| { | |
| "metadata": { | |
| "total_size": 737697804 | |
| }, | |
| "weight_map": { | |
| "classifier.bias": "model-00002-of-00002.safetensors", | |
| "classifier.weight": "model-00002-of-00002.safetensors", | |
| "deberta.embeddings.LayerNorm.bias": "model-00001-of-00002.safetensors", | |
| "deberta.embeddings.LayerNorm.weight": "model-00001-of-00002.safetensors", | |
| "deberta.embeddings.word_embeddings.weight": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.LayerNorm.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.LayerNorm.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.0.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.0.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.0.attention.output.dense.bias": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.0.attention.output.dense.weight": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.0.attention.self.key_proj.bias": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.0.attention.self.key_proj.weight": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.0.attention.self.query_proj.bias": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.0.attention.self.query_proj.weight": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.0.attention.self.value_proj.bias": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.0.attention.self.value_proj.weight": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.0.intermediate.dense.bias": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.0.intermediate.dense.weight": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.0.output.LayerNorm.bias": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.0.output.LayerNorm.weight": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.0.output.dense.bias": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.0.output.dense.weight": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.1.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.1.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.1.attention.output.dense.bias": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.1.attention.output.dense.weight": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.1.attention.self.key_proj.bias": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.1.attention.self.key_proj.weight": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.1.attention.self.query_proj.bias": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.1.attention.self.query_proj.weight": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.1.attention.self.value_proj.bias": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.1.attention.self.value_proj.weight": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.1.intermediate.dense.bias": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.1.intermediate.dense.weight": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.1.output.LayerNorm.bias": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.1.output.LayerNorm.weight": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.1.output.dense.bias": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.1.output.dense.weight": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.10.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.10.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.10.attention.output.dense.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.10.attention.output.dense.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.10.attention.self.key_proj.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.10.attention.self.key_proj.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.10.attention.self.query_proj.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.10.attention.self.query_proj.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.10.attention.self.value_proj.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.10.attention.self.value_proj.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.10.intermediate.dense.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.10.intermediate.dense.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.10.output.LayerNorm.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.10.output.LayerNorm.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.10.output.dense.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.10.output.dense.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.11.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.11.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.11.attention.output.dense.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.11.attention.output.dense.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.11.attention.self.key_proj.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.11.attention.self.key_proj.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.11.attention.self.query_proj.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.11.attention.self.query_proj.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.11.attention.self.value_proj.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.11.attention.self.value_proj.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.11.intermediate.dense.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.11.intermediate.dense.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.11.output.LayerNorm.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.11.output.LayerNorm.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.11.output.dense.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.11.output.dense.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.2.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.2.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.2.attention.output.dense.bias": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.2.attention.output.dense.weight": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.2.attention.self.key_proj.bias": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.2.attention.self.key_proj.weight": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.2.attention.self.query_proj.bias": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.2.attention.self.query_proj.weight": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.2.attention.self.value_proj.bias": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.2.attention.self.value_proj.weight": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.2.intermediate.dense.bias": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.2.intermediate.dense.weight": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.2.output.LayerNorm.bias": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.2.output.LayerNorm.weight": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.2.output.dense.bias": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.2.output.dense.weight": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.3.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.3.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.3.attention.output.dense.bias": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.3.attention.output.dense.weight": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.3.attention.self.key_proj.bias": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.3.attention.self.key_proj.weight": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.3.attention.self.query_proj.bias": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.3.attention.self.query_proj.weight": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.3.attention.self.value_proj.bias": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.3.attention.self.value_proj.weight": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.3.intermediate.dense.bias": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.3.intermediate.dense.weight": "model-00001-of-00002.safetensors", | |
| "deberta.encoder.layer.3.output.LayerNorm.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.3.output.LayerNorm.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.3.output.dense.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.3.output.dense.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.4.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.4.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.4.attention.output.dense.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.4.attention.output.dense.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.4.attention.self.key_proj.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.4.attention.self.key_proj.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.4.attention.self.query_proj.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.4.attention.self.query_proj.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.4.attention.self.value_proj.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.4.attention.self.value_proj.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.4.intermediate.dense.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.4.intermediate.dense.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.4.output.LayerNorm.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.4.output.LayerNorm.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.4.output.dense.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.4.output.dense.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.5.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.5.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.5.attention.output.dense.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.5.attention.output.dense.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.5.attention.self.key_proj.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.5.attention.self.key_proj.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.5.attention.self.query_proj.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.5.attention.self.query_proj.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.5.attention.self.value_proj.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.5.attention.self.value_proj.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.5.intermediate.dense.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.5.intermediate.dense.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.5.output.LayerNorm.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.5.output.LayerNorm.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.5.output.dense.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.5.output.dense.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.6.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.6.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.6.attention.output.dense.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.6.attention.output.dense.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.6.attention.self.key_proj.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.6.attention.self.key_proj.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.6.attention.self.query_proj.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.6.attention.self.query_proj.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.6.attention.self.value_proj.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.6.attention.self.value_proj.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.6.intermediate.dense.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.6.intermediate.dense.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.6.output.LayerNorm.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.6.output.LayerNorm.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.6.output.dense.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.6.output.dense.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.7.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.7.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.7.attention.output.dense.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.7.attention.output.dense.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.7.attention.self.key_proj.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.7.attention.self.key_proj.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.7.attention.self.query_proj.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.7.attention.self.query_proj.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.7.attention.self.value_proj.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.7.attention.self.value_proj.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.7.intermediate.dense.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.7.intermediate.dense.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.7.output.LayerNorm.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.7.output.LayerNorm.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.7.output.dense.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.7.output.dense.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.8.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.8.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.8.attention.output.dense.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.8.attention.output.dense.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.8.attention.self.key_proj.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.8.attention.self.key_proj.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.8.attention.self.query_proj.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.8.attention.self.query_proj.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.8.attention.self.value_proj.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.8.attention.self.value_proj.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.8.intermediate.dense.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.8.intermediate.dense.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.8.output.LayerNorm.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.8.output.LayerNorm.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.8.output.dense.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.8.output.dense.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.9.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.9.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.9.attention.output.dense.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.9.attention.output.dense.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.9.attention.self.key_proj.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.9.attention.self.key_proj.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.9.attention.self.query_proj.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.9.attention.self.query_proj.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.9.attention.self.value_proj.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.9.attention.self.value_proj.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.9.intermediate.dense.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.9.intermediate.dense.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.9.output.LayerNorm.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.9.output.LayerNorm.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.9.output.dense.bias": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.layer.9.output.dense.weight": "model-00002-of-00002.safetensors", | |
| "deberta.encoder.rel_embeddings.weight": "model-00002-of-00002.safetensors", | |
| "pooler.dense.bias": "model-00002-of-00002.safetensors", | |
| "pooler.dense.weight": "model-00002-of-00002.safetensors" | |
| } | |
| } | |