junnyu commited on
Commit
0935f40
1 Parent(s): 3937866
Files changed (4) hide show
  1. config.json +25 -0
  2. pytorch_model.bin +3 -0
  3. tokenizer_config.json +16 -0
  4. vocab.txt +12000 -0
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RoFormerForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "embedding_size": 768,
7
+ "hidden_act": "relu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 3072,
12
+ "layer_norm_eps": 1e-12,
13
+ "max_position_embeddings": 1536,
14
+ "model_type": "roformer",
15
+ "norm_type": "rms_norm",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "pad_token_id": 0,
19
+ "rotary_value": false,
20
+ "transformers_version": "4.15.0",
21
+ "type_vocab_size": 2,
22
+ "use_bias": false,
23
+ "use_cache": true,
24
+ "vocab_size": 12000
25
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a618b6ddb1af60c30344843500e467bffb8bbf2f58f0533779dcd27e5cefbe7
3
+ size 376635700
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_lower_case": true,
3
+ "do_basic_tokenize": true,
4
+ "never_split": null,
5
+ "unk_token": "[UNK]",
6
+ "sep_token": "[SEP]",
7
+ "pad_token": "[PAD]",
8
+ "cls_token": "[CLS]",
9
+ "mask_token": "[MASK]",
10
+ "tokenize_chinese_chars": true,
11
+ "strip_accents": null,
12
+ "special_tokens_map_file": null,
13
+ "tokenizer_file": null,
14
+ "name_or_path": "junnyu/roformer_v2_chinese_char_base",
15
+ "tokenizer_class": "BertTokenizer"
16
+ }
vocab.txt ADDED
@@ -0,0 +1,12000 @@