Yi-6b-dpo
Model Details
- Base Model: beomi/Yi-Ko-6B
Datasets
- sampling and translate Open-Orca/SlimOrca
- sampling and translate Anthropic/hh-rlhf
Benchmark
- SOTA model under 7B as of Dec 20, 2023 (https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard).
| Model | Average | Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |
|---|---|---|---|---|---|---|
| hyeogi/Yi-6b-dpo-v0.2 (Ours) | 52.63 | 41.72 | 52.96 | 46.69 | 52.38 | 69.42 |
| hyeogi/Yi-6b-dpo-v0.1(Ours) | 51.38 | 41.3 | 52.23 | 45.34 | 54.03 | 63.99 |
| Minirecord/Mini_DPO_7b_01 | 50.47 | 48.29 | 54.68 | 46.7 | 47.78 | 54.9 |
- Downloads last month
- 1,165