| { | |
| "_name_or_path": "C:\\Users\\jona-\\Documents\\Jona\\ESCOM\\semestre 9\\TT2\\Trabajo\\Codigo\\modeloLongformerV2\\longformer-base-4096-spanish-finetuned-squad_5_7_trainer6", | |
| "architectures": [ | |
| "RobertaForQuestionAnswering" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "attention_window": [ | |
| 512, | |
| 512, | |
| 512, | |
| 512, | |
| 512, | |
| 512, | |
| 512, | |
| 512, | |
| 512, | |
| 512, | |
| 512, | |
| 512 | |
| ], | |
| "bos_token_id": 0, | |
| "classifier_dropout": null, | |
| "eos_token_id": 2, | |
| "gradient_checkpointing": false, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-05, | |
| "max_position_embeddings": 4098, | |
| "model_type": "roberta", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 1, | |
| "position_embedding_type": "absolute", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.41.0", | |
| "type_vocab_size": 1, | |
| "use_cache": true, | |
| "vocab_size": 50265 | |
| } | |