MOLAR 10.7B
Q-LoRA fine-tuned on kyujinpy/Sakura-SOLAR-Instruct with meta-math/MetaMathQA
Adapter model and normal model is available, you can download with both styles.
You must use this prompt style.
### Query: <query>
### Response: <response>
Loss Curve:
Open LLM Leaderboard Evaluation Results
Detailed results will be found Here
| Metric | Value |
|---|---|
| Avg. | |
| ARC (25-shot) | |
| HellaSwag (10-shot) | |
| MMLU (5-shot) | |
| TruthfulQA (0-shot) | |
| Winogrande (5-shot) | |
| GSM8K (5-shot) |