| { | |
| "metadata": { | |
| "total_size": 11793268736 | |
| }, | |
| "weight_map": { | |
| "embeddings.cls_token": "model-00001-of-00003.safetensors", | |
| "embeddings.mask_token": "model-00001-of-00003.safetensors", | |
| "embeddings.patch_embeddings.projection.bias": "model-00001-of-00003.safetensors", | |
| "embeddings.patch_embeddings.projection.weight": "model-00001-of-00003.safetensors", | |
| "embeddings.position_embeddings": "model-00001-of-00003.safetensors", | |
| "encoder.layer.0.attention.attention.key.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.0.attention.attention.key.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.0.attention.attention.query.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.0.attention.attention.query.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.0.attention.attention.value.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.0.attention.attention.value.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.0.attention.output.dense.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.0.attention.output.dense.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.0.layer_scale1.lambda1": "model-00001-of-00003.safetensors", | |
| "encoder.layer.0.layer_scale2.lambda1": "model-00001-of-00003.safetensors", | |
| "encoder.layer.0.mlp.weights_in.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.0.mlp.weights_in.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.0.mlp.weights_out.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.0.mlp.weights_out.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.0.norm1.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.0.norm1.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.0.norm2.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.0.norm2.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.1.attention.attention.key.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.1.attention.attention.key.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.1.attention.attention.query.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.1.attention.attention.query.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.1.attention.attention.value.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.1.attention.attention.value.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.1.attention.output.dense.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.1.attention.output.dense.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.1.layer_scale1.lambda1": "model-00001-of-00003.safetensors", | |
| "encoder.layer.1.layer_scale2.lambda1": "model-00001-of-00003.safetensors", | |
| "encoder.layer.1.mlp.weights_in.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.1.mlp.weights_in.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.1.mlp.weights_out.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.1.mlp.weights_out.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.1.norm1.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.1.norm1.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.1.norm2.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.1.norm2.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.10.attention.attention.key.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.10.attention.attention.key.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.10.attention.attention.query.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.10.attention.attention.query.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.10.attention.attention.value.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.10.attention.attention.value.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.10.attention.output.dense.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.10.attention.output.dense.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.10.layer_scale1.lambda1": "model-00001-of-00003.safetensors", | |
| "encoder.layer.10.layer_scale2.lambda1": "model-00001-of-00003.safetensors", | |
| "encoder.layer.10.mlp.weights_in.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.10.mlp.weights_in.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.10.mlp.weights_out.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.10.mlp.weights_out.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.10.norm1.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.10.norm1.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.10.norm2.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.10.norm2.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.11.attention.attention.key.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.11.attention.attention.key.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.11.attention.attention.query.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.11.attention.attention.query.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.11.attention.attention.value.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.11.attention.attention.value.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.11.attention.output.dense.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.11.attention.output.dense.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.11.layer_scale1.lambda1": "model-00002-of-00003.safetensors", | |
| "encoder.layer.11.layer_scale2.lambda1": "model-00002-of-00003.safetensors", | |
| "encoder.layer.11.mlp.weights_in.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.11.mlp.weights_in.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.11.mlp.weights_out.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.11.mlp.weights_out.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.11.norm1.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.11.norm1.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.11.norm2.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.11.norm2.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.12.attention.attention.key.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.12.attention.attention.key.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.12.attention.attention.query.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.12.attention.attention.query.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.12.attention.attention.value.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.12.attention.attention.value.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.12.attention.output.dense.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.12.attention.output.dense.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.12.layer_scale1.lambda1": "model-00002-of-00003.safetensors", | |
| "encoder.layer.12.layer_scale2.lambda1": "model-00002-of-00003.safetensors", | |
| "encoder.layer.12.mlp.weights_in.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.12.mlp.weights_in.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.12.mlp.weights_out.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.12.mlp.weights_out.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.12.norm1.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.12.norm1.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.12.norm2.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.12.norm2.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.13.attention.attention.key.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.13.attention.attention.key.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.13.attention.attention.query.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.13.attention.attention.query.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.13.attention.attention.value.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.13.attention.attention.value.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.13.attention.output.dense.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.13.attention.output.dense.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.13.layer_scale1.lambda1": "model-00002-of-00003.safetensors", | |
| "encoder.layer.13.layer_scale2.lambda1": "model-00002-of-00003.safetensors", | |
| "encoder.layer.13.mlp.weights_in.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.13.mlp.weights_in.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.13.mlp.weights_out.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.13.mlp.weights_out.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.13.norm1.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.13.norm1.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.13.norm2.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.13.norm2.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.14.attention.attention.key.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.14.attention.attention.key.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.14.attention.attention.query.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.14.attention.attention.query.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.14.attention.attention.value.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.14.attention.attention.value.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.14.attention.output.dense.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.14.attention.output.dense.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.14.layer_scale1.lambda1": "model-00002-of-00003.safetensors", | |
| "encoder.layer.14.layer_scale2.lambda1": "model-00002-of-00003.safetensors", | |
| "encoder.layer.14.mlp.weights_in.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.14.mlp.weights_in.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.14.mlp.weights_out.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.14.mlp.weights_out.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.14.norm1.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.14.norm1.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.14.norm2.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.14.norm2.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.15.attention.attention.key.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.15.attention.attention.key.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.15.attention.attention.query.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.15.attention.attention.query.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.15.attention.attention.value.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.15.attention.attention.value.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.15.attention.output.dense.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.15.attention.output.dense.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.15.layer_scale1.lambda1": "model-00002-of-00003.safetensors", | |
| "encoder.layer.15.layer_scale2.lambda1": "model-00002-of-00003.safetensors", | |
| "encoder.layer.15.mlp.weights_in.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.15.mlp.weights_in.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.15.mlp.weights_out.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.15.mlp.weights_out.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.15.norm1.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.15.norm1.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.15.norm2.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.15.norm2.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.16.attention.attention.key.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.16.attention.attention.key.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.16.attention.attention.query.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.16.attention.attention.query.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.16.attention.attention.value.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.16.attention.attention.value.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.16.attention.output.dense.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.16.attention.output.dense.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.16.layer_scale1.lambda1": "model-00002-of-00003.safetensors", | |
| "encoder.layer.16.layer_scale2.lambda1": "model-00002-of-00003.safetensors", | |
| "encoder.layer.16.mlp.weights_in.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.16.mlp.weights_in.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.16.mlp.weights_out.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.16.mlp.weights_out.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.16.norm1.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.16.norm1.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.16.norm2.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.16.norm2.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.17.attention.attention.key.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.17.attention.attention.key.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.17.attention.attention.query.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.17.attention.attention.query.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.17.attention.attention.value.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.17.attention.attention.value.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.17.attention.output.dense.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.17.attention.output.dense.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.17.layer_scale1.lambda1": "model-00002-of-00003.safetensors", | |
| "encoder.layer.17.layer_scale2.lambda1": "model-00002-of-00003.safetensors", | |
| "encoder.layer.17.mlp.weights_in.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.17.mlp.weights_in.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.17.mlp.weights_out.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.17.mlp.weights_out.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.17.norm1.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.17.norm1.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.17.norm2.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.17.norm2.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.18.attention.attention.key.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.18.attention.attention.key.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.18.attention.attention.query.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.18.attention.attention.query.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.18.attention.attention.value.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.18.attention.attention.value.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.18.attention.output.dense.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.18.attention.output.dense.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.18.layer_scale1.lambda1": "model-00002-of-00003.safetensors", | |
| "encoder.layer.18.layer_scale2.lambda1": "model-00002-of-00003.safetensors", | |
| "encoder.layer.18.mlp.weights_in.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.18.mlp.weights_in.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.18.mlp.weights_out.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.18.mlp.weights_out.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.18.norm1.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.18.norm1.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.18.norm2.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.18.norm2.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.19.attention.attention.key.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.19.attention.attention.key.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.19.attention.attention.query.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.19.attention.attention.query.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.19.attention.attention.value.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.19.attention.attention.value.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.19.attention.output.dense.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.19.attention.output.dense.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.19.layer_scale1.lambda1": "model-00002-of-00003.safetensors", | |
| "encoder.layer.19.layer_scale2.lambda1": "model-00002-of-00003.safetensors", | |
| "encoder.layer.19.mlp.weights_in.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.19.mlp.weights_in.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.19.mlp.weights_out.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.19.mlp.weights_out.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.19.norm1.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.19.norm1.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.19.norm2.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.19.norm2.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.2.attention.attention.key.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.2.attention.attention.key.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.2.attention.attention.query.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.2.attention.attention.query.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.2.attention.attention.value.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.2.attention.attention.value.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.2.attention.output.dense.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.2.attention.output.dense.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.2.layer_scale1.lambda1": "model-00001-of-00003.safetensors", | |
| "encoder.layer.2.layer_scale2.lambda1": "model-00001-of-00003.safetensors", | |
| "encoder.layer.2.mlp.weights_in.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.2.mlp.weights_in.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.2.mlp.weights_out.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.2.mlp.weights_out.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.2.norm1.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.2.norm1.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.2.norm2.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.2.norm2.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.20.attention.attention.key.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.20.attention.attention.key.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.20.attention.attention.query.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.20.attention.attention.query.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.20.attention.attention.value.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.20.attention.attention.value.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.20.attention.output.dense.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.20.attention.output.dense.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.20.layer_scale1.lambda1": "model-00002-of-00003.safetensors", | |
| "encoder.layer.20.layer_scale2.lambda1": "model-00002-of-00003.safetensors", | |
| "encoder.layer.20.mlp.weights_in.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.20.mlp.weights_in.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.20.mlp.weights_out.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.20.mlp.weights_out.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.20.norm1.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.20.norm1.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.20.norm2.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.20.norm2.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.21.attention.attention.key.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.21.attention.attention.key.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.21.attention.attention.query.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.21.attention.attention.query.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.21.attention.attention.value.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.21.attention.attention.value.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.21.attention.output.dense.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.21.attention.output.dense.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.21.layer_scale1.lambda1": "model-00002-of-00003.safetensors", | |
| "encoder.layer.21.layer_scale2.lambda1": "model-00002-of-00003.safetensors", | |
| "encoder.layer.21.mlp.weights_in.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.21.mlp.weights_in.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.21.mlp.weights_out.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.21.mlp.weights_out.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.21.norm1.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.21.norm1.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.21.norm2.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.21.norm2.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.22.attention.attention.key.bias": "model-00003-of-00003.safetensors", | |
| "encoder.layer.22.attention.attention.key.weight": "model-00003-of-00003.safetensors", | |
| "encoder.layer.22.attention.attention.query.bias": "model-00003-of-00003.safetensors", | |
| "encoder.layer.22.attention.attention.query.weight": "model-00003-of-00003.safetensors", | |
| "encoder.layer.22.attention.attention.value.bias": "model-00003-of-00003.safetensors", | |
| "encoder.layer.22.attention.attention.value.weight": "model-00003-of-00003.safetensors", | |
| "encoder.layer.22.attention.output.dense.bias": "model-00003-of-00003.safetensors", | |
| "encoder.layer.22.attention.output.dense.weight": "model-00003-of-00003.safetensors", | |
| "encoder.layer.22.layer_scale1.lambda1": "model-00003-of-00003.safetensors", | |
| "encoder.layer.22.layer_scale2.lambda1": "model-00003-of-00003.safetensors", | |
| "encoder.layer.22.mlp.weights_in.bias": "model-00003-of-00003.safetensors", | |
| "encoder.layer.22.mlp.weights_in.weight": "model-00003-of-00003.safetensors", | |
| "encoder.layer.22.mlp.weights_out.bias": "model-00003-of-00003.safetensors", | |
| "encoder.layer.22.mlp.weights_out.weight": "model-00003-of-00003.safetensors", | |
| "encoder.layer.22.norm1.bias": "model-00002-of-00003.safetensors", | |
| "encoder.layer.22.norm1.weight": "model-00002-of-00003.safetensors", | |
| "encoder.layer.22.norm2.bias": "model-00003-of-00003.safetensors", | |
| "encoder.layer.22.norm2.weight": "model-00003-of-00003.safetensors", | |
| "encoder.layer.23.attention.attention.key.bias": "model-00003-of-00003.safetensors", | |
| "encoder.layer.23.attention.attention.key.weight": "model-00003-of-00003.safetensors", | |
| "encoder.layer.23.attention.attention.query.bias": "model-00003-of-00003.safetensors", | |
| "encoder.layer.23.attention.attention.query.weight": "model-00003-of-00003.safetensors", | |
| "encoder.layer.23.attention.attention.value.bias": "model-00003-of-00003.safetensors", | |
| "encoder.layer.23.attention.attention.value.weight": "model-00003-of-00003.safetensors", | |
| "encoder.layer.23.attention.output.dense.bias": "model-00003-of-00003.safetensors", | |
| "encoder.layer.23.attention.output.dense.weight": "model-00003-of-00003.safetensors", | |
| "encoder.layer.23.layer_scale1.lambda1": "model-00003-of-00003.safetensors", | |
| "encoder.layer.23.layer_scale2.lambda1": "model-00003-of-00003.safetensors", | |
| "encoder.layer.23.mlp.weights_in.bias": "model-00003-of-00003.safetensors", | |
| "encoder.layer.23.mlp.weights_in.weight": "model-00003-of-00003.safetensors", | |
| "encoder.layer.23.mlp.weights_out.bias": "model-00003-of-00003.safetensors", | |
| "encoder.layer.23.mlp.weights_out.weight": "model-00003-of-00003.safetensors", | |
| "encoder.layer.23.norm1.bias": "model-00003-of-00003.safetensors", | |
| "encoder.layer.23.norm1.weight": "model-00003-of-00003.safetensors", | |
| "encoder.layer.23.norm2.bias": "model-00003-of-00003.safetensors", | |
| "encoder.layer.23.norm2.weight": "model-00003-of-00003.safetensors", | |
| "encoder.layer.24.attention.attention.key.bias": "model-00003-of-00003.safetensors", | |
| "encoder.layer.24.attention.attention.key.weight": "model-00003-of-00003.safetensors", | |
| "encoder.layer.24.attention.attention.query.bias": "model-00003-of-00003.safetensors", | |
| "encoder.layer.24.attention.attention.query.weight": "model-00003-of-00003.safetensors", | |
| "encoder.layer.24.attention.attention.value.bias": "model-00003-of-00003.safetensors", | |
| "encoder.layer.24.attention.attention.value.weight": "model-00003-of-00003.safetensors", | |
| "encoder.layer.24.attention.output.dense.bias": "model-00003-of-00003.safetensors", | |
| "encoder.layer.24.attention.output.dense.weight": "model-00003-of-00003.safetensors", | |
| "encoder.layer.24.layer_scale1.lambda1": "model-00003-of-00003.safetensors", | |
| "encoder.layer.24.layer_scale2.lambda1": "model-00003-of-00003.safetensors", | |
| "encoder.layer.24.mlp.weights_in.bias": "model-00003-of-00003.safetensors", | |
| "encoder.layer.24.mlp.weights_in.weight": "model-00003-of-00003.safetensors", | |
| "encoder.layer.24.mlp.weights_out.bias": "model-00003-of-00003.safetensors", | |
| "encoder.layer.24.mlp.weights_out.weight": "model-00003-of-00003.safetensors", | |
| "encoder.layer.24.norm1.bias": "model-00003-of-00003.safetensors", | |
| "encoder.layer.24.norm1.weight": "model-00003-of-00003.safetensors", | |
| "encoder.layer.24.norm2.bias": "model-00003-of-00003.safetensors", | |
| "encoder.layer.24.norm2.weight": "model-00003-of-00003.safetensors", | |
| "encoder.layer.25.attention.attention.key.bias": "model-00003-of-00003.safetensors", | |
| "encoder.layer.25.attention.attention.key.weight": "model-00003-of-00003.safetensors", | |
| "encoder.layer.25.attention.attention.query.bias": "model-00003-of-00003.safetensors", | |
| "encoder.layer.25.attention.attention.query.weight": "model-00003-of-00003.safetensors", | |
| "encoder.layer.25.attention.attention.value.bias": "model-00003-of-00003.safetensors", | |
| "encoder.layer.25.attention.attention.value.weight": "model-00003-of-00003.safetensors", | |
| "encoder.layer.25.attention.output.dense.bias": "model-00003-of-00003.safetensors", | |
| "encoder.layer.25.attention.output.dense.weight": "model-00003-of-00003.safetensors", | |
| "encoder.layer.25.layer_scale1.lambda1": "model-00003-of-00003.safetensors", | |
| "encoder.layer.25.layer_scale2.lambda1": "model-00003-of-00003.safetensors", | |
| "encoder.layer.25.mlp.weights_in.bias": "model-00003-of-00003.safetensors", | |
| "encoder.layer.25.mlp.weights_in.weight": "model-00003-of-00003.safetensors", | |
| "encoder.layer.25.mlp.weights_out.bias": "model-00003-of-00003.safetensors", | |
| "encoder.layer.25.mlp.weights_out.weight": "model-00003-of-00003.safetensors", | |
| "encoder.layer.25.norm1.bias": "model-00003-of-00003.safetensors", | |
| "encoder.layer.25.norm1.weight": "model-00003-of-00003.safetensors", | |
| "encoder.layer.25.norm2.bias": "model-00003-of-00003.safetensors", | |
| "encoder.layer.25.norm2.weight": "model-00003-of-00003.safetensors", | |
| "encoder.layer.3.attention.attention.key.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.3.attention.attention.key.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.3.attention.attention.query.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.3.attention.attention.query.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.3.attention.attention.value.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.3.attention.attention.value.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.3.attention.output.dense.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.3.attention.output.dense.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.3.layer_scale1.lambda1": "model-00001-of-00003.safetensors", | |
| "encoder.layer.3.layer_scale2.lambda1": "model-00001-of-00003.safetensors", | |
| "encoder.layer.3.mlp.weights_in.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.3.mlp.weights_in.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.3.mlp.weights_out.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.3.mlp.weights_out.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.3.norm1.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.3.norm1.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.3.norm2.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.3.norm2.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.4.attention.attention.key.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.4.attention.attention.key.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.4.attention.attention.query.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.4.attention.attention.query.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.4.attention.attention.value.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.4.attention.attention.value.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.4.attention.output.dense.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.4.attention.output.dense.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.4.layer_scale1.lambda1": "model-00001-of-00003.safetensors", | |
| "encoder.layer.4.layer_scale2.lambda1": "model-00001-of-00003.safetensors", | |
| "encoder.layer.4.mlp.weights_in.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.4.mlp.weights_in.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.4.mlp.weights_out.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.4.mlp.weights_out.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.4.norm1.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.4.norm1.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.4.norm2.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.4.norm2.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.5.attention.attention.key.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.5.attention.attention.key.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.5.attention.attention.query.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.5.attention.attention.query.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.5.attention.attention.value.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.5.attention.attention.value.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.5.attention.output.dense.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.5.attention.output.dense.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.5.layer_scale1.lambda1": "model-00001-of-00003.safetensors", | |
| "encoder.layer.5.layer_scale2.lambda1": "model-00001-of-00003.safetensors", | |
| "encoder.layer.5.mlp.weights_in.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.5.mlp.weights_in.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.5.mlp.weights_out.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.5.mlp.weights_out.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.5.norm1.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.5.norm1.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.5.norm2.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.5.norm2.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.6.attention.attention.key.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.6.attention.attention.key.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.6.attention.attention.query.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.6.attention.attention.query.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.6.attention.attention.value.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.6.attention.attention.value.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.6.attention.output.dense.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.6.attention.output.dense.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.6.layer_scale1.lambda1": "model-00001-of-00003.safetensors", | |
| "encoder.layer.6.layer_scale2.lambda1": "model-00001-of-00003.safetensors", | |
| "encoder.layer.6.mlp.weights_in.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.6.mlp.weights_in.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.6.mlp.weights_out.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.6.mlp.weights_out.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.6.norm1.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.6.norm1.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.6.norm2.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.6.norm2.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.7.attention.attention.key.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.7.attention.attention.key.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.7.attention.attention.query.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.7.attention.attention.query.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.7.attention.attention.value.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.7.attention.attention.value.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.7.attention.output.dense.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.7.attention.output.dense.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.7.layer_scale1.lambda1": "model-00001-of-00003.safetensors", | |
| "encoder.layer.7.layer_scale2.lambda1": "model-00001-of-00003.safetensors", | |
| "encoder.layer.7.mlp.weights_in.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.7.mlp.weights_in.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.7.mlp.weights_out.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.7.mlp.weights_out.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.7.norm1.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.7.norm1.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.7.norm2.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.7.norm2.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.8.attention.attention.key.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.8.attention.attention.key.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.8.attention.attention.query.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.8.attention.attention.query.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.8.attention.attention.value.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.8.attention.attention.value.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.8.attention.output.dense.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.8.attention.output.dense.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.8.layer_scale1.lambda1": "model-00001-of-00003.safetensors", | |
| "encoder.layer.8.layer_scale2.lambda1": "model-00001-of-00003.safetensors", | |
| "encoder.layer.8.mlp.weights_in.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.8.mlp.weights_in.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.8.mlp.weights_out.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.8.mlp.weights_out.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.8.norm1.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.8.norm1.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.8.norm2.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.8.norm2.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.9.attention.attention.key.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.9.attention.attention.key.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.9.attention.attention.query.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.9.attention.attention.query.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.9.attention.attention.value.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.9.attention.attention.value.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.9.attention.output.dense.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.9.attention.output.dense.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.9.layer_scale1.lambda1": "model-00001-of-00003.safetensors", | |
| "encoder.layer.9.layer_scale2.lambda1": "model-00001-of-00003.safetensors", | |
| "encoder.layer.9.mlp.weights_in.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.9.mlp.weights_in.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.9.mlp.weights_out.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.9.mlp.weights_out.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.9.norm1.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.9.norm1.weight": "model-00001-of-00003.safetensors", | |
| "encoder.layer.9.norm2.bias": "model-00001-of-00003.safetensors", | |
| "encoder.layer.9.norm2.weight": "model-00001-of-00003.safetensors", | |
| "layernorm.bias": "model-00003-of-00003.safetensors", | |
| "layernorm.weight": "model-00003-of-00003.safetensors" | |
| } | |
| } | |