emfomy commited on
Commit
73c89dc
β€’
1 Parent(s): 6bb7377

Upload model files.

Browse files
README.md ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ datasets:
12
+ metrics:
13
+ ---
14
+
15
+ # CKIP BERT Base Chinese β€” Word Segmentation
16
+
17
+ ## Contributers
18
+
19
+ * [Mu Yang](https://muyang.pro) at [CKIP](https://ckip.iis.sinica.edu.tw) (Author & Maintainer)
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "directionality": "bidi",
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "B",
13
+ "1": "I"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "B": 0,
19
+ "I": 1
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 12,
25
+ "num_hidden_layers": 12,
26
+ "pad_token_id": 0,
27
+ "pooler_fc_size": 768,
28
+ "pooler_num_attention_heads": 12,
29
+ "pooler_num_fc_layers": 3,
30
+ "pooler_size_per_head": 128,
31
+ "pooler_type": "first_token_transform",
32
+ "type_vocab_size": 2,
33
+ "vocab_size": 21128
34
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25eb8910388cbd395b838d8baef3b274f3b5b692af38323e046e3416ed4b9737
3
+ size 406802935
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": false, "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, "model_max_length": 512, "name_or_path": "bert-base-chinese"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff