|
{ |
|
"_name_or_path": "/mnt/bingadseuunifiedstorage/v-liziheng/result/xtreme-rlm-t2-target-enlm-fwd-ams0-bert-base-multilingual-cased.2", |
|
"architectures": [ |
|
"BertForRLM" |
|
], |
|
"attention_probs_dropout_prob": 0.1, |
|
"classifier_dropout": null, |
|
"directionality": "bidi", |
|
"hidden_act": "gelu", |
|
"hidden_dropout_prob": 0.1, |
|
"hidden_size": 768, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 3072, |
|
"langs": [ |
|
"af", |
|
"ar", |
|
"bg", |
|
"bn", |
|
"de", |
|
"el", |
|
"es", |
|
"et", |
|
"eu", |
|
"fa", |
|
"fi", |
|
"fr", |
|
"he", |
|
"hi", |
|
"hu", |
|
"id", |
|
"it", |
|
"ja", |
|
"jv", |
|
"ka", |
|
"kk", |
|
"ko", |
|
"ml", |
|
"mr", |
|
"nl", |
|
"pt", |
|
"ru", |
|
"sw", |
|
"ta", |
|
"te", |
|
"th", |
|
"tl", |
|
"tr", |
|
"ur", |
|
"vi", |
|
"zh" |
|
], |
|
"layer_norm_eps": 1e-12, |
|
"max_position_embeddings": 512, |
|
"model_type": "bert", |
|
"n_langs": 38, |
|
"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", |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.20.1", |
|
"type_vocab_size": 2, |
|
"use_cache": true, |
|
"use_lang_emb": false, |
|
"vocab_size": 119547 |
|
} |
|
|