General Language Understanding on Open LLM Leaderboard
65.51Average ScoreHyPO-Llama-3
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| HyPO-Llama-3base_model=Meta-Llama-3-8B-Instruct, MMLU shots=5-shot, GSM8K shots=5-shot, Arc shots=25-shot, TruthfulQA shots=0-shot, HellaSwag shots=10-shot2024.06 | 65.51 | 65.74 | 73.84 | 62.71 | 45.55 | 79.74 | |
| DPO-Llama-3base_model=Meta-Llama-3-8B-Instruct, MMLU shots=5-shot, GSM8K shots=5-shot, Arc shots=25-shot, TruthfulQA shots=0-shot, HellaSwag shots=10-shot2024.06 | 65.34 | 65.82 | 73.62 | 63.14 | 45.02 | 79.1 | |
| Meta-Llama-3-8B-InstructMMLU shots=5-shot, GSM8K shots=5-shot, Arc shots=25-shot, TruthfulQA shots=0-shot, HellaSwag shots=10-shot2024.06 | 65.07 | 65.68 | 74.91 | 62.12 | 43.88 | 78.76 | |
| RECOSTData size=5202024.02 | 56.07 | — | — | — | — | — | |
| IFDData size=31112024.02 | 55.78 | — | — | — | — | — | |
| PEData size=5202024.02 | 55.31 | — | — | — | — | — | |
| Full AlpacaData size=520022024.02 | 55.06 | — | — | — | — | — |