metadata
license: llama3.2
datasets:
- CarrotAI/Carrot
- CarrotAI/Chat-Template
language:
- ko
- en
base_model:
- CarrotAI/Llama-3.2-Rabbit-Ko-3B-Instruct
pipeline_tag: text-generation
Score
LogicKor
| Category | Single turn | Multi turn |
|---|---|---|
| 수학(Math) | 5.86 | 5.14 |
| 문법(Grammar) | 4.71 | 1.29 |
| 이해(Understanding) | 4.00 | 4.43 |
| 추론(Reasoning) | 5.14 | 6.71 |
| 코딩(Coding) | 7.43 | 7.57 |
| 글쓰기(Writing) | 8.43 | 8.00 |
| Total | 5.93 | 5.52 |
| Overall | 5.73 |
| Task | Score | shot |
|---|---|---|
| ifeval | 58.61 | 0 |
| haerae | 43.26 | 5 |
| gsm8k-ko(strict-match) | 42.68 | 5 |
| gsm8k(strict-match) | 73.77 | 5 |