diff --git "a/model.safetensors.index.json" "b/model.safetensors.index.json" --- "a/model.safetensors.index.json" +++ "b/model.safetensors.index.json" @@ -1,678 +1,916 @@ { "metadata": { - "total_size": 6773041280 + "total_size": 6437497984 }, "weight_map": { - "language_model.lm_head.linear.bias": "model-00002-of-00002.safetensors", - "language_model.lm_head.linear.weight": "model-00002-of-00002.safetensors", - "language_model.lm_head.ln.bias": "model-00002-of-00002.safetensors", - "language_model.lm_head.ln.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.embd.wte.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.0.ln.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.0.ln.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.0.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.0.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.0.mixer.out_proj.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.0.mixer.out_proj.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.0.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.0.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.0.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.0.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.1.ln.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.1.ln.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.1.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.1.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.1.mixer.out_proj.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.1.mixer.out_proj.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.1.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.1.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.1.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.1.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.10.ln.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.10.ln.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.10.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.10.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.10.mixer.out_proj.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.10.mixer.out_proj.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.10.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.10.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.10.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.10.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.11.ln.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.11.ln.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.11.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.11.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.11.mixer.out_proj.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.11.mixer.out_proj.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.11.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.11.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.11.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.11.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.12.ln.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.12.ln.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.12.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.12.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.12.mixer.out_proj.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.12.mixer.out_proj.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.12.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.12.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.12.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.12.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.13.ln.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.13.ln.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.13.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.13.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.13.mixer.out_proj.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.13.mixer.out_proj.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.13.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.13.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.13.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.13.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.14.ln.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.14.ln.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.14.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.14.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.14.mixer.out_proj.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.14.mixer.out_proj.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.14.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.14.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.14.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.14.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.15.ln.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.15.ln.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.15.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.15.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.15.mixer.out_proj.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.15.mixer.out_proj.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.15.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.15.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.15.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.15.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.16.ln.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.16.ln.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.16.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.16.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.16.mixer.out_proj.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.16.mixer.out_proj.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.16.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.16.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.16.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.16.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.17.ln.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.17.ln.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.17.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.17.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.17.mixer.out_proj.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.17.mixer.out_proj.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.17.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.17.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.17.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.17.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.18.ln.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.18.ln.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.18.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.18.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.18.mixer.out_proj.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.18.mixer.out_proj.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.18.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.18.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.18.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.18.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.19.ln.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.19.ln.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.19.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.19.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.19.mixer.out_proj.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.19.mixer.out_proj.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.19.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.19.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.19.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.19.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.2.ln.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.2.ln.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.2.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.2.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.2.mixer.out_proj.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.2.mixer.out_proj.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.2.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.2.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.2.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.2.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.20.ln.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.20.ln.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.20.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.20.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.20.mixer.out_proj.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.20.mixer.out_proj.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.20.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.20.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.20.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.20.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.21.ln.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.21.ln.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.21.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.21.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.21.mixer.out_proj.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.21.mixer.out_proj.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.21.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.21.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.21.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.21.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.22.ln.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.22.ln.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.22.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.22.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.22.mixer.out_proj.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.22.mixer.out_proj.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.22.mlp.fc1.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.22.mlp.fc1.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.22.mlp.fc2.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.22.mlp.fc2.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.23.ln.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.23.ln.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.23.mixer.Wqkv.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.23.mixer.Wqkv.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.23.mixer.out_proj.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.23.mixer.out_proj.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.23.mlp.fc1.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.23.mlp.fc1.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.23.mlp.fc2.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.23.mlp.fc2.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.24.ln.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.24.ln.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.24.mixer.Wqkv.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.24.mixer.Wqkv.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.24.mixer.out_proj.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.24.mixer.out_proj.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.24.mlp.fc1.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.24.mlp.fc1.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.24.mlp.fc2.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.24.mlp.fc2.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.25.ln.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.25.ln.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.25.mixer.Wqkv.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.25.mixer.Wqkv.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.25.mixer.out_proj.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.25.mixer.out_proj.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.25.mlp.fc1.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.25.mlp.fc1.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.25.mlp.fc2.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.25.mlp.fc2.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.26.ln.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.26.ln.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.26.mixer.Wqkv.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.26.mixer.Wqkv.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.26.mixer.out_proj.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.26.mixer.out_proj.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.26.mlp.fc1.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.26.mlp.fc1.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.26.mlp.fc2.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.26.mlp.fc2.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.27.ln.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.27.ln.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.27.mixer.Wqkv.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.27.mixer.Wqkv.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.27.mixer.out_proj.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.27.mixer.out_proj.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.27.mlp.fc1.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.27.mlp.fc1.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.27.mlp.fc2.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.27.mlp.fc2.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.28.ln.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.28.ln.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.28.mixer.Wqkv.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.28.mixer.Wqkv.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.28.mixer.out_proj.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.28.mixer.out_proj.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.28.mlp.fc1.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.28.mlp.fc1.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.28.mlp.fc2.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.28.mlp.fc2.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.29.ln.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.29.ln.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.29.mixer.Wqkv.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.29.mixer.Wqkv.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.29.mixer.out_proj.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.29.mixer.out_proj.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.29.mlp.fc1.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.29.mlp.fc1.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.29.mlp.fc2.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.29.mlp.fc2.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.3.ln.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.3.ln.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.3.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.3.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.3.mixer.out_proj.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.3.mixer.out_proj.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.3.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.3.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.3.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.3.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.30.ln.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.30.ln.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.30.mixer.Wqkv.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.30.mixer.Wqkv.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.30.mixer.out_proj.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.30.mixer.out_proj.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.30.mlp.fc1.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.30.mlp.fc1.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.30.mlp.fc2.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.30.mlp.fc2.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.31.ln.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.31.ln.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.31.mixer.Wqkv.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.31.mixer.Wqkv.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.31.mixer.out_proj.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.31.mixer.out_proj.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.31.mlp.fc1.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.31.mlp.fc1.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.31.mlp.fc2.bias": "model-00002-of-00002.safetensors", - "language_model.transformer.h.31.mlp.fc2.weight": "model-00002-of-00002.safetensors", - "language_model.transformer.h.4.ln.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.4.ln.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.4.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.4.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.4.mixer.out_proj.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.4.mixer.out_proj.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.4.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.4.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.4.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.4.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.5.ln.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.5.ln.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.5.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.5.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.5.mixer.out_proj.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.5.mixer.out_proj.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.5.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.5.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.5.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.5.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.6.ln.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.6.ln.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.6.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.6.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.6.mixer.out_proj.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.6.mixer.out_proj.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.6.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.6.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.6.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.6.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.7.ln.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.7.ln.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.7.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.7.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.7.mixer.out_proj.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.7.mixer.out_proj.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.7.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.7.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.7.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.7.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.8.ln.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.8.ln.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.8.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.8.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.8.mixer.out_proj.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.8.mixer.out_proj.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.8.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.8.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.8.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.8.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.9.ln.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.9.ln.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.9.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.9.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.9.mixer.out_proj.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.9.mixer.out_proj.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.9.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.9.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "language_model.transformer.h.9.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "language_model.transformer.h.9.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "language_model.lm_head.bias": "model-00002-of-00002.safetensors", + "language_model.lm_head.weight": "model-00002-of-00002.safetensors", + "language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "language_model.model.final_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.final_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.15.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.15.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.16.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.16.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.17.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.17.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.18.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.18.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.19.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.19.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.20.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.20.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.21.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.21.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.22.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.22.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.22.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.23.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.23.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.23.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.24.input_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.24.mlp.fc1.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.24.mlp.fc1.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.24.mlp.fc2.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.24.mlp.fc2.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.24.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.24.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.25.input_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.mlp.fc1.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.mlp.fc1.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.mlp.fc2.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.mlp.fc2.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.self_attn.dense.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.self_attn.dense.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.input_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.mlp.fc1.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.mlp.fc1.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.mlp.fc2.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.mlp.fc2.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.self_attn.dense.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.self_attn.dense.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.input_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.mlp.fc1.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.mlp.fc1.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.mlp.fc2.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.mlp.fc2.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.self_attn.dense.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.self_attn.dense.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.input_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.mlp.fc1.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.mlp.fc1.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.mlp.fc2.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.mlp.fc2.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.self_attn.dense.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.self_attn.dense.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.input_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.mlp.fc1.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.mlp.fc1.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.mlp.fc2.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.mlp.fc2.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.self_attn.dense.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.self_attn.dense.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.30.input_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.30.mlp.fc1.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.30.mlp.fc1.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.30.mlp.fc2.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.30.mlp.fc2.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.30.self_attn.dense.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.30.self_attn.dense.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.31.input_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.31.mlp.fc1.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.31.mlp.fc1.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.31.mlp.fc2.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.31.mlp.fc2.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.31.self_attn.dense.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.31.self_attn.dense.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "multi_modal_projector.linear_1.bias": "model-00001-of-00002.safetensors", "multi_modal_projector.linear_1.weight": "model-00001-of-00002.safetensors", "multi_modal_projector.linear_2.bias": "model-00001-of-00002.safetensors", "multi_modal_projector.linear_2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.attn_pool.kv.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.attn_pool.kv.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.attn_pool.latent": "model-00001-of-00002.safetensors", - "vision_model.trunk.attn_pool.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.attn_pool.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.attn_pool.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.attn_pool.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.attn_pool.norm.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.attn_pool.norm.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.attn_pool.proj.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.attn_pool.proj.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.attn_pool.q.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.attn_pool.q.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.0.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.0.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.0.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.0.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.0.norm1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.0.norm1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.0.norm2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.0.norm2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.1.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.1.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.1.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.1.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.1.norm1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.1.norm1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.1.norm2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.1.norm2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.10.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.10.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.10.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.10.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.10.norm1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.10.norm1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.10.norm2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.10.norm2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.11.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.11.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.11.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.11.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.11.norm1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.11.norm1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.11.norm2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.11.norm2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.12.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.12.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.12.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.12.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.12.norm1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.12.norm1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.12.norm2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.12.norm2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.13.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.13.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.13.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.13.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.13.norm1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.13.norm1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.13.norm2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.13.norm2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.14.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.14.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.14.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.14.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.14.norm1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.14.norm1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.14.norm2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.14.norm2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.15.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.15.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.15.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.15.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.15.norm1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.15.norm1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.15.norm2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.15.norm2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.16.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.16.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.16.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.16.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.16.norm1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.16.norm1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.16.norm2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.16.norm2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.17.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.17.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.17.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.17.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.17.norm1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.17.norm1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.17.norm2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.17.norm2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.18.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.18.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.18.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.18.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.18.norm1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.18.norm1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.18.norm2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.18.norm2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.19.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.19.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.19.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.19.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.19.norm1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.19.norm1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.19.norm2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.19.norm2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.2.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.2.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.2.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.2.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.2.norm1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.2.norm1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.2.norm2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.2.norm2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.20.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.20.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.20.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.20.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.20.norm1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.20.norm1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.20.norm2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.20.norm2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.21.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.21.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.21.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.21.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.21.norm1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.21.norm1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.21.norm2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.21.norm2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.22.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.22.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.22.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.22.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.22.norm1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.22.norm1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.22.norm2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.22.norm2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.23.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.23.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.23.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.23.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.23.norm1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.23.norm1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.23.norm2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.23.norm2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.24.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.24.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.24.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.24.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.24.norm1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.24.norm1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.24.norm2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.24.norm2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.25.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.25.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.25.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.25.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.25.norm1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.25.norm1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.25.norm2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.25.norm2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.26.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.26.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.26.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.26.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.26.norm1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.26.norm1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.26.norm2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.26.norm2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.3.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.3.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.3.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.3.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.3.norm1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.3.norm1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.3.norm2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.3.norm2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.4.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.4.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.4.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.4.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.4.norm1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.4.norm1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.4.norm2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.4.norm2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.5.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.5.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.5.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.5.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.5.norm1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.5.norm1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.5.norm2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.5.norm2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.6.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.6.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.6.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.6.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.6.norm1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.6.norm1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.6.norm2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.6.norm2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.7.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.7.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.7.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.7.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.7.norm1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.7.norm1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.7.norm2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.7.norm2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.8.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.8.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.8.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.8.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.8.norm1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.8.norm1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.8.norm2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.8.norm2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.9.mlp.fc1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.9.mlp.fc1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.9.mlp.fc2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.9.mlp.fc2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.9.norm1.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.9.norm1.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.9.norm2.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.blocks.9.norm2.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.norm.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.norm.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.patch_embed.proj.bias": "model-00001-of-00002.safetensors", - "vision_model.trunk.patch_embed.proj.weight": "model-00001-of-00002.safetensors", - "vision_model.trunk.pos_embed": "model-00001-of-00002.safetensors" + "vision_model.coord_embed.0.bias": "model-00001-of-00002.safetensors", + "vision_model.coord_embed.0.weight": "model-00001-of-00002.safetensors", + "vision_model.coord_embed.2.bias": "model-00001-of-00002.safetensors", + "vision_model.coord_embed.2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.head.attention.in_proj_bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.head.attention.in_proj_weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.head.attention.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.head.attention.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.head.layernorm.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.head.layernorm.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.head.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.head.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.head.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.head.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.head.probe": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors", + "vision_model.vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors" } }