40 lines
863 B
JSON
40 lines
863 B
JSON
|
{
|
||
|
|
"_name_or_path": "distilbert-base-uncased",
|
||
|
|
"activation": "gelu",
|
||
|
|
"architectures": [
|
||
|
|
"DistilBertForSequenceClassification"
|
||
|
|
],
|
||
|
|
"attention_dropout": 0.1,
|
||
|
|
"dim": 768,
|
||
|
|
"dropout": 0.1,
|
||
|
|
"hidden_dim": 3072,
|
||
|
|
"id2label": {
|
||
|
|
"0": "QA",
|
||
|
|
"1": "CHITCHAT",
|
||
|
|
"2": "FINDPAPER",
|
||
|
|
"3": "FINDDATASET",
|
||
|
|
"4": "SUMMARIZEPAPER"
|
||
|
|
},
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"label2id": {
|
||
|
|
"CHITCHAT": 1,
|
||
|
|
"FINDDATASET": 3,
|
||
|
|
"FINDPAPER": 2,
|
||
|
|
"QA": 0,
|
||
|
|
"SUMMARIZEPAPER": 4
|
||
|
|
},
|
||
|
|
"max_position_embeddings": 512,
|
||
|
|
"model_type": "distilbert",
|
||
|
|
"n_heads": 12,
|
||
|
|
"n_layers": 6,
|
||
|
|
"pad_token_id": 0,
|
||
|
|
"problem_type": "single_label_classification",
|
||
|
|
"qa_dropout": 0.1,
|
||
|
|
"seq_classif_dropout": 0.2,
|
||
|
|
"sinusoidal_pos_embds": false,
|
||
|
|
"tie_weights_": true,
|
||
|
|
"torch_dtype": "float32",
|
||
|
|
"transformers_version": "4.26.1",
|
||
|
|
"vocab_size": 30522
|
||
|
|
}
|