ctlin commited on
Commit
7aad767
β€’
1 Parent(s): b3d3c7e

upload model files

Browse files
README.md CHANGED
@@ -1,3 +1,18 @@
1
  ---
 
 
 
 
 
 
 
 
2
  license: gpl-3.0
3
  ---
 
 
 
 
 
 
 
 
1
  ---
2
+ language:
3
+ - zh
4
+ thumbnail: https://ckip.iis.sinica.edu.tw/files/ckip_logo.png
5
+ tags:
6
+ - pytorch
7
+ - token-classification
8
+ - bert
9
+ - zh
10
  license: gpl-3.0
11
  ---
12
+
13
+ # CKIP BERT Base Han Chinese WS
14
+
15
+ This model provides word segmentation for the ancient Chinese language. Our training dataset covers four eras of the Chinese language.
16
+
17
+ ## Homepage
18
+ * [ckiplab/han-transformers](https://github.com/ckiplab/han-transformers)
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "hub/ckiplab/bert-base-chinese-20210817-001848",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "directionality": "bidi",
8
+ "finetuning_task": "ner",
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "label2id": {
14
+ "B": 0,
15
+ "I": 1
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "id2label": {
20
+ "0": "B",
21
+ "1": "I"
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "pooler_fc_size": 768,
30
+ "pooler_num_attention_heads": 12,
31
+ "pooler_num_fc_layers": 3,
32
+ "pooler_size_per_head": 128,
33
+ "pooler_type": "first_token_transform",
34
+ "position_embedding_type": "absolute",
35
+ "tokenizer_class": "BertTokenizerFast",
36
+ "transformers_version": "4.7.0",
37
+ "type_vocab_size": 2,
38
+ "use_cache": true,
39
+ "vocab_size": 26140
40
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc2960f793b6ab50c16cf241de8735537c4024251513f38c56b0125eb38bd78f
3
+ size 422194673
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": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "name_or_path": "hub/ckiplab/bert-base-chinese-20210817-001848", "special_tokens_map_file": "/home/cindy666/.cache/huggingface/transformers/d8a1a1b7a3de221ae53bf9d55154b9df9c4cda18409b393ee0fda4bce4ca7818.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "do_basic_tokenize": true, "never_split": null}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff