HillZhang commited on
Commit
2600493
1 Parent(s): 639faa6
.gitattributes CHANGED
@@ -1,34 +1,27 @@
1
  *.7z filter=lfs diff=lfs merge=lfs -text
2
  *.arrow filter=lfs diff=lfs merge=lfs -text
3
  *.bin filter=lfs diff=lfs merge=lfs -text
 
4
  *.bz2 filter=lfs diff=lfs merge=lfs -text
5
- *.ckpt filter=lfs diff=lfs merge=lfs -text
6
  *.ftz filter=lfs diff=lfs merge=lfs -text
7
  *.gz filter=lfs diff=lfs merge=lfs -text
8
  *.h5 filter=lfs diff=lfs merge=lfs -text
9
  *.joblib filter=lfs diff=lfs merge=lfs -text
10
  *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
- *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
  *.model filter=lfs diff=lfs merge=lfs -text
13
  *.msgpack filter=lfs diff=lfs merge=lfs -text
14
- *.npy filter=lfs diff=lfs merge=lfs -text
15
- *.npz filter=lfs diff=lfs merge=lfs -text
16
  *.onnx filter=lfs diff=lfs merge=lfs -text
17
  *.ot filter=lfs diff=lfs merge=lfs -text
18
  *.parquet filter=lfs diff=lfs merge=lfs -text
19
  *.pb filter=lfs diff=lfs merge=lfs -text
20
- *.pickle filter=lfs diff=lfs merge=lfs -text
21
- *.pkl filter=lfs diff=lfs merge=lfs -text
22
  *.pt filter=lfs diff=lfs merge=lfs -text
23
  *.pth filter=lfs diff=lfs merge=lfs -text
24
  *.rar filter=lfs diff=lfs merge=lfs -text
25
- *.safetensors filter=lfs diff=lfs merge=lfs -text
26
- saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
  *.tar.* filter=lfs diff=lfs merge=lfs -text
28
  *.tflite filter=lfs diff=lfs merge=lfs -text
29
  *.tgz filter=lfs diff=lfs merge=lfs -text
30
- *.wasm filter=lfs diff=lfs merge=lfs -text
31
  *.xz filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
- *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
1
  *.7z filter=lfs diff=lfs merge=lfs -text
2
  *.arrow filter=lfs diff=lfs merge=lfs -text
3
  *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bin.* filter=lfs diff=lfs merge=lfs -text
5
  *.bz2 filter=lfs diff=lfs merge=lfs -text
 
6
  *.ftz filter=lfs diff=lfs merge=lfs -text
7
  *.gz filter=lfs diff=lfs merge=lfs -text
8
  *.h5 filter=lfs diff=lfs merge=lfs -text
9
  *.joblib filter=lfs diff=lfs merge=lfs -text
10
  *.lfs.* filter=lfs diff=lfs merge=lfs -text
 
11
  *.model filter=lfs diff=lfs merge=lfs -text
12
  *.msgpack filter=lfs diff=lfs merge=lfs -text
 
 
13
  *.onnx filter=lfs diff=lfs merge=lfs -text
14
  *.ot filter=lfs diff=lfs merge=lfs -text
15
  *.parquet filter=lfs diff=lfs merge=lfs -text
16
  *.pb filter=lfs diff=lfs merge=lfs -text
 
 
17
  *.pt filter=lfs diff=lfs merge=lfs -text
18
  *.pth filter=lfs diff=lfs merge=lfs -text
19
  *.rar filter=lfs diff=lfs merge=lfs -text
20
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 
21
  *.tar.* filter=lfs diff=lfs merge=lfs -text
22
  *.tflite filter=lfs diff=lfs merge=lfs -text
23
  *.tgz filter=lfs diff=lfs merge=lfs -text
 
24
  *.xz filter=lfs diff=lfs merge=lfs -text
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
+ *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,3 +1,46 @@
1
  ---
 
 
 
 
 
 
2
  license: apache-2.0
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ tags:
3
+ - text2text-generation
4
+ - Chinese
5
+ - seq2seq
6
+ - grammar
7
+ language: zh
8
  license: apache-2.0
9
  ---
10
+ # Pseudo-Native-BART-CGEC
11
+
12
+ This model is a cutting-edge CGEC model based on [Chinese BART-large](https://huggingface.co/fnlp/bart-large-chinese).
13
+ It is trained with HSK and Lang8 learner CGEC data (about 1.3M) and human-annotated training data for the exam domain.
14
+ More details can be found in our [Github](https://github.com/HillZhang1999/NaSGEC) and the [paper]().
15
+
16
+ ## Usage
17
+
18
+ pip install transformers
19
+
20
+ ```
21
+ from transformers import BertTokenizer, BartForConditionalGeneration, Text2TextGenerationPipeline
22
+ tokenizer = BertTokenizer.from_pretrained("HillZhang/real_learner_bart_CGEC_exam")
23
+ model = BartForConditionalGeneration.from_pretrained("HillZhang/real_learner_bart_CGEC_exam")
24
+ encoded_input = tokenizer(["北京是中国的都。", "他说:”我最爱的运动是打蓝球“", "我每天大约喝5次水左右。", "今天,我非常开开心。"], return_tensors="pt", padding=True, truncation=True)
25
+ if "token_type_ids" in encoded_input:
26
+ del encoded_input["token_type_ids"]
27
+ output = model.generate(**encoded_input)
28
+ print(tokenizer.batch_decode(output, skip_special_tokens=True))
29
+ ```
30
+
31
+ ## Citation
32
+
33
+ ```
34
+ @inproceedings{zhang-etal-2023-nasgec,
35
+ title = "{Na}{SGEC}: a Multi-Domain Chinese Grammatical Error Correction Dataset from Native Speaker Texts",
36
+ author = "Zhang, Yue and
37
+ Zhang, Bo and
38
+ Jiang, Haochen and
39
+ Li, Zhenghua and
40
+ Li, Chen and
41
+ Huang, Fei and
42
+ Zhang, Min"
43
+ booktitle = "Findings of ACL",
44
+ year = "2023"
45
+ }
46
+ ```
config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.1,
3
+ "activation_function": "gelu",
4
+ "add_bias_logits": false,
5
+ "add_final_layer_norm": false,
6
+ "architectures": [
7
+ "BartForConditionalGeneration"
8
+ ],
9
+ "attention_dropout": 0.1,
10
+ "bos_token_id": 0,
11
+ "unk_token_id": 3,
12
+ "classif_dropout": 0.1,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 1024,
15
+ "decoder_attention_heads": 16,
16
+ "decoder_ffn_dim": 4096,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 12,
19
+ "decoder_start_token_id": 2,
20
+ "do_blenderbot_90_layernorm": false,
21
+ "dropout": 0.1,
22
+ "early_stopping": true,
23
+ "encoder_attention_heads": 16,
24
+ "encoder_ffn_dim": 4096,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 12,
27
+ "eos_token_id": 2,
28
+ "extra_pos_embeddings": 2,
29
+ "force_bos_token_to_be_generated": true,
30
+ "forced_bos_token_id": 0,
31
+ "forced_eos_token_id": 2,
32
+ "gradient_checkpointing": false,
33
+ "id2label": {
34
+ "0": "LABEL_0",
35
+ "1": "LABEL_1",
36
+ "2": "LABEL_2"
37
+ },
38
+ "init_std": 0.02,
39
+ "is_encoder_decoder": true,
40
+ "label2id": {
41
+ "LABEL_0": 0,
42
+ "LABEL_1": 1,
43
+ "LABEL_2": 2
44
+ },
45
+ "max_position_embeddings": 512,
46
+ "model_type": "bart",
47
+ "no_repeat_ngram_size": 3,
48
+ "normalize_before": false,
49
+ "normalize_embedding": true,
50
+ "num_beams": 4,
51
+ "num_hidden_layers": 12,
52
+ "pad_token_id": 1,
53
+ "scale_embedding": false,
54
+ "static_position_embeddings": false,
55
+ "task_specific_params": {
56
+ "summarization": {
57
+ "length_penalty": 1.0,
58
+ "max_length": 128,
59
+ "min_length": 12,
60
+ "num_beams": 4
61
+ },
62
+ "summarization_cnn": {
63
+ "length_penalty": 2.0,
64
+ "max_length": 142,
65
+ "min_length": 56,
66
+ "num_beams": 4
67
+ },
68
+ "summarization_xsum": {
69
+ "length_penalty": 1.0,
70
+ "max_length": 62,
71
+ "min_length": 11,
72
+ "num_beams": 6
73
+ }
74
+ },
75
+ "transformers_version": "4.4.1",
76
+ "use_cache": true,
77
+ "vocab_size": 21132
78
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f241747cf149b5ea32d04c8b91765a8484eba1021f7542d803d5d27b96187f45
3
+ size 1501922415
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "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, "bos_token": "<s>", "eos_token": "</s>"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff