pongjin commited on
Commit
138378c
โ€ข
1 Parent(s): 5a2aaf5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +26 -1
README.md CHANGED
@@ -9,7 +9,12 @@ metrics:
9
  pipeline_tag: zero-shot-classification
10
  ---
11
 
12
- This model has been referred to the following link : https://github.com/Huffon/klue-transformers-tutorial.git
 
 
 
 
 
13
 
14
 
15
  RoBERTa์™€ ๊ฐ™์ด token_type_ids๋ฅผ ์‚ฌ์šฉํ•˜์ง€ ์•Š๋Š” ๋ชจ๋ธ์˜ ๊ฒฝ์šฐ, zero-shot pipeline์„ ๋ฐ”๋กœ ์ ์šฉํ•  ์ˆ˜ ์—†์Šต๋‹ˆ๋‹ค(transformers==4.7.0 ๊ธฐ์ค€)
@@ -67,4 +72,24 @@ classifier = pipeline(
67
  args_parser=CustomZeroShotClassificationArgumentHandler(),
68
  model="pongjin/roberta_with_kornli"
69
  )
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
70
  ```
 
9
  pipeline_tag: zero-shot-classification
10
  ---
11
 
12
+ **This model has been referred to the following link : https://github.com/Huffon/klue-transformers-tutorial.git**
13
+
14
+ ํ•ด๋‹น ๋ชจ๋ธ์€ ์œ„ ๊นƒํ—ˆ๋ธŒ๋ฅผ ์ฐธ๊ณ ํ•˜์—ฌ klue/roberta-base ๋ชจ๋ธ์„ kor_nli ์˜ mnli, xnli๋กœ ํŒŒ์ธํŠœ๋‹ํ•œ ๋ชจ๋ธ์ž…๋‹ˆ๋‹ค.
15
+ | train_loss | val_loss | acc | epoch | batch | lr |
16
+ | --- | --- | --- | --- | --- | --- |
17
+ | 0.326 | 0.538 | 0.811 | 3 | 32 | 2e-5 |
18
 
19
 
20
  RoBERTa์™€ ๊ฐ™์ด token_type_ids๋ฅผ ์‚ฌ์šฉํ•˜์ง€ ์•Š๋Š” ๋ชจ๋ธ์˜ ๊ฒฝ์šฐ, zero-shot pipeline์„ ๋ฐ”๋กœ ์ ์šฉํ•  ์ˆ˜ ์—†์Šต๋‹ˆ๋‹ค(transformers==4.7.0 ๊ธฐ์ค€)
 
72
  args_parser=CustomZeroShotClassificationArgumentHandler(),
73
  model="pongjin/roberta_with_kornli"
74
  )
75
+ ```
76
+ #### results
77
+ ```python
78
+ sequence = "๋ฐฐ๋‹น๋ฝ D-1 ์ฝ”์Šคํ”ผ, 2330์„  ์ƒ์Šน์„ธ...์™ธ์ธยท๊ธฐ๊ด€ ์‚ฌ์ž"
79
+ candidate_labels =["์™ธํ™˜",'ํ™˜์œจ', "๊ฒฝ์ œ", "๊ธˆ์œต", "๋ถ€๋™์‚ฐ","์ฃผ์‹"]
80
+
81
+ classifier(
82
+ sequence,
83
+ candidate_labels,
84
+ hypothesis_template='์ด๋Š” {}์— ๊ด€ํ•œ ๊ฒƒ์ด๋‹ค.',
85
+ )
86
+
87
+ >>{'sequence': '๋ฐฐ๋‹น๋ฝ D-1 ์ฝ”์Šคํ”ผ, 2330์„  ์ƒ์Šน์„ธ...์™ธ์ธยท๊ธฐ๊ด€ ์‚ฌ์ž',
88
+ 'labels': ['์ฃผ์‹', '๊ธˆ์œต', '๊ฒฝ์ œ', '์™ธํ™˜', 'ํ™˜์œจ', '๋ถ€๋™์‚ฐ'],
89
+ 'scores': [0.5052872896194458,
90
+ 0.17972524464130402,
91
+ 0.13852974772453308,
92
+ 0.09460823982954025,
93
+ 0.042949128895998,
94
+ 0.038900360465049744]}
95
  ```