Upload 6 files
Browse files- config.json +71 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +14 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/mnt/bingadseuunifiedstorage/v-liziheng/result/xtreme-rlm-t2-target-enlm-fwd-ams0-bert-base-multilingual-cased.2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForRLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"directionality": "bidi",
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"langs": [
|
| 15 |
+
"af",
|
| 16 |
+
"ar",
|
| 17 |
+
"bg",
|
| 18 |
+
"bn",
|
| 19 |
+
"de",
|
| 20 |
+
"el",
|
| 21 |
+
"es",
|
| 22 |
+
"et",
|
| 23 |
+
"eu",
|
| 24 |
+
"fa",
|
| 25 |
+
"fi",
|
| 26 |
+
"fr",
|
| 27 |
+
"he",
|
| 28 |
+
"hi",
|
| 29 |
+
"hu",
|
| 30 |
+
"id",
|
| 31 |
+
"it",
|
| 32 |
+
"ja",
|
| 33 |
+
"jv",
|
| 34 |
+
"ka",
|
| 35 |
+
"kk",
|
| 36 |
+
"ko",
|
| 37 |
+
"ml",
|
| 38 |
+
"mr",
|
| 39 |
+
"nl",
|
| 40 |
+
"pt",
|
| 41 |
+
"ru",
|
| 42 |
+
"sw",
|
| 43 |
+
"ta",
|
| 44 |
+
"te",
|
| 45 |
+
"th",
|
| 46 |
+
"tl",
|
| 47 |
+
"tr",
|
| 48 |
+
"ur",
|
| 49 |
+
"vi",
|
| 50 |
+
"zh"
|
| 51 |
+
],
|
| 52 |
+
"layer_norm_eps": 1e-12,
|
| 53 |
+
"max_position_embeddings": 512,
|
| 54 |
+
"model_type": "bert",
|
| 55 |
+
"n_langs": 38,
|
| 56 |
+
"num_attention_heads": 12,
|
| 57 |
+
"num_hidden_layers": 12,
|
| 58 |
+
"pad_token_id": 0,
|
| 59 |
+
"pooler_fc_size": 768,
|
| 60 |
+
"pooler_num_attention_heads": 12,
|
| 61 |
+
"pooler_num_fc_layers": 3,
|
| 62 |
+
"pooler_size_per_head": 128,
|
| 63 |
+
"pooler_type": "first_token_transform",
|
| 64 |
+
"position_embedding_type": "absolute",
|
| 65 |
+
"torch_dtype": "float32",
|
| 66 |
+
"transformers_version": "4.20.1",
|
| 67 |
+
"type_vocab_size": 2,
|
| 68 |
+
"use_cache": true,
|
| 69 |
+
"use_lang_emb": false,
|
| 70 |
+
"vocab_size": 119547
|
| 71 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0f2a1a886f7a4850bff53d60481351e838a38fd13c37fa37fe17caeddf1f1af
|
| 3 |
+
size 711489335
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"do_lower_case": false,
|
| 4 |
+
"mask_token": "[MASK]",
|
| 5 |
+
"model_max_length": 512,
|
| 6 |
+
"name_or_path": "bert-base-multilingual-cased",
|
| 7 |
+
"pad_token": "[PAD]",
|
| 8 |
+
"sep_token": "[SEP]",
|
| 9 |
+
"special_tokens_map_file": null,
|
| 10 |
+
"strip_accents": null,
|
| 11 |
+
"tokenize_chinese_chars": true,
|
| 12 |
+
"tokenizer_class": "BertTokenizer",
|
| 13 |
+
"unk_token": "[UNK]"
|
| 14 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|