| { | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "RobertaForSequenceClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "bos_token_id": 0, | |
| "classifier_dropout": null, | |
| "dtype": "float32", | |
| "eos_token_id": 2, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 1024, | |
| "id2label": { | |
| "0": "11", | |
| "1": "21", | |
| "2": "22", | |
| "3": "23", | |
| "4": "31-33", | |
| "5": "42", | |
| "6": "44-45", | |
| "7": "48-49", | |
| "8": "51", | |
| "9": "52", | |
| "10": "53", | |
| "11": "54", | |
| "12": "56", | |
| "13": "61", | |
| "14": "62", | |
| "15": "71", | |
| "16": "72", | |
| "17": "81", | |
| "18": "92" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "is_decoder": false, | |
| "label2id": { | |
| "11": 0, | |
| "21": 1, | |
| "22": 2, | |
| "23": 3, | |
| "31-33": 4, | |
| "42": 5, | |
| "44-45": 6, | |
| "48-49": 7, | |
| "51": 8, | |
| "52": 9, | |
| "53": 10, | |
| "54": 11, | |
| "56": 12, | |
| "61": 13, | |
| "62": 14, | |
| "71": 15, | |
| "72": 16, | |
| "81": 17, | |
| "92": 18 | |
| }, | |
| "layer_norm_eps": 1e-05, | |
| "max_position_embeddings": 514, | |
| "model_type": "roberta", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 24, | |
| "pad_token_id": 1, | |
| "problem_type": "single_label_classification", | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.0.0", | |
| "type_vocab_size": 1, | |
| "use_cache": false, | |
| "vocab_size": 50265 | |
| } | |