Hugging Face's logo

maywell
/
Synatra-7B-v0.3-dpo

Text Generation
Transformers
PyTorch
mistral
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
4
maywell commited on
Commit
405a4f1
•
1 Parent(s): 59f0576

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -34,7 +34,7 @@ It follows [ChatML](https://github.com/openai/openai-python/blob/main/chatml.md)
34
  [EleutherAI/lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness/tree/polyglot)를 사용하여 BoolQ, SentiNeg, Wic을 측정했습니다.
35
 
36
  | Model | COPA | HellaSwag | BoolQ | SentiNeg
37
- | --- | --- | --- | --- | --- | ---
38
  | EleutherAI/polyglot-ko-12.8b | 0.7937 | 0.5954 | 0.4818 | 0.9117
39
  | Synatra-7B-v0.3-base | 0.6344 | 0.5140 | 0.5226 | NaN
40
  | **Synatra-7B-v0.3-dpo** | **0.6380** | **0.4780** | **0.8058** | **0.8942**
 
34
  [EleutherAI/lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness/tree/polyglot)를 사용하여 BoolQ, SentiNeg, Wic을 측정했습니다.
35
 
36
  | Model | COPA | HellaSwag | BoolQ | SentiNeg
37
+ | --- | --- | --- | --- | ---
38
  | EleutherAI/polyglot-ko-12.8b | 0.7937 | 0.5954 | 0.4818 | 0.9117
39
  | Synatra-7B-v0.3-base | 0.6344 | 0.5140 | 0.5226 | NaN
40
  | **Synatra-7B-v0.3-dpo** | **0.6380** | **0.4780** | **0.8058** | **0.8942**