ethanyt commited on
Commit
b89b945
1 Parent(s): a063a13
README.md ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - "zh"
4
+ thumbnail: "https://user-images.githubusercontent.com/9592150/97142000-cad08e00-179a-11eb-88df-aff9221482d8.png"
5
+ tags:
6
+ - "chinese"
7
+ - "classical chinese"
8
+ - "literary chinese"
9
+ - "ancient chinese"
10
+ - "bert"
11
+ - "pytorch"
12
+ - "quotation detection"
13
+ license: "apache-2.0"
14
+ pipeline_tag: "token-classification"
15
+ widget:
16
+ - text: "君子之道辟如行远必自迩辟如登高必自卑诗曰妻子好合如鼓瑟琴兄弟既翕和乐且耽宜尔室家乐尔妻帑子曰父母其顺矣乎"
17
+ ---
18
+
19
+ # Guwen Quote
20
+
21
+ A Classical Chinese Quotation Detector.
22
+
23
+ See also:
24
+
25
+ <a href="https://github.com/ethan-yt/guwen-models">
26
+ <img align="center" width="400" src="https://github-readme-stats.vercel.app/api/pin/?username=ethan-yt&repo=guwen-models&bg_color=30,e96443,904e95&title_color=fff&text_color=fff&icon_color=fff&show_owner=true" />
27
+ </a>
28
+ <a href="https://github.com/ethan-yt/cclue/">
29
+ <img align="center" width="400" src="https://github-readme-stats.vercel.app/api/pin/?username=ethan-yt&repo=cclue&bg_color=30,e96443,904e95&title_color=fff&text_color=fff&icon_color=fff&show_owner=true" />
30
+ </a>
31
+ <a href="https://github.com/ethan-yt/guwenbert/">
32
+ <img align="center" width="400" src="https://github-readme-stats.vercel.app/api/pin/?username=ethan-yt&repo=guwenbert&bg_color=30,e96443,904e95&title_color=fff&text_color=fff&icon_color=fff&show_owner=true" />
33
+ </a>
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "output/guwenbert-fs/quote/checkpoint-2000",
3
+ "architectures": [
4
+ "RobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "crf_lr": 0.005,
9
+ "eos_token_id": 2,
10
+ "finetuning_task": "quote",
11
+ "gradient_checkpointing": false,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
+ "id2label": {
16
+ "0": "O",
17
+ "1": "B",
18
+ "2": "I"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "O": 0,
24
+ "B": 1,
25
+ "I": 2
26
+ },
27
+ "layer_norm_eps": 1e-05,
28
+ "max_position_embeddings": 514,
29
+ "model_type": "roberta",
30
+ "num_attention_heads": 12,
31
+ "num_hidden_layers": 12,
32
+ "pad_token_id": 1,
33
+ "position_embedding_type": "absolute",
34
+ "tokenizer_class": "BertTokenizer",
35
+ "transformers_version": "4.5.1",
36
+ "type_vocab_size": 1,
37
+ "use_cache": true,
38
+ "vocab_size": 23292
39
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b194c02c32bcf27aaf69ebf747a74e2d662791e62d2a5625865ed5b76cef09d8
3
+ size 413459154
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": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "use_fast": true, "special_tokens_map_file": "models/guwenbert-base-fs/special_tokens_map.json", "name_or_path": "models/guwenbert-base-fs", "do_basic_tokenize": true, "never_split": null}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff