ner-deBERTa-v2-x-large / config.json
alphaduriendur's picture
Training in progress, epoch 1
de78ea2
{
"_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-MISC",
"8": "I-MISC"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"B-LOC": 5,
"B-MISC": 7,
"B-ORG": 3,
"B-PER": 1,
"I-LOC": 6,
"I-MISC": 8,
"I-ORG": 4,
"I-PER": 2,
"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": "4.30.2",
"type_vocab_size": 0,
"vocab_size": 128100
}