|
{
|
|
"_name_or_path": "bert-base-multilingual-uncased",
|
|
"architectures": [
|
|
"BertForSequenceClassification"
|
|
],
|
|
"attention_probs_dropout_prob": 0.1,
|
|
"classifier_dropout": null,
|
|
"directionality": "bidi",
|
|
"hidden_act": "gelu",
|
|
"hidden_dropout_prob": 0.1,
|
|
"hidden_size": 768,
|
|
"id2label": {
|
|
"0": "LABEL_0"
|
|
},
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 3072,
|
|
"label2id": {
|
|
"LABEL_0": 0
|
|
},
|
|
"layer_norm_eps": 1e-12,
|
|
"max_position_embeddings": 512,
|
|
"model_type": "bert",
|
|
"num_attention_heads": 12,
|
|
"num_hidden_layers": 12,
|
|
"pad_token_id": 0,
|
|
"pooler_fc_size": 768,
|
|
"pooler_num_attention_heads": 12,
|
|
"pooler_num_fc_layers": 3,
|
|
"pooler_size_per_head": 128,
|
|
"pooler_type": "first_token_transform",
|
|
"position_embedding_type": "absolute",
|
|
"problem_type": "regression",
|
|
"torch_dtype": "float32",
|
|
"transformers_version": "4.32.1",
|
|
"type_vocab_size": 2,
|
|
"use_cache": true,
|
|
"vocab_size": 105879
|
|
}
|
|
|