Upload model files.
Browse files- README.md +22 -0
- config.json +37 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
- albert
|
9 |
+
- zh
|
10 |
+
license: gpl-3.0
|
11 |
+
datasets:
|
12 |
+
metrics:
|
13 |
+
---
|
14 |
+
|
15 |
+
# CKIP ALBERT Tiny Chinese β Word Segmentation
|
16 |
+
|
17 |
+
## Contributers
|
18 |
+
|
19 |
+
* [Mu Yang](https://muyang.pro) at [CKIP](https://ckip.iis.sinica.edu.tw) (Author & Maintainer)
|
20 |
+
|
21 |
+
## Attention
|
22 |
+
Please Use `BertTokenizer` instead of `AutoTokenizer`!!!
|
config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"AlbertForTokenClassification"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.0,
|
6 |
+
"bos_token_id": 2,
|
7 |
+
"classifier_dropout_prob": 0.1,
|
8 |
+
"down_scale_factor": 1,
|
9 |
+
"embedding_size": 128,
|
10 |
+
"eos_token_id": 3,
|
11 |
+
"gap_size": 0,
|
12 |
+
"hidden_act": "gelu",
|
13 |
+
"hidden_dropout_prob": 0.0,
|
14 |
+
"hidden_size": 312,
|
15 |
+
"id2label": {
|
16 |
+
"0": "B",
|
17 |
+
"1": "I"
|
18 |
+
},
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"inner_group_num": 1,
|
21 |
+
"intermediate_size": 1248,
|
22 |
+
"label2id": {
|
23 |
+
"B": 0,
|
24 |
+
"I": 1
|
25 |
+
},
|
26 |
+
"layer_norm_eps": 1e-12,
|
27 |
+
"max_position_embeddings": 512,
|
28 |
+
"model_type": "albert",
|
29 |
+
"net_structure_type": 0,
|
30 |
+
"num_attention_heads": 12,
|
31 |
+
"num_hidden_groups": 1,
|
32 |
+
"num_hidden_layers": 4,
|
33 |
+
"num_memory_blocks": 0,
|
34 |
+
"pad_token_id": 0,
|
35 |
+
"type_vocab_size": 2,
|
36 |
+
"vocab_size": 21128
|
37 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ededb20956722e26434fcda12b31a1da568e1629228be273cffe53f275b9d94
|
3 |
+
size 15949017
|
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
|
|