deberta-v3-base-ner-A / config.json
alexeyak's picture
Training in progress, step 2051
aecadb9
{
"_name_or_path": "microsoft/deberta-v3-base",
"architectures": [
"DebertaV2ForTokenClassification"
],
"attention_probs_dropout_prob": 0.1,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "O",
"1": "B-PER",
"2": "I-PER",
"3": "B-ORG",
"4": "I-ORG",
"5": "B-LOC",
"6": "I-LOC",
"7": "B-ANIM",
"8": "I-ANIM",
"9": "B-BIO",
"10": "I-BIO",
"11": "B-CEL",
"12": "I-CEL",
"13": "B-DIS",
"14": "I-DIS",
"15": "B-EVE",
"16": "I-EVE",
"17": "B-FOOD",
"18": "I-FOOD",
"19": "B-INST",
"20": "I-INST",
"21": "B-MEDIA",
"22": "I-MEDIA",
"23": "B-MYTH",
"24": "I-MYTH",
"25": "B-PLANT",
"26": "I-PLANT",
"27": "B-TIME",
"28": "I-TIME",
"29": "B-VEHI",
"30": "I-VEHI"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"B-ANIM": 7,
"B-BIO": 9,
"B-CEL": 11,
"B-DIS": 13,
"B-EVE": 15,
"B-FOOD": 17,
"B-INST": 19,
"B-LOC": 5,
"B-MEDIA": 21,
"B-MYTH": 23,
"B-ORG": 3,
"B-PER": 1,
"B-PLANT": 25,
"B-TIME": 27,
"B-VEHI": 29,
"I-ANIM": 8,
"I-BIO": 10,
"I-CEL": 12,
"I-DIS": 14,
"I-EVE": 16,
"I-FOOD": 18,
"I-INST": 20,
"I-LOC": 6,
"I-MEDIA": 22,
"I-MYTH": 24,
"I-ORG": 4,
"I-PER": 2,
"I-PLANT": 26,
"I-TIME": 28,
"I-VEHI": 30,
"O": 0
},
"layer_norm_eps": 1e-07,
"max_position_embeddings": 512,
"max_relative_positions": -1,
"model_type": "deberta-v2",
"norm_rel_ebd": "layer_norm",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 0,
"pooler_dropout": 0,
"pooler_hidden_act": "gelu",
"pooler_hidden_size": 768,
"pos_att_type": [
"p2c",
"c2p"
],
"position_biased_input": false,
"position_buckets": 256,
"relative_attention": true,
"share_att_key": true,
"torch_dtype": "float32",
"transformers_version": "4.35.2",
"type_vocab_size": 0,
"vocab_size": 128100
}