{ "metadata": { "total_size": 5093506560 }, "weight_map": { "image_encoder.blocks.0.attn.key.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.0.attn.key.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.0.attn.out.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.0.attn.out.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.0.attn.query.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.0.attn.query.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.0.attn.value.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.0.attn.value.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.0.ls1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.0.ls2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.0.mlp.hidden_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.0.mlp.hidden_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.0.mlp.output_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.0.mlp.output_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.0.norm1.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.0.norm1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.0.norm2.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.0.norm2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.1.attn.key.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.1.attn.key.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.1.attn.out.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.1.attn.out.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.1.attn.query.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.1.attn.query.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.1.attn.value.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.1.attn.value.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.1.ls1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.1.ls2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.1.mlp.hidden_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.1.mlp.hidden_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.1.mlp.output_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.1.mlp.output_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.1.norm1.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.1.norm1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.1.norm2.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.1.norm2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.10.attn.key.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.10.attn.key.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.10.attn.out.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.10.attn.out.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.10.attn.query.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.10.attn.query.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.10.attn.value.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.10.attn.value.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.10.ls1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.10.ls2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.10.mlp.hidden_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.10.mlp.hidden_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.10.mlp.output_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.10.mlp.output_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.10.norm1.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.10.norm1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.10.norm2.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.10.norm2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.11.attn.key.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.11.attn.key.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.11.attn.out.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.11.attn.out.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.11.attn.query.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.11.attn.query.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.11.attn.value.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.11.attn.value.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.11.ls1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.11.ls2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.11.mlp.hidden_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.11.mlp.hidden_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.11.mlp.output_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.11.mlp.output_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.11.norm1.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.11.norm1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.11.norm2.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.11.norm2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.12.attn.key.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.12.attn.key.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.12.attn.out.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.12.attn.out.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.12.attn.query.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.12.attn.query.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.12.attn.value.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.12.attn.value.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.12.ls1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.12.ls2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.12.mlp.hidden_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.12.mlp.hidden_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.12.mlp.output_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.12.mlp.output_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.12.norm1.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.12.norm1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.12.norm2.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.12.norm2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.13.attn.key.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.13.attn.key.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.13.attn.out.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.13.attn.out.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.13.attn.query.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.13.attn.query.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.13.attn.value.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.13.attn.value.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.13.ls1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.13.ls2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.13.mlp.hidden_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.13.mlp.hidden_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.13.mlp.output_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.13.mlp.output_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.13.norm1.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.13.norm1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.13.norm2.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.13.norm2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.14.attn.key.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.14.attn.key.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.14.attn.out.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.14.attn.out.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.14.attn.query.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.14.attn.query.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.14.attn.value.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.14.attn.value.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.14.ls1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.14.ls2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.14.mlp.hidden_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.14.mlp.hidden_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.14.mlp.output_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.14.mlp.output_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.14.norm1.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.14.norm1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.14.norm2.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.14.norm2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.15.attn.key.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.15.attn.key.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.15.attn.out.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.15.attn.out.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.15.attn.query.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.15.attn.query.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.15.attn.value.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.15.attn.value.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.15.ls1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.15.ls2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.15.mlp.hidden_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.15.mlp.hidden_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.15.mlp.output_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.15.mlp.output_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.15.norm1.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.15.norm1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.15.norm2.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.15.norm2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.16.attn.key.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.16.attn.key.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.16.attn.out.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.16.attn.out.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.16.attn.query.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.16.attn.query.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.16.attn.value.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.16.attn.value.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.16.ls1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.16.ls2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.16.mlp.hidden_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.16.mlp.hidden_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.16.mlp.output_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.16.mlp.output_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.16.norm1.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.16.norm1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.16.norm2.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.16.norm2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.17.attn.key.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.17.attn.key.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.17.attn.out.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.17.attn.out.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.17.attn.query.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.17.attn.query.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.17.attn.value.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.17.attn.value.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.17.ls1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.17.ls2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.17.mlp.hidden_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.17.mlp.hidden_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.17.mlp.output_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.17.mlp.output_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.17.norm1.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.17.norm1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.17.norm2.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.17.norm2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.18.attn.key.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.18.attn.key.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.18.attn.out.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.18.attn.out.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.18.attn.query.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.18.attn.query.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.18.attn.value.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.18.attn.value.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.18.ls1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.18.ls2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.18.mlp.hidden_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.18.mlp.hidden_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.18.mlp.output_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.18.mlp.output_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.18.norm1.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.18.norm1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.18.norm2.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.18.norm2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.19.attn.key.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.19.attn.key.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.19.attn.out.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.19.attn.out.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.19.attn.query.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.19.attn.query.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.19.attn.value.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.19.attn.value.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.19.ls1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.19.ls2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.19.mlp.hidden_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.19.mlp.hidden_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.19.mlp.output_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.19.mlp.output_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.19.norm1.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.19.norm1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.19.norm2.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.19.norm2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.2.attn.key.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.2.attn.key.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.2.attn.out.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.2.attn.out.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.2.attn.query.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.2.attn.query.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.2.attn.value.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.2.attn.value.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.2.ls1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.2.ls2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.2.mlp.hidden_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.2.mlp.hidden_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.2.mlp.output_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.2.mlp.output_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.2.norm1.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.2.norm1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.2.norm2.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.2.norm2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.20.attn.key.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.20.attn.key.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.20.attn.out.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.20.attn.out.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.20.attn.query.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.20.attn.query.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.20.attn.value.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.20.attn.value.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.20.ls1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.20.ls2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.20.mlp.hidden_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.20.mlp.hidden_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.20.mlp.output_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.20.mlp.output_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.20.norm1.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.20.norm1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.20.norm2.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.20.norm2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.21.attn.key.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.21.attn.key.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.21.attn.out.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.21.attn.out.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.21.attn.query.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.21.attn.query.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.21.attn.value.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.21.attn.value.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.21.ls1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.21.ls2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.21.mlp.hidden_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.21.mlp.hidden_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.21.mlp.output_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.21.mlp.output_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.21.norm1.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.21.norm1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.21.norm2.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.21.norm2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.22.attn.key.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.22.attn.key.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.22.attn.out.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.22.attn.out.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.22.attn.query.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.22.attn.query.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.22.attn.value.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.22.attn.value.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.22.ls1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.22.ls2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.22.mlp.hidden_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.22.mlp.hidden_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.22.mlp.output_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.22.mlp.output_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.22.norm1.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.22.norm1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.22.norm2.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.22.norm2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.23.attn.key.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.23.attn.key.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.23.attn.out.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.23.attn.out.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.23.attn.query.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.23.attn.query.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.23.attn.value.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.23.attn.value.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.23.ls1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.23.ls2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.23.mlp.hidden_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.23.mlp.hidden_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.23.mlp.output_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.23.mlp.output_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.23.norm1.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.23.norm1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.23.norm2.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.23.norm2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.24.attn.key.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.24.attn.key.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.24.attn.out.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.24.attn.out.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.24.attn.query.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.24.attn.query.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.24.attn.value.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.24.attn.value.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.24.ls1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.24.ls2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.24.mlp.hidden_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.24.mlp.hidden_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.24.mlp.output_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.24.mlp.output_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.24.norm1.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.24.norm1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.24.norm2.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.24.norm2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.25.attn.key.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.25.attn.key.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.25.attn.out.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.25.attn.out.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.25.attn.query.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.25.attn.query.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.25.attn.value.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.25.attn.value.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.25.ls1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.25.ls2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.25.mlp.hidden_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.25.mlp.hidden_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.25.mlp.output_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.25.mlp.output_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.25.norm1.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.25.norm1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.25.norm2.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.25.norm2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.26.attn.key.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.26.attn.key.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.26.attn.out.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.26.attn.out.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.26.attn.query.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.26.attn.query.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.26.attn.value.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.26.attn.value.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.26.ls1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.26.ls2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.26.mlp.hidden_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.26.mlp.hidden_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.26.mlp.output_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.26.mlp.output_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.26.norm1.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.26.norm1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.26.norm2.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.26.norm2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.27.attn.key.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.27.attn.key.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.27.attn.out.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.27.attn.out.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.27.attn.query.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.27.attn.query.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.27.attn.value.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.27.attn.value.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.27.ls1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.27.ls2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.27.mlp.hidden_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.27.mlp.hidden_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.27.mlp.output_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.27.mlp.output_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.27.norm1.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.27.norm1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.27.norm2.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.27.norm2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.28.attn.key.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.28.attn.key.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.28.attn.out.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.28.attn.out.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.28.attn.query.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.28.attn.query.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.28.attn.value.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.28.attn.value.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.28.ls1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.28.ls2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.28.mlp.hidden_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.28.mlp.hidden_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.28.mlp.output_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.28.mlp.output_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.28.norm1.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.28.norm1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.28.norm2.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.28.norm2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.29.attn.key.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.29.attn.key.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.29.attn.out.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.29.attn.out.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.29.attn.query.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.29.attn.query.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.29.attn.value.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.29.attn.value.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.29.ls1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.29.ls2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.29.mlp.hidden_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.29.mlp.hidden_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.29.mlp.output_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.29.mlp.output_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.29.norm1.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.29.norm1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.29.norm2.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.29.norm2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.3.attn.key.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.3.attn.key.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.3.attn.out.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.3.attn.out.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.3.attn.query.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.3.attn.query.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.3.attn.value.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.3.attn.value.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.3.ls1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.3.ls2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.3.mlp.hidden_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.3.mlp.hidden_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.3.mlp.output_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.3.mlp.output_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.3.norm1.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.3.norm1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.3.norm2.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.3.norm2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.30.attn.key.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.30.attn.key.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.30.attn.out.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.30.attn.out.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.30.attn.query.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.30.attn.query.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.30.attn.value.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.30.attn.value.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.30.ls1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.30.ls2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.30.mlp.hidden_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.30.mlp.hidden_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.30.mlp.output_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.30.mlp.output_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.30.norm1.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.30.norm1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.30.norm2.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.30.norm2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.31.attn.key.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.31.attn.key.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.31.attn.out.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.31.attn.out.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.31.attn.query.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.31.attn.query.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.31.attn.value.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.31.attn.value.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.31.ls1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.31.ls2.weight": "model-00002-of-00002.safetensors", "image_encoder.blocks.31.mlp.hidden_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.31.mlp.hidden_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.31.mlp.output_layer.bias": "model-00002-of-00002.safetensors", "image_encoder.blocks.31.mlp.output_layer.weight": "model-00002-of-00002.safetensors", "image_encoder.blocks.31.norm1.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.31.norm1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.31.norm2.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.31.norm2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.4.attn.key.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.4.attn.key.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.4.attn.out.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.4.attn.out.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.4.attn.query.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.4.attn.query.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.4.attn.value.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.4.attn.value.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.4.ls1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.4.ls2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.4.mlp.hidden_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.4.mlp.hidden_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.4.mlp.output_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.4.mlp.output_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.4.norm1.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.4.norm1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.4.norm2.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.4.norm2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.5.attn.key.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.5.attn.key.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.5.attn.out.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.5.attn.out.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.5.attn.query.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.5.attn.query.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.5.attn.value.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.5.attn.value.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.5.ls1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.5.ls2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.5.mlp.hidden_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.5.mlp.hidden_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.5.mlp.output_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.5.mlp.output_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.5.norm1.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.5.norm1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.5.norm2.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.5.norm2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.6.attn.key.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.6.attn.key.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.6.attn.out.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.6.attn.out.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.6.attn.query.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.6.attn.query.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.6.attn.value.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.6.attn.value.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.6.ls1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.6.ls2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.6.mlp.hidden_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.6.mlp.hidden_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.6.mlp.output_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.6.mlp.output_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.6.norm1.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.6.norm1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.6.norm2.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.6.norm2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.7.attn.key.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.7.attn.key.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.7.attn.out.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.7.attn.out.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.7.attn.query.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.7.attn.query.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.7.attn.value.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.7.attn.value.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.7.ls1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.7.ls2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.7.mlp.hidden_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.7.mlp.hidden_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.7.mlp.output_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.7.mlp.output_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.7.norm1.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.7.norm1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.7.norm2.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.7.norm2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.8.attn.key.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.8.attn.key.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.8.attn.out.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.8.attn.out.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.8.attn.query.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.8.attn.query.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.8.attn.value.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.8.attn.value.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.8.ls1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.8.ls2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.8.mlp.hidden_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.8.mlp.hidden_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.8.mlp.output_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.8.mlp.output_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.8.norm1.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.8.norm1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.8.norm2.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.8.norm2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.9.attn.key.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.9.attn.key.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.9.attn.out.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.9.attn.out.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.9.attn.query.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.9.attn.query.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.9.attn.value.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.9.attn.value.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.9.ls1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.9.ls2.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.9.mlp.hidden_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.9.mlp.hidden_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.9.mlp.output_layer.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.9.mlp.output_layer.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.9.norm1.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.9.norm1.weight": "model-00001-of-00002.safetensors", "image_encoder.blocks.9.norm2.bias": "model-00001-of-00002.safetensors", "image_encoder.blocks.9.norm2.weight": "model-00001-of-00002.safetensors", "image_encoder.cls_token": "model-00001-of-00002.safetensors", "image_encoder.norm.bias": "model-00002-of-00002.safetensors", "image_encoder.norm.weight": "model-00002-of-00002.safetensors", "image_encoder.patch_embed.bias": "model-00001-of-00002.safetensors", "image_encoder.patch_embed.weight": "model-00001-of-00002.safetensors", "image_encoder.pos_embed": "model-00001-of-00002.safetensors", "image_pooler.image_latents": "model-00002-of-00002.safetensors", "image_pooler.pooler.linear1.bias": "model-00002-of-00002.safetensors", "image_pooler.pooler.linear1.weight": "model-00002-of-00002.safetensors", "image_pooler.pooler.linear2.bias": "model-00002-of-00002.safetensors", "image_pooler.pooler.linear2.weight": "model-00002-of-00002.safetensors", "image_pooler.pooler.multihead_attn.in_proj_bias": "model-00002-of-00002.safetensors", "image_pooler.pooler.multihead_attn.in_proj_weight": "model-00002-of-00002.safetensors", "image_pooler.pooler.multihead_attn.out_proj.bias": "model-00002-of-00002.safetensors", "image_pooler.pooler.multihead_attn.out_proj.weight": "model-00002-of-00002.safetensors", "image_pooler.pooler.norm1.bias": "model-00002-of-00002.safetensors", "image_pooler.pooler.norm1.weight": "model-00002-of-00002.safetensors", "image_pooler.pooler.norm2.bias": "model-00002-of-00002.safetensors", "image_pooler.pooler.norm2.weight": "model-00002-of-00002.safetensors", "image_pooler.pooler.norm3.bias": "model-00002-of-00002.safetensors", "image_pooler.pooler.norm3.weight": "model-00002-of-00002.safetensors", "image_pooler.pooler.self_attn.in_proj_bias": "model-00002-of-00002.safetensors", "image_pooler.pooler.self_attn.in_proj_weight": "model-00002-of-00002.safetensors", "image_pooler.pooler.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "image_pooler.pooler.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "image_pooler.projection.bias": "model-00002-of-00002.safetensors", "image_pooler.projection.weight": "model-00002-of-00002.safetensors", "text_decoder.lm_head.weight": "model-00001-of-00002.safetensors", "text_decoder.model.embed_tokens.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "text_decoder.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "text_decoder.model.norm.weight": "model-00001-of-00002.safetensors" } }