paper-classifier / src /model /final /config.json
Andrei Pavlov
Paper classifier app and model
e0b0f3b
{
"add_cross_attention": false,
"architectures": [
"BertForSequenceClassification"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": null,
"classifier_dropout": null,
"dtype": "float32",
"eos_token_id": null,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "cmp-lg",
"1": "cs.AI",
"2": "cs.CE",
"3": "cs.CL",
"4": "cs.CR",
"5": "cs.CV",
"6": "cs.CY",
"7": "cs.DB",
"8": "cs.DC",
"9": "cs.DS",
"10": "cs.GT",
"11": "cs.HC",
"12": "cs.IR",
"13": "cs.IT",
"14": "cs.LG",
"15": "cs.LO",
"16": "cs.MM",
"17": "cs.NE",
"18": "cs.RO",
"19": "cs.SD",
"20": "cs.SE",
"21": "cs.SI",
"22": "math.OC",
"23": "q-bio.NC",
"24": "stat.ME",
"25": "stat.ML"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"is_decoder": false,
"label2id": {
"cmp-lg": 0,
"cs.AI": 1,
"cs.CE": 2,
"cs.CL": 3,
"cs.CR": 4,
"cs.CV": 5,
"cs.CY": 6,
"cs.DB": 7,
"cs.DC": 8,
"cs.DS": 9,
"cs.GT": 10,
"cs.HC": 11,
"cs.IR": 12,
"cs.IT": 13,
"cs.LG": 14,
"cs.LO": 15,
"cs.MM": 16,
"cs.NE": 17,
"cs.RO": 18,
"cs.SD": 19,
"cs.SE": 20,
"cs.SI": 21,
"math.OC": 22,
"q-bio.NC": 23,
"stat.ME": 24,
"stat.ML": 25
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 0,
"problem_type": "single_label_classification",
"tie_word_embeddings": true,
"transformers_version": "5.5.0",
"type_vocab_size": 2,
"use_cache": false,
"vocab_size": 31090
}