|
{ |
|
"_name_or_path": "microsoft/deberta-v3-base", |
|
"architectures": [ |
|
"DebertaV2ForSequenceClassification" |
|
], |
|
"attention_probs_dropout_prob": 0.1, |
|
"hidden_act": "gelu", |
|
"hidden_dropout_prob": 0.1, |
|
"hidden_size": 768, |
|
"id2label": { |
|
"0": "LABEL_0", |
|
"1": "LABEL_1", |
|
"2": "LABEL_2", |
|
"3": "LABEL_3", |
|
"4": "LABEL_4", |
|
"5": "LABEL_5", |
|
"6": "LABEL_6", |
|
"7": "LABEL_7", |
|
"8": "LABEL_8" |
|
}, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 3072, |
|
"label2id": { |
|
"LABEL_0": 0, |
|
"LABEL_1": 1, |
|
"LABEL_2": 2, |
|
"LABEL_3": 3, |
|
"LABEL_4": 4, |
|
"LABEL_5": 5, |
|
"LABEL_6": 6, |
|
"LABEL_7": 7, |
|
"LABEL_8": 8 |
|
}, |
|
"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": "float16", |
|
"transformers_version": "4.28.0.dev0", |
|
"type_vocab_size": 0, |
|
"vocab_size": 128100 |
|
} |
|
|