Yuang commited on
Commit
9435a97
1 Parent(s): 8e3a200

Upload 4 files

Browse files
Files changed (4) hide show
  1. config.json +36 -0
  2. special_tokens_map.json +1 -0
  3. tokenizer_config.json +1 -0
  4. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "peterchou/unilm-chinese-base",
3
+ "architectures": [
4
+ "UniLMForConditionalGeneration"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 101,
8
+ "classifier_dropout": null,
9
+ "directionality": "bidi",
10
+ "eos_token_id": 102,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-12,
17
+ "mask_token_id": 103,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "bert",
20
+ "num_attention_heads": 12,
21
+ "num_hidden_layers": 12,
22
+ "pad_token_id": 0,
23
+ "pooler_fc_size": 768,
24
+ "pooler_num_attention_heads": 12,
25
+ "pooler_num_fc_layers": 3,
26
+ "pooler_size_per_head": 128,
27
+ "pooler_type": "first_token_transform",
28
+ "position_embedding_type": "absolute",
29
+ "src_type_id": 4,
30
+ "tgt_type_id": 5,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.18.0",
33
+ "type_vocab_size": 6,
34
+ "use_cache": true,
35
+ "vocab_size": 21128
36
+ }
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "peterchou/unilm-chinese-base", "tokenizer_class": "UniLMTokenizer"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff