Quantization made by Richard Erkhov.
Llama-2-7b-hf-eli5-cleaned-wiki65k-1024_qlora_merged - bnb 8bits
- Model creator: https://huggingface.co/dhmeltzer/
- Original model: https://huggingface.co/dhmeltzer/Llama-2-7b-hf-eli5-cleaned-wiki65k-1024_qlora_merged/
Original model description:
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 43.55 |
| ARC (25-shot) | 53.67 |
| HellaSwag (10-shot) | 78.09 |
| MMLU (5-shot) | 45.63 |
| TruthfulQA (0-shot) | 41.72 |
| Winogrande (5-shot) | 73.56 |
| GSM8K (5-shot) | 5.61 |
| DROP (3-shot) | 6.6 |