Hugging Face's logo

DILAB-HYU
/
KoQuality-Polyglot-5.8b

Text Generation
Transformers
PyTorch
Korean
gpt_neox
Generated from Trainer
polyglot-ko
gpt-neox
KoQuality
text-generation-inference
Inference Endpoints
Model card Files Community
1
dahye1 commited on
Commit
cb6d75a
•
1 Parent(s): 3da7e76

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -10
README.md CHANGED
@@ -10,8 +10,7 @@ KoQuality-Polyglot-5.8b is a fine-tuned version of [EleutherAI/polyglot-ko-5.8b]
10
  ## Overall Average accuracy score of the KoBEST datasets
11
 
12
  We use [KoBEST benchmark](https://huggingface.co/datasets/skt/kobest_v1) datasets(BoolQ, COPA, HellaSwag, SentiNeg, WiC) to compare the performance of our best model and other models accuracy. Our model outperforms other models in the average accuracy score of the KoBEST datasets.
13
- <img src=https://cdn-uploads.huggingface.co/production/uploads/650fecfd247f564485f8fbcf/t5x4PphoNb-tW3iCzXXHT.png style="max-width: 500px; width: 300%"/>
14
-
15
 
16
 
17
 
@@ -24,22 +23,19 @@ We use [KoBEST benchmark](https://huggingface.co/datasets/skt/kobest_v1) dataset
24
 
25
  ## Evaluation results
26
  ### COPA (F1)
27
- <img src=https://cdn-uploads.huggingface.co/production/uploads/650fecfd247f564485f8fbcf/QAie0x99S8-KEKvK0I_uZ.png style="max-width: 400px; width: 200%"/>
28
 
29
  ### BoolQ (F1)
30
- <img src=https://cdn-uploads.huggingface.co/production/uploads/650fecfd247f564485f8fbcf/CtEWEQ5BBS05V9cDWA7kp.png style="max-width: 400px; width: 200%"/>
31
 
32
  ### HellaSwag (F1)
33
- <img src=https://cdn-uploads.huggingface.co/production/uploads/650fecfd247f564485f8fbcf/cHws6qWkDlTfs5GVcQvtN.png style="max-width: 400px; width: 200%"/>
34
-
35
 
36
  ### SentiNeg (F1)
37
- <img src=https://cdn-uploads.huggingface.co/production/uploads/650fecfd247f564485f8fbcf/VEG15XXOIbzJyQAusLa4B.png style="max-width: 400px; width: 200%"/>
38
-
39
 
40
  ### WiC (F1)
41
- <img src=https://cdn-uploads.huggingface.co/production/uploads/650fecfd247f564485f8fbcf/hV-uADJiydkVQOyYysej9.png style="max-width: 400px; width: 200%"/>
42
-
43
 
44
 
45
  ## Training hyperparameters
 
10
  ## Overall Average accuracy score of the KoBEST datasets
11
 
12
  We use [KoBEST benchmark](https://huggingface.co/datasets/skt/kobest_v1) datasets(BoolQ, COPA, HellaSwag, SentiNeg, WiC) to compare the performance of our best model and other models accuracy. Our model outperforms other models in the average accuracy score of the KoBEST datasets.
13
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/650fecfd247f564485f8fbcf/t5x4PphoNb-tW3iCzXXHT.png" width= "500px">
 
14
 
15
 
16
 
 
23
 
24
  ## Evaluation results
25
  ### COPA (F1)
26
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/650fecfd247f564485f8fbcf/QAie0x99S8-KEKvK0I_uZ.png" width= "500px">
27
 
28
  ### BoolQ (F1)
29
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/650fecfd247f564485f8fbcf/CtEWEQ5BBS05V9cDWA7kp.png" width= "500px">
30
 
31
  ### HellaSwag (F1)
32
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/650fecfd247f564485f8fbcf/cHws6qWkDlTfs5GVcQvtN.png" width= "500px">
 
33
 
34
  ### SentiNeg (F1)
35
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/650fecfd247f564485f8fbcf/VEG15XXOIbzJyQAusLa4B.png" width= "500px">
 
36
 
37
  ### WiC (F1)
38
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/650fecfd247f564485f8fbcf/hV-uADJiydkVQOyYysej9.png" width= "500px">
 
39
 
40
 
41
  ## Training hyperparameters