rotary_emb.inv_freq": "model-00001-of-00003.safetensors", "layers.5.mlp.fc1.bias": "model-00001-of-00003.safetensors", "layers.5.mlp.fc1.weight": "model-00001-of-00003.safetensors", "layers.5.mlp.fc2.bias": "model-00001-of-00003.safetensors", "layers.5.mlp.fc2.weight": "model-00001-of-00003.safetensors", "layers.6.ln.bias": "model-00001-of-00003.safetensors", "layers.6.ln.weight": "model-00001-of-00003.safetensors", "layers.6.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "layers.6.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "layers.6.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "layers.6.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "layers.6.mixer.rotary_emb.inv_freq": "model-00001-of-00003.safetensors", "layers.6.mlp.fc1.bias": "model-00001-of-00003.safetensors", "layers.6.mlp.fc1.weight": "model-00001-of-00003.safetensors", "layers.6.mlp.fc2.bias": "model-00001-of-00003.safetensors", "layers.6.mlp.fc2.weight": "model-00001-of-00003.safetensors", "layers.7.ln.bias": "model-00001-of-00003.safetensors", "layers.7.ln.weight": "model-00001-of-00003.safetensors", "layers.7.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "layers.7.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "layers.7.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "layers.7.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "layers.7.mixer.rotary_emb.inv_freq": "model-00001-of-00003.safetensors", "layers.7.mlp.fc1.bias": "model-00001-of-00003.safetensors", "layers.7.mlp.fc1.weight": "model-00001-of-00003.safetensors", "layers.7.mlp.fc2.bias": "model-00001-of-00003.safetensors", "layers.7.mlp.fc2.weight": "model-00001-of-00003.safetensors", "layers.8.ln.bias": "model-00001-of-00003.safetensors", "layers.8.ln.weight": "model-00001-of-00003.safetensors", "layers.8.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "layers.8.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "layers.8.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "layers.8.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "layers.8.mixer.rotary_emb.inv_freq": "model-00001-of-00003.safetensors", "layers.8.mlp.fc1.bias": "model-00001-of-00003.safetensors", "layers.8.mlp.fc1.weight": "model-00001-of-00003.safetensors", "layers.8.mlp.fc2.bias": "model-00002-of-00003.safetensors", "layers.8.mlp.fc2.weight": "model-00002-of-00003.safetensors", "layers.9.ln.bias": "model-00002-of-00003.safetensors", "layers.9.ln.weight": "model-00002-of-00003.safetensors", "layers.9.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "layers.9.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "layers.9.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "layers.9.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "layers.9.mixer.rotary_emb.inv_freq": "model-00002-of-00003.safetensors", "layers.9.mlp.fc1.bias": "model-00002-of-00003.safetensors", "layers.9.mlp.fc1.weight": "model-00002-of-00003.safetensors", "layers.9.mlp.fc2.bias": "model-00002-of-00003.safetensors", "layers.9.mlp.fc2.weight": "model-00002-of-00003.safetensors" } }