{ "metadata": { "total_size": 15159214280 }, "weight_map": { "grounding_encoder.sam2_model.image_encoder.neck.convs.0.conv.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.neck.convs.0.conv.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.neck.convs.1.conv.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.neck.convs.1.conv.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.neck.convs.2.conv.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.neck.convs.2.conv.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.neck.convs.3.conv.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.neck.convs.3.conv.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.0.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.0.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.0.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.0.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.0.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.0.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.0.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.0.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.0.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.0.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.0.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.0.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.1.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.1.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.1.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.1.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.1.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.1.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.1.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.1.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.1.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.1.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.1.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.1.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.10.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.10.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.10.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.10.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.10.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.10.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.10.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.10.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.10.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.10.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.10.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.10.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.11.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.11.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.11.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.11.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.11.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.11.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.11.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.11.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.11.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.11.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.11.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.11.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.12.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.12.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.12.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.12.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.12.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.12.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.12.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.12.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.12.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.12.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.12.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.12.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.13.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.13.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.13.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.13.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.13.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.13.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.13.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.13.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.13.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.13.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.13.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.13.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.14.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.14.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.14.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.14.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.14.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.14.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.14.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.14.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.14.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.14.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.14.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.14.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.15.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.15.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.15.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.15.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.15.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.15.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.15.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.15.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.15.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.15.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.15.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.15.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.16.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.16.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.16.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.16.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.16.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.16.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.16.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.16.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.16.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.16.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.16.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.16.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.17.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.17.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.17.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.17.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.17.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.17.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.17.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.17.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.17.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.17.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.17.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.17.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.18.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.18.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.18.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.18.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.18.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.18.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.18.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.18.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.18.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.18.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.18.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.18.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.19.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.19.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.19.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.19.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.19.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.19.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.19.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.19.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.19.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.19.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.19.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.19.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.2.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.2.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.2.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.2.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.2.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.2.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.2.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.2.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.2.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.2.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.2.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.2.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.2.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.2.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.20.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.20.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.20.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.20.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.20.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.20.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.20.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.20.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.20.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.20.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.20.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.20.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.21.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.21.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.21.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.21.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.21.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.21.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.21.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.21.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.21.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.21.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.21.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.21.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.22.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.22.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.22.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.22.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.22.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.22.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.22.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.22.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.22.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.22.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.22.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.22.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.23.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.23.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.23.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.23.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.23.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.23.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.23.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.23.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.23.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.23.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.23.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.23.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.24.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.24.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.24.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.24.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.24.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.24.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.24.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.24.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.24.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.24.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.24.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.24.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.25.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.25.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.25.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.25.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.25.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.25.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.25.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.25.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.25.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.25.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.25.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.25.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.26.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.26.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.26.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.26.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.26.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.26.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.26.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.26.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.26.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.26.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.26.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.26.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.27.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.27.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.27.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.27.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.27.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.27.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.27.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.27.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.27.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.27.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.27.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.27.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.28.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.28.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.28.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.28.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.28.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.28.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.28.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.28.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.28.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.28.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.28.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.28.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.29.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.29.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.29.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.29.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.29.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.29.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.29.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.29.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.29.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.29.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.29.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.29.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.3.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.3.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.3.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.3.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.3.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.3.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.3.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.3.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.3.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.3.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.3.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.3.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.30.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.30.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.30.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.30.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.30.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.30.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.30.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.30.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.30.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.30.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.30.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.30.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.31.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.31.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.31.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.31.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.31.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.31.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.31.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.31.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.31.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.31.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.31.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.31.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.32.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.32.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.32.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.32.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.32.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.32.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.32.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.32.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.32.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.32.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.32.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.32.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.33.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.33.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.33.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.33.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.33.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.33.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.33.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.33.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.33.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.33.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.33.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.33.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.34.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.34.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.34.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.34.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.34.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.34.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.34.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.34.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.34.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.34.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.34.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.34.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.35.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.35.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.35.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.35.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.35.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.35.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.35.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.35.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.35.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.35.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.35.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.35.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.36.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.36.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.36.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.36.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.36.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.36.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.36.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.36.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.36.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.36.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.36.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.36.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.37.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.37.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.37.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.37.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.37.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.37.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.37.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.37.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.37.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.37.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.37.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.37.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.38.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.38.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.38.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.38.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.38.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.38.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.38.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.38.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.38.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.38.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.38.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.38.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.39.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.39.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.39.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.39.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.39.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.39.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.39.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.39.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.39.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.39.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.39.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.39.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.4.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.4.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.4.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.4.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.4.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.4.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.4.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.4.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.4.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.4.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.4.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.4.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.40.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.40.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.40.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.40.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.40.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.40.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.40.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.40.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.40.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.40.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.40.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.40.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.41.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.41.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.41.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.41.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.41.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.41.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.41.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.41.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.41.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.41.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.41.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.41.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.42.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.42.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.42.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.42.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.42.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.42.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.42.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.42.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.42.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.42.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.42.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.42.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.43.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.43.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.43.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.43.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.43.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.43.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.43.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.43.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.43.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.43.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.43.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.43.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.44.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.44.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.44.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.44.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.44.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.44.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.44.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.44.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.44.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.44.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.44.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.44.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.44.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.44.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.45.attn.proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.45.attn.proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.45.attn.qkv.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.45.attn.qkv.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.45.mlp.layers.0.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.45.mlp.layers.0.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.45.mlp.layers.1.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.45.mlp.layers.1.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.45.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.45.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.45.norm2.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.45.norm2.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.46.attn.proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.46.attn.proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.46.attn.qkv.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.46.attn.qkv.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.46.mlp.layers.0.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.46.mlp.layers.0.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.46.mlp.layers.1.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.46.mlp.layers.1.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.46.norm1.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.46.norm1.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.46.norm2.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.46.norm2.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.47.attn.proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.47.attn.proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.47.attn.qkv.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.47.attn.qkv.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.47.mlp.layers.0.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.47.mlp.layers.0.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.47.mlp.layers.1.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.47.mlp.layers.1.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.47.norm1.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.47.norm1.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.47.norm2.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.47.norm2.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.5.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.5.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.5.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.5.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.5.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.5.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.5.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.5.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.5.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.5.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.5.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.5.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.6.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.6.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.6.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.6.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.6.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.6.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.6.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.6.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.6.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.6.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.6.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.6.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.7.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.7.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.7.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.7.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.7.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.7.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.7.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.7.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.7.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.7.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.7.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.7.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.8.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.8.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.8.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.8.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.8.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.8.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.8.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.8.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.8.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.8.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.8.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.8.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.8.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.8.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.9.attn.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.9.attn.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.9.attn.qkv.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.9.attn.qkv.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.9.mlp.layers.0.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.9.mlp.layers.0.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.9.mlp.layers.1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.9.mlp.layers.1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.9.norm1.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.9.norm1.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.9.norm2.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.blocks.9.norm2.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.patch_embed.proj.bias": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.patch_embed.proj.weight": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.pos_embed": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.image_encoder.trunk.pos_embed_window": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.mask_downsample.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.mask_downsample.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.maskmem_tpos_enc": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.0.cross_attn_image.k_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.0.cross_attn_image.k_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.0.cross_attn_image.out_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.0.cross_attn_image.out_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.0.cross_attn_image.q_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.0.cross_attn_image.q_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.0.cross_attn_image.v_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.0.cross_attn_image.v_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.0.linear1.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.0.linear1.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.0.linear2.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.0.linear2.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.0.norm1.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.0.norm1.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.0.norm2.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.0.norm2.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.0.norm3.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.0.norm3.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.0.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.0.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.0.self_attn.out_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.0.self_attn.out_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.0.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.0.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.0.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.0.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.1.cross_attn_image.k_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.1.cross_attn_image.k_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.1.cross_attn_image.out_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.1.cross_attn_image.out_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.1.cross_attn_image.q_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.1.cross_attn_image.q_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.1.cross_attn_image.v_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.1.cross_attn_image.v_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.1.linear1.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.1.linear1.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.1.linear2.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.1.linear2.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.1.norm1.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.1.norm1.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.1.norm2.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.1.norm2.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.1.norm3.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.1.norm3.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.1.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.1.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.1.self_attn.out_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.1.self_attn.out_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.1.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.1.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.1.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.1.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.2.cross_attn_image.k_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.2.cross_attn_image.k_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.2.cross_attn_image.out_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.2.cross_attn_image.out_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.2.cross_attn_image.q_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.2.cross_attn_image.q_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.2.cross_attn_image.v_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.2.cross_attn_image.v_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.2.linear1.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.2.linear1.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.2.linear2.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.2.linear2.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.2.norm1.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.2.norm1.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.2.norm2.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.2.norm2.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.2.norm3.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.2.norm3.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.2.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.2.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.2.self_attn.out_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.2.self_attn.out_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.2.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.2.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.2.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.2.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.3.cross_attn_image.k_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.3.cross_attn_image.k_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.3.cross_attn_image.out_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.3.cross_attn_image.out_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.3.cross_attn_image.q_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.3.cross_attn_image.q_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.3.cross_attn_image.v_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.3.cross_attn_image.v_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.3.linear1.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.3.linear1.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.3.linear2.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.3.linear2.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.3.norm1.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.3.norm1.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.3.norm2.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.3.norm2.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.3.norm3.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.3.norm3.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.3.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.3.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.3.self_attn.out_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.3.self_attn.out_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.3.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.3.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.3.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.layers.3.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.norm.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_attention.norm.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.fuser.layers.0.dwconv.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.fuser.layers.0.dwconv.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.fuser.layers.0.g_weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.fuser.layers.0.norm.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.fuser.layers.0.norm.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.fuser.layers.0.pwconv1.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.fuser.layers.0.pwconv1.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.fuser.layers.0.pwconv2.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.fuser.layers.0.pwconv2.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.fuser.layers.1.dwconv.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.fuser.layers.1.dwconv.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.fuser.layers.1.g_weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.fuser.layers.1.norm.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.fuser.layers.1.norm.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.fuser.layers.1.pwconv1.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.fuser.layers.1.pwconv1.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.fuser.layers.1.pwconv2.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.fuser.layers.1.pwconv2.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.mask_downsampler.encoder.0.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.mask_downsampler.encoder.0.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.mask_downsampler.encoder.1.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.mask_downsampler.encoder.1.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.mask_downsampler.encoder.10.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.mask_downsampler.encoder.10.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.mask_downsampler.encoder.12.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.mask_downsampler.encoder.12.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.mask_downsampler.encoder.3.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.mask_downsampler.encoder.3.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.mask_downsampler.encoder.4.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.mask_downsampler.encoder.4.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.mask_downsampler.encoder.6.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.mask_downsampler.encoder.6.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.mask_downsampler.encoder.7.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.mask_downsampler.encoder.7.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.mask_downsampler.encoder.9.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.mask_downsampler.encoder.9.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.out_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.out_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.pix_feat_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.memory_encoder.pix_feat_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.no_mem_embed": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.no_mem_pos_enc": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.no_obj_ptr": "model-00003-of-00004.safetensors", "grounding_encoder.sam2_model.obj_ptr_proj.layers.0.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.obj_ptr_proj.layers.0.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.obj_ptr_proj.layers.1.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.obj_ptr_proj.layers.1.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.obj_ptr_proj.layers.2.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.obj_ptr_proj.layers.2.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.conv_s0.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.conv_s0.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.conv_s1.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.conv_s1.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.iou_prediction_head.layers.0.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.iou_prediction_head.layers.0.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.iou_prediction_head.layers.1.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.iou_prediction_head.layers.1.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.iou_prediction_head.layers.2.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.iou_prediction_head.layers.2.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.iou_token.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.mask_tokens.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.obj_score_token.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.output_hypernetworks_mlps.0.layers.0.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.output_hypernetworks_mlps.0.layers.0.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.output_hypernetworks_mlps.0.layers.1.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.output_hypernetworks_mlps.0.layers.1.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.output_hypernetworks_mlps.0.layers.2.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.output_hypernetworks_mlps.0.layers.2.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.output_hypernetworks_mlps.1.layers.0.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.output_hypernetworks_mlps.1.layers.0.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.output_hypernetworks_mlps.1.layers.1.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.output_hypernetworks_mlps.1.layers.1.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.output_hypernetworks_mlps.1.layers.2.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.output_hypernetworks_mlps.1.layers.2.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.output_hypernetworks_mlps.2.layers.0.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.output_hypernetworks_mlps.2.layers.0.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.output_hypernetworks_mlps.2.layers.1.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.output_hypernetworks_mlps.2.layers.1.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.output_hypernetworks_mlps.2.layers.2.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.output_hypernetworks_mlps.2.layers.2.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.output_hypernetworks_mlps.3.layers.0.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.output_hypernetworks_mlps.3.layers.0.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.output_hypernetworks_mlps.3.layers.1.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.output_hypernetworks_mlps.3.layers.1.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.output_hypernetworks_mlps.3.layers.2.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.output_hypernetworks_mlps.3.layers.2.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.output_upscaling.0.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.output_upscaling.0.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.output_upscaling.1.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.output_upscaling.1.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.output_upscaling.3.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.output_upscaling.3.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.pred_obj_score_head.layers.0.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.pred_obj_score_head.layers.0.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.pred_obj_score_head.layers.1.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.pred_obj_score_head.layers.1.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.pred_obj_score_head.layers.2.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.pred_obj_score_head.layers.2.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.final_attn_token_to_image.k_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.final_attn_token_to_image.k_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.final_attn_token_to_image.out_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.final_attn_token_to_image.out_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.final_attn_token_to_image.q_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.final_attn_token_to_image.q_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.final_attn_token_to_image.v_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.final_attn_token_to_image.v_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.cross_attn_image_to_token.k_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.cross_attn_image_to_token.k_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.cross_attn_image_to_token.out_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.cross_attn_image_to_token.out_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.cross_attn_image_to_token.q_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.cross_attn_image_to_token.q_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.cross_attn_image_to_token.v_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.cross_attn_image_to_token.v_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.cross_attn_token_to_image.k_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.cross_attn_token_to_image.k_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.cross_attn_token_to_image.out_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.cross_attn_token_to_image.out_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.cross_attn_token_to_image.q_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.cross_attn_token_to_image.q_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.cross_attn_token_to_image.v_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.cross_attn_token_to_image.v_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.mlp.layers.0.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.mlp.layers.0.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.mlp.layers.1.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.mlp.layers.1.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.norm1.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.norm1.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.norm2.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.norm2.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.norm3.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.norm3.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.norm4.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.norm4.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.self_attn.out_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.self_attn.out_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.0.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.cross_attn_image_to_token.k_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.cross_attn_image_to_token.k_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.cross_attn_image_to_token.out_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.cross_attn_image_to_token.out_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.cross_attn_image_to_token.q_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.cross_attn_image_to_token.q_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.cross_attn_image_to_token.v_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.cross_attn_image_to_token.v_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.cross_attn_token_to_image.k_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.cross_attn_token_to_image.k_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.cross_attn_token_to_image.out_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.cross_attn_token_to_image.out_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.cross_attn_token_to_image.q_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.cross_attn_token_to_image.q_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.cross_attn_token_to_image.v_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.cross_attn_token_to_image.v_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.mlp.layers.0.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.mlp.layers.0.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.mlp.layers.1.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.mlp.layers.1.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.norm1.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.norm1.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.norm2.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.norm2.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.norm3.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.norm3.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.norm4.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.norm4.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.self_attn.out_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.self_attn.out_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.layers.1.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.norm_final_attn.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_mask_decoder.transformer.norm_final_attn.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_prompt_encoder.mask_downscaling.0.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_prompt_encoder.mask_downscaling.0.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_prompt_encoder.mask_downscaling.1.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_prompt_encoder.mask_downscaling.1.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_prompt_encoder.mask_downscaling.3.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_prompt_encoder.mask_downscaling.3.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_prompt_encoder.mask_downscaling.4.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_prompt_encoder.mask_downscaling.4.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_prompt_encoder.mask_downscaling.6.bias": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_prompt_encoder.mask_downscaling.6.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_prompt_encoder.no_mask_embed.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_prompt_encoder.not_a_point_embed.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_prompt_encoder.pe_layer.positional_encoding_gaussian_matrix": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_prompt_encoder.point_embeddings.0.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_prompt_encoder.point_embeddings.1.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_prompt_encoder.point_embeddings.2.weight": "model-00004-of-00004.safetensors", "grounding_encoder.sam2_model.sam_prompt_encoder.point_embeddings.3.weight": "model-00004-of-00004.safetensors", "language_model.lm_head.weight": "model-00003-of-00004.safetensors", "language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.19.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.19.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.19.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.20.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.20.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.20.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.21.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.21.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.21.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.22.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.22.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.22.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.23.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.23.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.23.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.24.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.24.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.24.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.25.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.25.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.25.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.25.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.26.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.26.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.26.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.26.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "language_model.model.layers.26.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.28.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "language_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.28.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "language_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.28.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "language_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.29.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "language_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.29.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "language_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.29.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "language_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.30.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "language_model.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.30.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "language_model.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.30.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "language_model.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.31.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "language_model.model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.31.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "language_model.model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.31.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "language_model.model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.32.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "language_model.model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.32.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "language_model.model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.32.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "language_model.model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.33.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "language_model.model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.33.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "language_model.model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.33.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "language_model.model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.34.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "language_model.model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.34.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "language_model.model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.34.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "language_model.model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.35.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.35.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.35.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.35.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "language_model.model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.35.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "language_model.model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.35.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "language_model.model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.norm.weight": "model-00003-of-00004.safetensors", "mlp1.0.bias": "model-00003-of-00004.safetensors", "mlp1.0.weight": "model-00003-of-00004.safetensors", "mlp1.1.bias": "model-00003-of-00004.safetensors", "mlp1.1.weight": "model-00003-of-00004.safetensors", "mlp1.3.bias": "model-00003-of-00004.safetensors", "mlp1.3.weight": "model-00003-of-00004.safetensors", "text_hidden_fcs.0.bias": "model-00004-of-00004.safetensors", "text_hidden_fcs.0.weight": "model-00004-of-00004.safetensors", "text_hidden_fcs.2.bias": "model-00004-of-00004.safetensors", "text_hidden_fcs.2.weight": "model-00004-of-00004.safetensors", "vision_model.embeddings.class_embedding": "model-00001-of-00004.safetensors", "vision_model.embeddings.patch_embedding.bias": "model-00001-of-00004.safetensors", "vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors", "vision_model.embeddings.position_embedding": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.0.attn.proj.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.0.attn.proj.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.0.attn.qkv.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.0.attn.qkv.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.0.ls1": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.0.ls2": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.0.norm1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.0.norm1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.0.norm2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.0.norm2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.1.attn.proj.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.1.attn.proj.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.1.attn.qkv.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.1.attn.qkv.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.1.ls1": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.1.ls2": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.1.norm1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.1.norm1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.1.norm2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.1.norm2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.10.attn.proj.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.10.attn.proj.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.10.attn.qkv.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.10.attn.qkv.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.10.ls1": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.10.ls2": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.10.norm1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.10.norm1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.10.norm2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.10.norm2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.11.attn.proj.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.11.attn.proj.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.11.attn.qkv.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.11.attn.qkv.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.11.ls1": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.11.ls2": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.11.norm1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.11.norm1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.11.norm2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.11.norm2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.12.attn.proj.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.12.attn.proj.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.12.attn.qkv.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.12.attn.qkv.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.12.ls1": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.12.ls2": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.12.norm1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.12.norm1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.12.norm2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.12.norm2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.13.attn.proj.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.13.attn.proj.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.13.attn.qkv.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.13.attn.qkv.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.13.ls1": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.13.ls2": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.13.norm1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.13.norm1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.13.norm2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.13.norm2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.14.attn.proj.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.14.attn.proj.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.14.attn.qkv.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.14.attn.qkv.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.14.ls1": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.14.ls2": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.14.norm1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.14.norm1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.14.norm2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.14.norm2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.15.attn.proj.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.15.attn.proj.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.15.attn.qkv.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.15.attn.qkv.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.15.ls1": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.15.ls2": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.15.norm1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.15.norm1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.15.norm2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.15.norm2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.16.attn.proj.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.16.attn.proj.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.16.attn.qkv.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.16.attn.qkv.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.16.ls1": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.16.ls2": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.16.norm1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.16.norm1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.16.norm2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.16.norm2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.17.attn.proj.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.17.attn.proj.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.17.attn.qkv.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.17.attn.qkv.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.17.ls1": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.17.ls2": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.17.norm1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.17.norm1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.17.norm2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.17.norm2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.18.attn.proj.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.18.attn.proj.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.18.attn.qkv.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.18.attn.qkv.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.18.ls1": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.18.ls2": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.18.norm1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.18.norm1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.18.norm2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.18.norm2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.19.attn.proj.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.19.attn.proj.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.19.attn.qkv.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.19.attn.qkv.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.19.ls1": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.19.ls2": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.19.norm1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.19.norm1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.19.norm2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.19.norm2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.2.attn.proj.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.2.attn.proj.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.2.attn.qkv.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.2.attn.qkv.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.2.ls1": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.2.ls2": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.2.norm1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.2.norm1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.2.norm2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.2.norm2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.20.attn.proj.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.20.attn.proj.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.20.attn.qkv.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.20.attn.qkv.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.20.ls1": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.20.ls2": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.20.norm1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.20.norm1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.20.norm2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.20.norm2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.21.attn.proj.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.21.attn.proj.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.21.attn.qkv.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.21.attn.qkv.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.21.ls1": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.21.ls2": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.21.norm1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.21.norm1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.21.norm2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.21.norm2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.22.attn.proj.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.22.attn.proj.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.22.attn.qkv.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.22.attn.qkv.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.22.ls1": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.22.ls2": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.22.norm1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.22.norm1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.22.norm2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.22.norm2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.23.attn.proj.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.23.attn.proj.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.23.attn.qkv.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.23.attn.qkv.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.23.ls1": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.23.ls2": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.23.norm1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.23.norm1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.23.norm2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.23.norm2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.3.attn.proj.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.3.attn.proj.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.3.attn.qkv.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.3.attn.qkv.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.3.ls1": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.3.ls2": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.3.norm1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.3.norm1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.3.norm2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.3.norm2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.4.attn.proj.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.4.attn.proj.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.4.attn.qkv.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.4.attn.qkv.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.4.ls1": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.4.ls2": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.4.norm1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.4.norm1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.4.norm2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.4.norm2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.5.attn.proj.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.5.attn.proj.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.5.attn.qkv.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.5.attn.qkv.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.5.ls1": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.5.ls2": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.5.norm1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.5.norm1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.5.norm2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.5.norm2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.6.attn.proj.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.6.attn.proj.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.6.attn.qkv.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.6.attn.qkv.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.6.ls1": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.6.ls2": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.6.norm1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.6.norm1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.6.norm2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.6.norm2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.7.attn.proj.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.7.attn.proj.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.7.attn.qkv.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.7.attn.qkv.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.7.ls1": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.7.ls2": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.7.norm1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.7.norm1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.7.norm2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.7.norm2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.8.attn.proj.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.8.attn.proj.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.8.attn.qkv.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.8.attn.qkv.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.8.ls1": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.8.ls2": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.8.norm1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.8.norm1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.8.norm2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.8.norm2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.9.attn.proj.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.9.attn.proj.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.9.attn.qkv.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.9.attn.qkv.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.9.ls1": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.9.ls2": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.9.norm1.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.9.norm1.weight": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.9.norm2.bias": "model-00001-of-00004.safetensors", "vision_model.encoder.layers.9.norm2.weight": "model-00001-of-00004.safetensors" } }