Views
No views yet
openai/gpt-4 : 0.6158
gemini-pro: 0.515
OpenCarrot-Mix-7B (this) : 0.4425
mistralai/Mixtral-8x7B-Instruct-v0.1 : 0.4304
openai/gpt-3.5-turbo : 0.4217| 평가 지표 | 점수 |
|---|---|
| AVG_llm_kr_eval | 0.4425 |
| EL | 0.0522 |
| FA | 0.0865 |
| NLI | 0.6700 |
| QA | 0.5100 |
| RC | 0.8937 |
| klue_ner_set_f1 | 0.0944 |
| klue_re_exact_match | 0.0100 |
| kmmlu_preview_exact_match | 0.4000 |
| kobest_copa_exact_match | 0.8200 |
| kobest_hs_exact_match | 0.5500 |
| kobest_sn_exact_match | 0.9800 |
| kobest_wic_exact_match | 0.6200 |
| korea_cg_bleu | 0.0865 |
| kornli_exact_match | 0.6400 |
| korsts_pearson | 0.8547 |
| korsts_spearman | 0.8464 |
| 카테고리 | 싱글 점수 평균 | 멀티 점수 평균 |
|---|---|---|
| 코딩(Coding) | 7.71 | 7.71 |
| 수학(Math) | 5.57 | 3.86 |
| 이해(Understanding) | 6.86 | 8.14 |
| 추론(Reasoning) | 8.14 | 6.43 |
| 글쓰기(Writing) | 8.71 | 6.86 |
| 문법(Grammar) | 5.29 | 2.29 |
| 카테고리 | 싱글 점수 평균 | 멀티 점수 평균 |
|---|---|---|
| 전체 싱글 | 7.05 | 5.88 |
1models:
2 - model: amazingvince/Not-WizardLM-2-7B
3 parameters:
4 weight: 1.0
5 - model: CarrotAI/OpenCarrot-Mistral-7B-Instruct-v0.2
6 parameters:
7 weight: 0.5
8merge_method: linear
9dtype: float16