Spaces:
Configuration error
Configuration error
Commit
•
52a1665
1
Parent(s):
b4324e8
test
Browse files- README.md +32 -9
- added_tokens.json +2 -0
- config.json +48 -0
- gitattributes.txt +16 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +2 -0
- summ.png +0 -0
- tokenizer.json +0 -0
- vocab.json +0 -0
README.md
CHANGED
@@ -1,13 +1,36 @@
|
|
1 |
---
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
colorTo: purple
|
6 |
-
sdk: streamlit
|
7 |
-
sdk_version: 1.21.0
|
8 |
-
app_file: app.py
|
9 |
-
pinned: false
|
10 |
license: mit
|
11 |
---
|
12 |
|
13 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
language: ko
|
3 |
+
tags:
|
4 |
+
- bart
|
|
|
|
|
|
|
|
|
|
|
5 |
license: mit
|
6 |
---
|
7 |
|
8 |
+
# Korean News Summarization Model
|
9 |
+
|
10 |
+
## Demo
|
11 |
+
|
12 |
+
https://huggingface.co/spaces/gogamza/kobart-summarization
|
13 |
+
|
14 |
+
## How to use
|
15 |
+
|
16 |
+
```python
|
17 |
+
import torch
|
18 |
+
from transformers import PreTrainedTokenizerFast
|
19 |
+
from transformers import BartForConditionalGeneration
|
20 |
+
|
21 |
+
tokenizer = PreTrainedTokenizerFast.from_pretrained('gogamza/kobart-summarization')
|
22 |
+
model = BartForConditionalGeneration.from_pretrained('gogamza/kobart-summarization')
|
23 |
+
|
24 |
+
text = "과거를 떠올려보자. 방송을 보던 우리의 모습을. 독보적인 매체는 TV였다. 온 가족이 둘러앉아 TV를 봤다. 간혹 가족들끼리 뉴스와 드라마, 예능 프로그램을 둘러싸고 리모컨 쟁탈전이 벌어지기도 했다. 각자 선호하는 프로그램을 ‘본방’으로 보기 위한 싸움이었다. TV가 한 대인지 두 대인지 여부도 그래서 중요했다. 지금은 어떤가. ‘안방극장’이라는 말은 옛말이 됐다. TV가 없는 집도 많다. 미디어의 혜 택을 누릴 수 있는 방법은 늘어났다. 각자의 방에서 각자의 휴대폰으로, 노트북으로, 태블릿으로 콘텐츠 를 즐긴다."
|
25 |
+
|
26 |
+
raw_input_ids = tokenizer.encode(text)
|
27 |
+
input_ids = [tokenizer.bos_token_id] + raw_input_ids + [tokenizer.eos_token_id]
|
28 |
+
|
29 |
+
summary_ids = model.generate(torch.tensor([input_ids]))
|
30 |
+
tokenizer.decode(summary_ids.squeeze().tolist(), skip_special_tokens=True)
|
31 |
+
```
|
32 |
+
|
33 |
+
|
34 |
+
|
35 |
+
|
36 |
+
|
added_tokens.json
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
{}
|
2 |
+
|
config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_dropout": 0.0,
|
3 |
+
"activation_function": "gelu",
|
4 |
+
"add_bias_logits": false,
|
5 |
+
"add_final_layer_norm": false,
|
6 |
+
"architectures": [
|
7 |
+
"BartForConditionalGeneration"
|
8 |
+
],
|
9 |
+
"attention_dropout": 0.0,
|
10 |
+
"bos_token_id": 0,
|
11 |
+
"classif_dropout": 0.1,
|
12 |
+
"classifier_dropout": 0.1,
|
13 |
+
"d_model": 768,
|
14 |
+
"decoder_attention_heads": 16,
|
15 |
+
"decoder_ffn_dim": 3072,
|
16 |
+
"decoder_layerdrop": 0.0,
|
17 |
+
"decoder_layers": 6,
|
18 |
+
"do_blenderbot_90_layernorm": false,
|
19 |
+
"dropout": 0.1,
|
20 |
+
"encoder_attention_heads": 16,
|
21 |
+
"encoder_ffn_dim": 3072,
|
22 |
+
"encoder_layerdrop": 0.0,
|
23 |
+
"encoder_layers": 6,
|
24 |
+
"eos_token_id": 1,
|
25 |
+
"extra_pos_embeddings": 2,
|
26 |
+
"force_bos_token_to_be_generated": false,
|
27 |
+
"id2label": {
|
28 |
+
"0": "NEGATIVE",
|
29 |
+
"1": "POSITIVE"
|
30 |
+
},
|
31 |
+
"init_std": 0.02,
|
32 |
+
"is_encoder_decoder": true,
|
33 |
+
"label2id": {
|
34 |
+
"NEGATIVE": 0,
|
35 |
+
"POSITIVE": 1
|
36 |
+
},
|
37 |
+
"max_position_embeddings": 1026,
|
38 |
+
"model_type": "bart",
|
39 |
+
"normalize_before": false,
|
40 |
+
"normalize_embedding": true,
|
41 |
+
"num_hidden_layers": 6,
|
42 |
+
"pad_token_id": 3,
|
43 |
+
"scale_embedding": false,
|
44 |
+
"static_position_embeddings": false,
|
45 |
+
"use_cache": true,
|
46 |
+
"vocab_size": 30000,
|
47 |
+
"author": "Heewon Jeon(madjakarta@gmail.com)"
|
48 |
+
}
|
gitattributes.txt
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
5 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.tar.gz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
10 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
11 |
+
*.joblib 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 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
15 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
16 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f59dd27e0e73b4b5cf45a6c70513cc5af667df248be097874be71bc51fd5f53
|
3 |
+
size 495659091
|
special_tokens_map.json
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>"}
|
2 |
+
|
summ.png
ADDED
![]() |
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|