s-nlp/Mutual_Implication_Score

1{2  "_name_or_path": "/home/babakov/TST_res/MIS/MIS_final",3  "architectures": [4    "RobertaForSequenceClassification_all_in_one_local"5  ],6  "attention_probs_dropout_prob": 0.1,7  "bos_token_id": 0,8  "classifier_dropout": null,9  "eos_token_id": 2,10  "gradient_checkpointing": false,11  "hidden_act": "gelu",12  "hidden_dropout_prob": 0.1,13  "hidden_size": 1024,14  "id2label": {15    "0": "entailment",16    "1": "neutral",17    "2": "contradiction"18  },19  "initializer_range": 0.02,20  "intermediate_size": 4096,21  "label2id": {22    "contradiction": 2,23    "entailment": 0,24    "neutral": 125  },26  "layer_norm_eps": 1e-05,27  "max_position_embeddings": 514,28  "model_type": "roberta",29  "num_attention_heads": 16,30  "num_hidden_layers": 24,31  "pad_token_id": 1,32  "position_embedding_type": "absolute",33  "torch_dtype": "float32",34  "transformers_version": "4.18.0",35  "type_vocab_size": 1,36  "use_cache": true,37  "vocab_size": 5026538}39