| { |
| "metadata": { |
| "total_size": 2746797040, |
| "mergekit_version": "0.1.4" |
| }, |
| "weight_map": { |
| "bert.embeddings.LayerNorm.bias": "model-00001-of-00004.safetensors", |
| "bert.embeddings.LayerNorm.weight": "model-00001-of-00004.safetensors", |
| "bert.embeddings.position_embeddings.weight": "model-00001-of-00004.safetensors", |
| "bert.embeddings.position_ids": "model-00001-of-00004.safetensors", |
| "bert.embeddings.token_type_embeddings.weight": "model-00001-of-00004.safetensors", |
| "bert.embeddings.word_embeddings.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.0.attention.output.LayerNorm.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.0.attention.output.LayerNorm.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.0.attention.output.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.0.attention.output.dense.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.0.attention.self.key.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.0.attention.self.key.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.0.attention.self.query.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.0.attention.self.query.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.0.attention.self.value.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.0.attention.self.value.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.0.intermediate.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.0.intermediate.dense.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.0.output.LayerNorm.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.0.output.LayerNorm.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.0.output.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.0.output.dense.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.1.attention.output.LayerNorm.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.1.attention.output.LayerNorm.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.1.attention.output.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.1.attention.output.dense.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.1.attention.self.key.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.1.attention.self.key.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.1.attention.self.query.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.1.attention.self.query.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.1.attention.self.value.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.1.attention.self.value.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.1.intermediate.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.1.intermediate.dense.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.1.output.LayerNorm.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.1.output.LayerNorm.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.1.output.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.1.output.dense.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.10.attention.output.LayerNorm.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.10.attention.output.LayerNorm.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.10.attention.output.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.10.attention.output.dense.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.10.attention.self.key.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.10.attention.self.key.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.10.attention.self.query.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.10.attention.self.query.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.10.attention.self.value.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.10.attention.self.value.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.10.intermediate.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.10.intermediate.dense.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.10.output.LayerNorm.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.10.output.LayerNorm.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.10.output.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.10.output.dense.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.11.attention.output.LayerNorm.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.11.attention.output.LayerNorm.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.11.attention.output.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.11.attention.output.dense.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.11.attention.self.key.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.11.attention.self.key.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.11.attention.self.query.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.11.attention.self.query.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.11.attention.self.value.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.11.attention.self.value.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.11.intermediate.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.11.intermediate.dense.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.11.output.LayerNorm.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.11.output.LayerNorm.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.11.output.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.11.output.dense.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.2.attention.output.LayerNorm.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.2.attention.output.LayerNorm.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.2.attention.output.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.2.attention.output.dense.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.2.attention.self.key.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.2.attention.self.key.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.2.attention.self.query.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.2.attention.self.query.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.2.attention.self.value.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.2.attention.self.value.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.2.intermediate.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.2.intermediate.dense.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.2.output.LayerNorm.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.2.output.LayerNorm.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.2.output.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.2.output.dense.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.3.attention.output.LayerNorm.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.3.attention.output.LayerNorm.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.3.attention.output.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.3.attention.output.dense.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.3.attention.self.key.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.3.attention.self.key.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.3.attention.self.query.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.3.attention.self.query.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.3.attention.self.value.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.3.attention.self.value.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.3.intermediate.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.3.intermediate.dense.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.3.output.LayerNorm.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.3.output.LayerNorm.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.3.output.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.3.output.dense.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.4.attention.output.LayerNorm.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.4.attention.output.LayerNorm.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.4.attention.output.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.4.attention.output.dense.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.4.attention.self.key.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.4.attention.self.key.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.4.attention.self.query.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.4.attention.self.query.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.4.attention.self.value.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.4.attention.self.value.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.4.intermediate.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.4.intermediate.dense.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.4.output.LayerNorm.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.4.output.LayerNorm.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.4.output.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.4.output.dense.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.5.attention.output.LayerNorm.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.5.attention.output.LayerNorm.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.5.attention.output.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.5.attention.output.dense.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.5.attention.self.key.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.5.attention.self.key.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.5.attention.self.query.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.5.attention.self.query.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.5.attention.self.value.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.5.attention.self.value.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.5.intermediate.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.5.intermediate.dense.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.5.output.LayerNorm.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.5.output.LayerNorm.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.5.output.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.5.output.dense.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.6.attention.output.LayerNorm.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.6.attention.output.LayerNorm.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.6.attention.output.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.6.attention.output.dense.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.6.attention.self.key.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.6.attention.self.key.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.6.attention.self.query.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.6.attention.self.query.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.6.attention.self.value.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.6.attention.self.value.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.6.intermediate.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.6.intermediate.dense.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.6.output.LayerNorm.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.6.output.LayerNorm.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.6.output.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.6.output.dense.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.7.attention.output.LayerNorm.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.7.attention.output.LayerNorm.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.7.attention.output.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.7.attention.output.dense.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.7.attention.self.key.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.7.attention.self.key.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.7.attention.self.query.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.7.attention.self.query.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.7.attention.self.value.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.7.attention.self.value.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.7.intermediate.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.7.intermediate.dense.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.7.output.LayerNorm.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.7.output.LayerNorm.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.7.output.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.7.output.dense.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.8.attention.output.LayerNorm.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.8.attention.output.LayerNorm.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.8.attention.output.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.8.attention.output.dense.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.8.attention.self.key.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.8.attention.self.key.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.8.attention.self.query.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.8.attention.self.query.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.8.attention.self.value.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.8.attention.self.value.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.8.intermediate.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.8.intermediate.dense.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.8.output.LayerNorm.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.8.output.LayerNorm.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.8.output.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.8.output.dense.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.9.attention.output.LayerNorm.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.9.attention.output.LayerNorm.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.9.attention.output.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.9.attention.output.dense.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.9.attention.self.key.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.9.attention.self.key.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.9.attention.self.query.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.9.attention.self.query.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.9.attention.self.value.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.9.attention.self.value.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.9.intermediate.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.9.intermediate.dense.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.9.output.LayerNorm.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.9.output.LayerNorm.weight": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.9.output.dense.bias": "model-00001-of-00004.safetensors", |
| "bert.encoder.layer.9.output.dense.weight": "model-00001-of-00004.safetensors", |
| "classifier.bias": "model-00001-of-00004.safetensors", |
| "classifier.dense.bias": "model-00001-of-00004.safetensors", |
| "classifier.dense.weight": "model-00001-of-00004.safetensors", |
| "classifier.out_proj.bias": "model-00001-of-00004.safetensors", |
| "classifier.out_proj.weight": "model-00001-of-00004.safetensors", |
| "classifier.weight": "model-00001-of-00004.safetensors", |
| "cls.predictions.bias": "model-00001-of-00004.safetensors", |
| "cls.predictions.decoder.bias": "model-00001-of-00004.safetensors", |
| "cls.predictions.decoder.weight": "model-00002-of-00004.safetensors", |
| "cls.predictions.transform.LayerNorm.bias": "model-00002-of-00004.safetensors", |
| "cls.predictions.transform.LayerNorm.weight": "model-00002-of-00004.safetensors", |
| "cls.predictions.transform.dense.bias": "model-00002-of-00004.safetensors", |
| "cls.predictions.transform.dense.weight": "model-00002-of-00004.safetensors", |
| "deberta.embeddings.LayerNorm.bias": "model-00002-of-00004.safetensors", |
| "deberta.embeddings.LayerNorm.weight": "model-00002-of-00004.safetensors", |
| "deberta.embeddings.word_embeddings.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.LayerNorm.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.LayerNorm.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.0.attention.output.LayerNorm.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.0.attention.output.LayerNorm.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.0.attention.output.dense.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.0.attention.output.dense.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.0.attention.self.key_proj.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.0.attention.self.key_proj.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.0.attention.self.query_proj.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.0.attention.self.query_proj.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.0.attention.self.value_proj.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.0.attention.self.value_proj.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.0.intermediate.dense.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.0.intermediate.dense.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.0.output.LayerNorm.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.0.output.LayerNorm.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.0.output.dense.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.0.output.dense.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.1.attention.output.LayerNorm.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.1.attention.output.LayerNorm.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.1.attention.output.dense.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.1.attention.output.dense.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.1.attention.self.key_proj.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.1.attention.self.key_proj.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.1.attention.self.query_proj.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.1.attention.self.query_proj.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.1.attention.self.value_proj.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.1.attention.self.value_proj.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.1.intermediate.dense.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.1.intermediate.dense.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.1.output.LayerNorm.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.1.output.LayerNorm.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.1.output.dense.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.1.output.dense.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.10.attention.output.LayerNorm.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.10.attention.output.LayerNorm.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.10.attention.output.dense.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.10.attention.output.dense.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.10.attention.self.key_proj.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.10.attention.self.key_proj.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.10.attention.self.query_proj.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.10.attention.self.query_proj.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.10.attention.self.value_proj.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.10.attention.self.value_proj.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.10.intermediate.dense.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.10.intermediate.dense.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.10.output.LayerNorm.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.10.output.LayerNorm.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.10.output.dense.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.10.output.dense.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.11.attention.output.LayerNorm.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.11.attention.output.LayerNorm.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.11.attention.output.dense.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.11.attention.output.dense.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.11.attention.self.key_proj.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.11.attention.self.key_proj.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.11.attention.self.query_proj.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.11.attention.self.query_proj.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.11.attention.self.value_proj.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.11.attention.self.value_proj.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.11.intermediate.dense.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.11.intermediate.dense.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.11.output.LayerNorm.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.11.output.LayerNorm.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.11.output.dense.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.11.output.dense.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.2.attention.output.LayerNorm.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.2.attention.output.LayerNorm.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.2.attention.output.dense.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.2.attention.output.dense.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.2.attention.self.key_proj.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.2.attention.self.key_proj.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.2.attention.self.query_proj.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.2.attention.self.query_proj.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.2.attention.self.value_proj.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.2.attention.self.value_proj.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.2.intermediate.dense.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.2.intermediate.dense.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.2.output.LayerNorm.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.2.output.LayerNorm.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.2.output.dense.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.2.output.dense.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.3.attention.output.LayerNorm.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.3.attention.output.LayerNorm.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.3.attention.output.dense.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.3.attention.output.dense.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.3.attention.self.key_proj.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.3.attention.self.key_proj.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.3.attention.self.query_proj.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.3.attention.self.query_proj.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.3.attention.self.value_proj.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.3.attention.self.value_proj.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.3.intermediate.dense.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.3.intermediate.dense.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.3.output.LayerNorm.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.3.output.LayerNorm.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.3.output.dense.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.3.output.dense.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.4.attention.output.LayerNorm.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.4.attention.output.LayerNorm.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.4.attention.output.dense.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.4.attention.output.dense.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.4.attention.self.key_proj.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.4.attention.self.key_proj.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.4.attention.self.query_proj.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.4.attention.self.query_proj.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.4.attention.self.value_proj.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.4.attention.self.value_proj.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.4.intermediate.dense.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.4.intermediate.dense.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.4.output.LayerNorm.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.4.output.LayerNorm.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.4.output.dense.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.4.output.dense.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.5.attention.output.LayerNorm.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.5.attention.output.LayerNorm.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.5.attention.output.dense.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.5.attention.output.dense.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.5.attention.self.key_proj.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.5.attention.self.key_proj.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.5.attention.self.query_proj.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.5.attention.self.query_proj.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.5.attention.self.value_proj.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.5.attention.self.value_proj.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.5.intermediate.dense.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.5.intermediate.dense.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.5.output.LayerNorm.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.5.output.LayerNorm.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.5.output.dense.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.5.output.dense.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.6.attention.output.LayerNorm.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.6.attention.output.LayerNorm.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.6.attention.output.dense.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.6.attention.output.dense.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.6.attention.self.key_proj.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.6.attention.self.key_proj.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.6.attention.self.query_proj.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.6.attention.self.query_proj.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.6.attention.self.value_proj.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.6.attention.self.value_proj.weight": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.6.intermediate.dense.bias": "model-00002-of-00004.safetensors", |
| "deberta.encoder.layer.6.intermediate.dense.weight": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.6.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.6.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.6.output.dense.bias": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.6.output.dense.weight": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.7.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.7.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.7.attention.output.dense.bias": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.7.attention.output.dense.weight": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.7.attention.self.key_proj.bias": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.7.attention.self.key_proj.weight": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.7.attention.self.query_proj.bias": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.7.attention.self.query_proj.weight": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.7.attention.self.value_proj.bias": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.7.attention.self.value_proj.weight": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.7.intermediate.dense.bias": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.7.intermediate.dense.weight": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.7.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.7.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.7.output.dense.bias": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.7.output.dense.weight": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.8.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.8.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.8.attention.output.dense.bias": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.8.attention.output.dense.weight": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.8.attention.self.key_proj.bias": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.8.attention.self.key_proj.weight": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.8.attention.self.query_proj.bias": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.8.attention.self.query_proj.weight": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.8.attention.self.value_proj.bias": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.8.attention.self.value_proj.weight": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.8.intermediate.dense.bias": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.8.intermediate.dense.weight": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.8.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.8.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.8.output.dense.bias": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.8.output.dense.weight": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.9.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.9.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.9.attention.output.dense.bias": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.9.attention.output.dense.weight": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.9.attention.self.key_proj.bias": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.9.attention.self.key_proj.weight": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.9.attention.self.query_proj.bias": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.9.attention.self.query_proj.weight": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.9.attention.self.value_proj.bias": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.9.attention.self.value_proj.weight": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.9.intermediate.dense.bias": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.9.intermediate.dense.weight": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.9.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.9.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.9.output.dense.bias": "model-00003-of-00004.safetensors", |
| "deberta.encoder.layer.9.output.dense.weight": "model-00003-of-00004.safetensors", |
| "deberta.encoder.rel_embeddings.weight": "model-00003-of-00004.safetensors", |
| "embeddings.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "embeddings.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "embeddings.position_embeddings.weight": "model-00003-of-00004.safetensors", |
| "embeddings.position_ids": "model-00003-of-00004.safetensors", |
| "embeddings.token_type_embeddings.weight": "model-00003-of-00004.safetensors", |
| "embeddings.word_embeddings.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.0.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.0.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.0.attention.output.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.0.attention.output.dense.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.0.attention.self.key.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.0.attention.self.key.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.0.attention.self.query.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.0.attention.self.query.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.0.attention.self.value.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.0.attention.self.value.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.0.intermediate.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.0.intermediate.dense.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.0.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.0.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.0.output.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.0.output.dense.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.1.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.1.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.1.attention.output.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.1.attention.output.dense.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.1.attention.self.key.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.1.attention.self.key.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.1.attention.self.query.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.1.attention.self.query.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.1.attention.self.value.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.1.attention.self.value.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.1.intermediate.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.1.intermediate.dense.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.1.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.1.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.1.output.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.1.output.dense.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.10.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.10.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.10.attention.output.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.10.attention.output.dense.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.10.attention.self.key.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.10.attention.self.key.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.10.attention.self.query.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.10.attention.self.query.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.10.attention.self.value.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.10.attention.self.value.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.10.intermediate.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.10.intermediate.dense.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.10.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.10.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.10.output.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.10.output.dense.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.11.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.11.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.11.attention.output.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.11.attention.output.dense.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.11.attention.self.key.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.11.attention.self.key.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.11.attention.self.query.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.11.attention.self.query.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.11.attention.self.value.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.11.attention.self.value.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.11.intermediate.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.11.intermediate.dense.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.11.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.11.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.11.output.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.11.output.dense.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.2.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.2.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.2.attention.output.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.2.attention.output.dense.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.2.attention.self.key.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.2.attention.self.key.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.2.attention.self.query.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.2.attention.self.query.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.2.attention.self.value.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.2.attention.self.value.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.2.intermediate.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.2.intermediate.dense.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.2.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.2.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.2.output.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.2.output.dense.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.3.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.3.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.3.attention.output.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.3.attention.output.dense.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.3.attention.self.key.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.3.attention.self.key.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.3.attention.self.query.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.3.attention.self.query.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.3.attention.self.value.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.3.attention.self.value.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.3.intermediate.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.3.intermediate.dense.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.3.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.3.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.3.output.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.3.output.dense.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.4.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.4.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.4.attention.output.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.4.attention.output.dense.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.4.attention.self.key.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.4.attention.self.key.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.4.attention.self.query.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.4.attention.self.query.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.4.attention.self.value.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.4.attention.self.value.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.4.intermediate.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.4.intermediate.dense.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.4.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.4.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.4.output.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.4.output.dense.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.5.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.5.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.5.attention.output.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.5.attention.output.dense.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.5.attention.self.key.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.5.attention.self.key.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.5.attention.self.query.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.5.attention.self.query.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.5.attention.self.value.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.5.attention.self.value.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.5.intermediate.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.5.intermediate.dense.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.5.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.5.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.5.output.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.5.output.dense.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.6.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.6.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.6.attention.output.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.6.attention.output.dense.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.6.attention.self.key.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.6.attention.self.key.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.6.attention.self.query.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.6.attention.self.query.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.6.attention.self.value.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.6.attention.self.value.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.6.intermediate.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.6.intermediate.dense.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.6.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.6.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.6.output.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.6.output.dense.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.7.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.7.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.7.attention.output.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.7.attention.output.dense.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.7.attention.self.key.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.7.attention.self.key.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.7.attention.self.query.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.7.attention.self.query.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.7.attention.self.value.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.7.attention.self.value.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.7.intermediate.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.7.intermediate.dense.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.7.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.7.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.7.output.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.7.output.dense.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.8.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.8.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.8.attention.output.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.8.attention.output.dense.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.8.attention.self.key.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.8.attention.self.key.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.8.attention.self.query.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.8.attention.self.query.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.8.attention.self.value.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.8.attention.self.value.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.8.intermediate.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.8.intermediate.dense.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.8.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.8.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.8.output.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.8.output.dense.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.9.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.9.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.9.attention.output.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.9.attention.output.dense.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.9.attention.self.key.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.9.attention.self.key.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.9.attention.self.query.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.9.attention.self.query.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.9.attention.self.value.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.9.attention.self.value.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.9.intermediate.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.9.intermediate.dense.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.9.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.9.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "encoder.layer.9.output.dense.bias": "model-00003-of-00004.safetensors", |
| "encoder.layer.9.output.dense.weight": "model-00003-of-00004.safetensors", |
| "pooler.dense.bias": "model-00003-of-00004.safetensors", |
| "pooler.dense.weight": "model-00003-of-00004.safetensors", |
| "roberta.embeddings.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "roberta.embeddings.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "roberta.embeddings.position_embeddings.weight": "model-00003-of-00004.safetensors", |
| "roberta.embeddings.token_type_embeddings.weight": "model-00003-of-00004.safetensors", |
| "roberta.embeddings.word_embeddings.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.0.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.0.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.0.attention.output.dense.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.0.attention.output.dense.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.0.attention.self.key.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.0.attention.self.key.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.0.attention.self.query.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.0.attention.self.query.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.0.attention.self.value.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.0.attention.self.value.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.0.intermediate.dense.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.0.intermediate.dense.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.0.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.0.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.0.output.dense.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.0.output.dense.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.1.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.1.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.1.attention.output.dense.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.1.attention.output.dense.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.1.attention.self.key.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.1.attention.self.key.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.1.attention.self.query.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.1.attention.self.query.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.1.attention.self.value.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.1.attention.self.value.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.1.intermediate.dense.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.1.intermediate.dense.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.1.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.1.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.1.output.dense.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.1.output.dense.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.10.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.10.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.10.attention.output.dense.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.10.attention.output.dense.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.10.attention.self.key.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.10.attention.self.key.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.10.attention.self.query.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.10.attention.self.query.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.10.attention.self.value.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.10.attention.self.value.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.10.intermediate.dense.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.10.intermediate.dense.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.10.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.10.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.10.output.dense.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.10.output.dense.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.11.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.11.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.11.attention.output.dense.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.11.attention.output.dense.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.11.attention.self.key.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.11.attention.self.key.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.11.attention.self.query.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.11.attention.self.query.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.11.attention.self.value.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.11.attention.self.value.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.11.intermediate.dense.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.11.intermediate.dense.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.11.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.11.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.11.output.dense.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.11.output.dense.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.2.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.2.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.2.attention.output.dense.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.2.attention.output.dense.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.2.attention.self.key.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.2.attention.self.key.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.2.attention.self.query.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.2.attention.self.query.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.2.attention.self.value.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.2.attention.self.value.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.2.intermediate.dense.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.2.intermediate.dense.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.2.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.2.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.2.output.dense.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.2.output.dense.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.3.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.3.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.3.attention.output.dense.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.3.attention.output.dense.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.3.attention.self.key.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.3.attention.self.key.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.3.attention.self.query.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.3.attention.self.query.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.3.attention.self.value.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.3.attention.self.value.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.3.intermediate.dense.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.3.intermediate.dense.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.3.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.3.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.3.output.dense.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.3.output.dense.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.4.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.4.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.4.attention.output.dense.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.4.attention.output.dense.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.4.attention.self.key.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.4.attention.self.key.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.4.attention.self.query.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.4.attention.self.query.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.4.attention.self.value.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.4.attention.self.value.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.4.intermediate.dense.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.4.intermediate.dense.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.4.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.4.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.4.output.dense.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.4.output.dense.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.5.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.5.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.5.attention.output.dense.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.5.attention.output.dense.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.5.attention.self.key.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.5.attention.self.key.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.5.attention.self.query.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.5.attention.self.query.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.5.attention.self.value.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.5.attention.self.value.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.5.intermediate.dense.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.5.intermediate.dense.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.5.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.5.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.5.output.dense.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.5.output.dense.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.6.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.6.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.6.attention.output.dense.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.6.attention.output.dense.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.6.attention.self.key.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.6.attention.self.key.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.6.attention.self.query.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.6.attention.self.query.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.6.attention.self.value.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.6.attention.self.value.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.6.intermediate.dense.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.6.intermediate.dense.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.6.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.6.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.6.output.dense.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.6.output.dense.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.7.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.7.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.7.attention.output.dense.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.7.attention.output.dense.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.7.attention.self.key.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.7.attention.self.key.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.7.attention.self.query.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.7.attention.self.query.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.7.attention.self.value.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.7.attention.self.value.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.7.intermediate.dense.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.7.intermediate.dense.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.7.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.7.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.7.output.dense.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.7.output.dense.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.8.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.8.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.8.attention.output.dense.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.8.attention.output.dense.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.8.attention.self.key.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.8.attention.self.key.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.8.attention.self.query.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.8.attention.self.query.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.8.attention.self.value.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.8.attention.self.value.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.8.intermediate.dense.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.8.intermediate.dense.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.8.output.LayerNorm.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.8.output.LayerNorm.weight": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.8.output.dense.bias": "model-00003-of-00004.safetensors", |
| "roberta.encoder.layer.8.output.dense.weight": "model-00004-of-00004.safetensors", |
| "roberta.encoder.layer.9.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors", |
| "roberta.encoder.layer.9.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors", |
| "roberta.encoder.layer.9.attention.output.dense.bias": "model-00004-of-00004.safetensors", |
| "roberta.encoder.layer.9.attention.output.dense.weight": "model-00004-of-00004.safetensors", |
| "roberta.encoder.layer.9.attention.self.key.bias": "model-00004-of-00004.safetensors", |
| "roberta.encoder.layer.9.attention.self.key.weight": "model-00004-of-00004.safetensors", |
| "roberta.encoder.layer.9.attention.self.query.bias": "model-00004-of-00004.safetensors", |
| "roberta.encoder.layer.9.attention.self.query.weight": "model-00004-of-00004.safetensors", |
| "roberta.encoder.layer.9.attention.self.value.bias": "model-00004-of-00004.safetensors", |
| "roberta.encoder.layer.9.attention.self.value.weight": "model-00004-of-00004.safetensors", |
| "roberta.encoder.layer.9.intermediate.dense.bias": "model-00004-of-00004.safetensors", |
| "roberta.encoder.layer.9.intermediate.dense.weight": "model-00004-of-00004.safetensors", |
| "roberta.encoder.layer.9.output.LayerNorm.bias": "model-00004-of-00004.safetensors", |
| "roberta.encoder.layer.9.output.LayerNorm.weight": "model-00004-of-00004.safetensors", |
| "roberta.encoder.layer.9.output.dense.bias": "model-00004-of-00004.safetensors", |
| "roberta.encoder.layer.9.output.dense.weight": "model-00004-of-00004.safetensors" |
| } |
| } |
