text_classifier / config.json
jagadeesr's picture
jagadeesr/ms-deberta-v3-small-rvl-cdip
6ebfec4
{
"_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": "presentation",
"1": "budget",
"2": "scientific publication",
"3": "letter",
"4": "invoice",
"5": "handwritten",
"6": "email",
"7": "questionnaire",
"8": "memo",
"9": "specification",
"10": "resume",
"11": "file folder",
"12": "form",
"13": "scientific report",
"14": "news article",
"15": "advertisement"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"advertisement": 15,
"budget": 1,
"email": 6,
"file folder": 11,
"form": 12,
"handwritten": 5,
"invoice": 4,
"letter": 3,
"memo": 8,
"news article": 14,
"presentation": 0,
"questionnaire": 7,
"resume": 10,
"scientific publication": 2,
"scientific report": 13,
"specification": 9
},
"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,
"relative_attention": true,
"share_att_key": true,
"torch_dtype": "float32",
"transformers_version": "4.36.0",
"type_vocab_size": 0,
"vocab_size": 128100
}