DeBERTaV3_model_V2 / config.json
sergiomvazq's picture
End of training
bee8271 verified
{
"_name_or_path": "microsoft/deberta-v3-small",
"architectures": [
"DebertaV2ForSequenceClassification"
],
"attention_probs_dropout_prob": 0.1,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "N/D",
"1": "staff",
"2": "clothes",
"3": "shop",
"4": "cash desk",
"5": "fitting rooms",
"6": "queue",
"7": "others"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"N/D": 0,
"cash desk": 4,
"clothes": 2,
"fitting rooms": 5,
"others": 7,
"queue": 6,
"shop": 3,
"staff": 1
},
"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": 6,
"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,
"problem_type": "multi_label_classification",
"relative_attention": true,
"share_att_key": true,
"torch_dtype": "float32",
"transformers_version": "4.41.2",
"type_vocab_size": 0,
"vocab_size": 128100
}