{ | |
"architectures": [ | |
"RobertaForSequenceClassification" | |
], | |
"attention_probs_dropout_prob": 0.1, | |
"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, | |
"id2label": { | |
"0": "1025", | |
"1": "1071", | |
"2": "131", | |
"3": "138", | |
"4": "284", | |
"5": "285", | |
"6": "435", | |
"7": "436", | |
"8": "595", | |
"9": "657", | |
"10": "664", | |
"11": "682", | |
"12": "684", | |
"13": "691", | |
"14": "693", | |
"15": "697", | |
"16": "703", | |
"17": "706", | |
"18": "707", | |
"19": "710", | |
"20": "74", | |
"21": "754", | |
"22": "829", | |
"23": "862", | |
"24": "913", | |
"25": "94" | |
}, | |
"initializer_range": 0.02, | |
"intermediate_size": 3072, | |
"label2id": { | |
"1025": 0, | |
"1071": 1, | |
"131": 2, | |
"138": 3, | |
"284": 4, | |
"285": 5, | |
"435": 6, | |
"436": 7, | |
"595": 8, | |
"657": 9, | |
"664": 10, | |
"682": 11, | |
"684": 12, | |
"691": 13, | |
"693": 14, | |
"697": 15, | |
"703": 16, | |
"706": 17, | |
"707": 18, | |
"710": 19, | |
"74": 20, | |
"754": 21, | |
"829": 22, | |
"862": 23, | |
"913": 24, | |
"94": 25 | |
}, | |
"layer_norm_eps": 1e-05, | |
"max_position_embeddings": 514, | |
"model_type": "roberta", | |
"num_attention_heads": 12, | |
"num_hidden_layers": 12, | |
"output_past": true, | |
"pad_token_id": 1, | |
"position_embedding_type": "absolute", | |
"problem_type": "single_label_classification", | |
"torch_dtype": "float32", | |
"transformers_version": "4.55.4", | |
"type_vocab_size": 1, | |
"use_cache": true, | |
"vocab_size": 50265 | |
} | |