weiweishi commited on
Commit
07aeb11
1 Parent(s): cceceb1

change file mode

Browse files
.gitattributes CHANGED
@@ -30,10 +30,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
30
  *.zip filter=lfs diff=lfs merge=lfs -text
31
  *.zst filter=lfs diff=lfs merge=lfs -text
32
  *tfevents* filter=lfs diff=lfs merge=lfs -text
33
- config.json filter=lfs diff=lfs merge=lfs -text
34
  pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
35
- special_tokens_map.json filter=lfs diff=lfs merge=lfs -text
36
- tokenizer_config.json filter=lfs diff=lfs merge=lfs -text
37
- vocab.txt filter=lfs diff=lfs merge=lfs -text
38
- word_pronunciation.json filter=lfs diff=lfs merge=lfs -text
39
- word_shape.json filter=lfs diff=lfs merge=lfs -text
 
30
  *.zip filter=lfs diff=lfs merge=lfs -text
31
  *.zst filter=lfs diff=lfs merge=lfs -text
32
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
33
  pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
README.md CHANGED
File without changes
config.json CHANGED
@@ -1,3 +1,39 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e27676e5340a801a9e9a8503fca5d9ec0070cca07ad5555a747232e30079485
3
- size 1070
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "weiweishi/roc-bert-base-zh",
3
+ "architectures": [
4
+ "RoCBertForPreTraining"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "concat_input": true,
9
+ "directionality": "bidi",
10
+ "enable_cls": true,
11
+ "enable_pronunciation": true,
12
+ "enable_shape": true,
13
+ "hidden_act": "gelu",
14
+ "hidden_dropout_prob": 0.1,
15
+ "hidden_size": 768,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "layer_norm_eps": 1e-12,
19
+ "max_position_embeddings": 512,
20
+ "model_type": "roc_bert",
21
+ "num_attention_heads": 12,
22
+ "num_hidden_layers": 12,
23
+ "pad_token_id": 0,
24
+ "pooler_fc_size": 768,
25
+ "pooler_num_attention_heads": 12,
26
+ "pooler_num_fc_layers": 3,
27
+ "pooler_size_per_head": 128,
28
+ "pooler_type": "first_token_transform",
29
+ "position_embedding_type": "absolute",
30
+ "pronunciation_embed_dim": 768,
31
+ "pronunciation_vocab_size": 910,
32
+ "shape_embed_dim": 512,
33
+ "shape_vocab_size": 24858,
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.24.0.dev0",
36
+ "type_vocab_size": 2,
37
+ "use_cache": true,
38
+ "vocab_size": 21128
39
+ }
pytorch_model.bin CHANGED
File without changes
special_tokens_map.json CHANGED
@@ -1,3 +1,7 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6d346be366a7d1d48332dbc9fdf3bf8960b5d879522b7799ddba59e76237ee3
3
- size 125
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer_config.json CHANGED
@@ -1,3 +1,16 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:741610a7422466d1a9d83e290e2fcc32b67d97f656d107702b8cf6798140d5b1
3
- size 412
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "name_or_path": "weiweishi/roc-bert-base-zh",
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "special_tokens_map_file": null,
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "RoCBertTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff
 
word_pronunciation.json CHANGED
The diff for this file is too large to render. See raw diff
 
word_shape.json CHANGED
The diff for this file is too large to render. See raw diff