Hugging Face's logo

Edentns
/
DataVortexS-10.7B-v0.4

Text Generation
Transformers
Safetensors
Korean
llama
conversational
text-generation-inference
Model card Files Community
Jeongwon Choi commited on
Commit
3ed0766
·
verified ·
1 Parent(s): b460c0e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -8
README.md CHANGED
@@ -71,14 +71,12 @@ text = """\
71
 
72
  ### **[Ko LM Eval Harnesss](https://github.com/Beomi/ko-lm-evaluation-harness)**
73
 
74
- On Benchmarking ...
75
-
76
- | Task | 0-shot | 5-shot | 10-shot | 50-shot |
77
- | :--------------- | -----: | -----: | ------: | ------: |
78
- | kobest_boolq | 0.0 | 0.0 | 0.0 | 0.0 |
79
- | kobest_copa | 0.0 | 0.0 | 0.0 | 0.0 |
80
- | kobest_hellaswag | 0.0 | 0.0 | 0.0 | 0.0 |
81
- | kobest_sentineg | 0.0 | 0.0 | 0.0 | 0.0 |
82
 
83
  ### **[Ko-LLM-Leaderboard](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard)**
84
 
 
71
 
72
  ### **[Ko LM Eval Harnesss](https://github.com/Beomi/ko-lm-evaluation-harness)**
73
 
74
+ | Task | 0-shot | 5-shot | 10-shot | 50-shot |
75
+ | :--------------- | -------: | -------: | -------: | -------: |
76
+ | kobest_boolq | 0.389066 | 0.912924 | 0.912808 | 0.906428 |
77
+ | kobest_copa | 0.744865 | 0.747742 | 0.768856 | 0.785896 |
78
+ | kobest_hellaswag | 0.455793 | 0.443909 | 0.465783 | 0.472771 |
79
+ | kobest_sentineg | 0.584156 | 0.947082 | 0.962216 | 0.954657 |
 
 
80
 
81
  ### **[Ko-LLM-Leaderboard](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard)**
82