cointegrated commited on
Commit
4226f31
1 Parent(s): 5e216f6

The first commit

Browse files

config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cointegrated/rubert-tiny2",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "emb_size": 312,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 312,
13
+ "id2label": {
14
+ "0": "keep",
15
+ "1": "drop"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 600,
19
+ "label2id": {
20
+ "drop": 1,
21
+ "keep": 0
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 2048,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 3,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.19.2",
32
+ "type_vocab_size": 2,
33
+ "use_cache": true,
34
+ "vocab_size": 83828
35
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5e075a4e8bc398eca4af6eca352611edbebe5b93ff068ee7a53e86fbd453bbc
3
+ size 116420477
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.json ADDED
The diff for this file is too large to render. See raw diff
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "do_basic_tokenize": true, "never_split": null, "model_max_length": 2048, "special_tokens_map_file": null, "name_or_path": "cointegrated/rubert-tiny2", "tokenizer_class": "BertTokenizer"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff