ltuzova/citation_intent_classification_roberta_dapt

1{2  "_name_or_path": "ltuzova/cs_domain_pretrained_model",3  "architectures": [4    "RobertaForSequenceClassification"5  ],6  "attention_probs_dropout_prob": 0.1,7  "bos_token_id": 0,8  "classifier_dropout": 0.1,9  "eos_token_id": 2,10  "hidden_act": "gelu",11  "hidden_dropout_prob": 0.1,12  "hidden_size": 768,13  "id2label": {14    "0": "Background",15    "1": "CompareOrContrast",16    "2": "Uses",17    "3": "Motivation",18    "4": "Future",19    "5": "Extends"20  },21  "initializer_range": 0.02,22  "intermediate_size": 3072,23  "label2id": {24    "Background": 0,25    "CompareOrContrast": 1,26    "Extends": 5,27    "Future": 4,28    "Motivation": 3,29    "Uses": 230  },31  "layer_norm_eps": 1e-05,32  "max_position_embeddings": 514,33  "model_type": "roberta",34  "num_attention_heads": 12,35  "num_hidden_layers": 12,36  "num_of_labels": 6,37  "pad_token_id": 1,38  "position_embedding_type": "absolute",39  "problem_type": "single_label_classification",40  "torch_dtype": "float32",41  "transformers_version": "4.30.2",42  "type_vocab_size": 1,43  "use_cache": true,44  "vocab_size": 5026545}46