Hugging Face's logo

wkshin89
/
Yi-Ko-6B-Instruct-v1.0

Text Generation
Transformers
Safetensors
Korean
llama
text-generation-inference
Inference Endpoints
Model card Files Community
wkshin89 commited on
Commit
21d1f29
·
1 Parent(s): e6bfa32

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -27,11 +27,11 @@ base_model: beomi/Yi-Ko-6B
27
  ### AI-Harness Evaluation
28
  https://github.com/Beomi/ko-lm-evaluation-harness
29
 
30
- | Model | BoolQ | Copa | HellaSwag | Sentineg |
31
- | --- | --- | --- | --- | --- |
32
- | | *Zero-shot* ||||
33
- | Yi-Ko-6B-Instruct-v1.0 | 0.6619 | 0.7794 | 0.4858 | 0.4589 |
34
- | Yi-Ko-6B | 0.7070 | 0.7696 | 0.5009 | 0.4044 |
35
 
36
  ## Instruction Format
37
  ```python
 
27
  ### AI-Harness Evaluation
28
  https://github.com/Beomi/ko-lm-evaluation-harness
29
 
30
+ | Model | kobest_boolq | kobest_copa | kobest_hellaswag | kobest_sentineg | korunsmile | pawsx_ko |
31
+ | --- | --- | --- | --- | --- | --- | --- |
32
+ | | *Zero-shot* ||||||
33
+ | Yi-Ko-6B-Instruct-v1.0 | 0.6619 | 0.7794 | 0.4858 | 0.4589 | 0.3520 | 0.5545 |
34
+ | Yi-Ko-6B | 0.7070 | 0.7696 | 0.5009 | 0.4044 | 0.3828 | 0.5145 |
35
 
36
  ## Instruction Format
37
  ```python