Update README.md

README.md

@@ -29,6 +29,21 @@ language:
 \n\n### User:\n {question}'''
 
 
+### Evaluation results
+
+llm as a judge 방식으로 평가른 진행했습니다.
+자세한 내용은 " "를 참고해주세요
+
+| Model                                                                                                   | params | Fluency | Coherence | Accuracy | Completeness |
+|---------------------------------------------------------------------------------------------------------|--------|---------|-----------|----------|--------------|
+| **[kikikara/llama_with_eeve_new_03_150m](https://huggingface.co/kikikara/llama_with_eeve_new_03_150m)** | **0.15B**  | **63.12%**  |   **37.18%**  |  **23.75%**  |    **23.75%**  |
+| [EleutherAI/polyglot-ko-1.3b](https://huggingface.co/EleutherAI/polyglot-ko-1.3b)                       | 1.3B   | 51.25%  |   40.31%  |  34.68%  |    32.5%     |
+| [EleutherAI/polyglot-ko-5.8b](https://huggingface.co/EleutherAI/polyglot-ko-5.8b) (this)                | 5.8B   | 54.37%  |   40.62%  |  41.25%  |     35%      |
+
+### kikikara/llama_with_eeve_new_03_150m - 36.953125%
+### EleutherAI/polyglot-ko-1.3b - 39.6875%
+### EleutherAI/polyglot-ko-5.8b - 42.8125%
+
 ### How to use
 
 ```python
@@ -43,7 +58,7 @@ prompt = f"### System:\n당신은 비도덕적이거나, 성적이거나, 불법
 pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=400, repetition_penalty=1.12)
 result = pipe(prompt)
 
-print(result[0]['generated_text'])
+print(result[0]['generated_text'])```
 
 
-## Evaluation results
+### How to use