nhanv
commited on
Commit
•
305796a
1
Parent(s):
e6b460d
upload model
Browse files- README.md +87 -0
- config.json +39 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
- vocab.txt +0 -0
README.md
CHANGED
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
metrics:
|
5 |
+
- precision
|
6 |
+
- recall
|
7 |
+
- f1
|
8 |
+
- accuracy
|
9 |
+
model-index:
|
10 |
+
- name: vi-word-segmentation
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# vi-word-segmentation
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [NlpHUST/electra-base-vn](https://huggingface.co/NlpHUST/electra-base-vn) on an vlsp 2013 word segmentation dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.0501
|
22 |
+
- Precision: 0.9833
|
23 |
+
- Recall: 0.9838
|
24 |
+
- F1: 0.9835
|
25 |
+
- Accuracy: 0.9911
|
26 |
+
|
27 |
+
## Model description
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Intended uses & limitations
|
32 |
+
|
33 |
+
You can use this model with Transformers *pipeline* for NER.
|
34 |
+
|
35 |
+
```python
|
36 |
+
from transformers import AutoTokenizer, AutoModelForTokenClassification
|
37 |
+
from transformers import pipeline
|
38 |
+
|
39 |
+
tokenizer = AutoTokenizer.from_pretrained("NlpHUST/vi-word-segmentation")
|
40 |
+
model = AutoModelForTokenClassification.from_pretrained("NlpHUST/vi-word-segmentation")
|
41 |
+
|
42 |
+
nlp = pipeline("ner", model=model, tokenizer=tokenizer)
|
43 |
+
example = "Phát biểu tại phiên thảo luận về tình hình kinh tế xã hội của Quốc hội sáng 28/10 , Bộ trưởng Bộ LĐ-TB&XH Đào Ngọc Dung khái quát , tại phiên khai mạc kỳ họp , lãnh đạo chính phủ đã báo cáo , đề cập tương đối rõ ràng về việc thực hiện các chính sách an sinh xã hội"
|
44 |
+
|
45 |
+
ner_results = nlp(example)
|
46 |
+
print(ner_results)
|
47 |
+
|
48 |
+
Phát_biểu tại phiên thảo_luận về tình_hình kinh_tế xã_hội của Quốc_hội sáng 28 / 10 , Bộ_trưởng Bộ LĐ - TB [UNK] XH Đào_Ngọc_Dung khái_quát , tại phiên khai_mạc kỳ họp , lãnh_đạo chính_phủ đã báo_cáo , đề_cập tương_đối rõ_ràng về việc thực_hiện các chính_sách an_sinh xã_hội
|
49 |
+
|
50 |
+
```
|
51 |
+
|
52 |
+
## Training and evaluation data
|
53 |
+
|
54 |
+
More information needed
|
55 |
+
|
56 |
+
## Training procedure
|
57 |
+
|
58 |
+
### Training hyperparameters
|
59 |
+
|
60 |
+
The following hyperparameters were used during training:
|
61 |
+
- learning_rate: 5e-05
|
62 |
+
- train_batch_size: 8
|
63 |
+
- eval_batch_size: 4
|
64 |
+
- seed: 42
|
65 |
+
- gradient_accumulation_steps: 2
|
66 |
+
- total_train_batch_size: 16
|
67 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
68 |
+
- lr_scheduler_type: linear
|
69 |
+
- num_epochs: 5.0
|
70 |
+
|
71 |
+
### Training results
|
72 |
+
|
73 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
74 |
+
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
75 |
+
| 0.0168 | 1.0 | 4712 | 0.0284 | 0.9813 | 0.9825 | 0.9819 | 0.9904 |
|
76 |
+
| 0.0107 | 2.0 | 9424 | 0.0350 | 0.9789 | 0.9814 | 0.9802 | 0.9895 |
|
77 |
+
| 0.005 | 3.0 | 14136 | 0.0364 | 0.9826 | 0.9843 | 0.9835 | 0.9909 |
|
78 |
+
| 0.0033 | 4.0 | 18848 | 0.0434 | 0.9830 | 0.9831 | 0.9830 | 0.9908 |
|
79 |
+
| 0.0017 | 5.0 | 23560 | 0.0501 | 0.9833 | 0.9838 | 0.9835 | 0.9911 |
|
80 |
+
|
81 |
+
|
82 |
+
### Framework versions
|
83 |
+
|
84 |
+
- Transformers 4.22.2
|
85 |
+
- Pytorch 1.12.1+cu113
|
86 |
+
- Datasets 2.4.0
|
87 |
+
- Tokenizers 0.12.1
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "NlpHUST/electra-base-vn",
|
3 |
+
"architectures": [
|
4 |
+
"ElectraForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"embedding_size": 768,
|
9 |
+
"finetuning_task": "ner",
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "B",
|
15 |
+
"1": "I"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"B": 0,
|
21 |
+
"I": 1
|
22 |
+
},
|
23 |
+
"layer_norm_eps": 1e-12,
|
24 |
+
"max_position_embeddings": 512,
|
25 |
+
"model_type": "electra",
|
26 |
+
"num_attention_heads": 12,
|
27 |
+
"num_hidden_layers": 12,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"position_embedding_type": "absolute",
|
30 |
+
"summary_activation": "gelu",
|
31 |
+
"summary_last_dropout": 0.1,
|
32 |
+
"summary_type": "first",
|
33 |
+
"summary_use_proj": true,
|
34 |
+
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.22.2",
|
36 |
+
"type_vocab_size": 2,
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 62000
|
39 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ad63e82ab68b3df1f3553fa5090e79effbd99a081dd4cd53ba24bc8da64020e
|
3 |
+
size 532344177
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": false,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"name_or_path": "NlpHUST/electra-base-vn",
|
7 |
+
"never_split": null,
|
8 |
+
"pad_token": "[PAD]",
|
9 |
+
"sep_token": "[SEP]",
|
10 |
+
"special_tokens_map_file": null,
|
11 |
+
"strip_accents": null,
|
12 |
+
"tokenize_chinese_chars": true,
|
13 |
+
"tokenizer_class": "ElectraTokenizer",
|
14 |
+
"unk_token": "[UNK]"
|
15 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|