| Quantization made by Richard Erkhov. | |
| [Github](https://github.com/RichardErkhov) | |
| [Discord](https://discord.gg/pvy7H8DZMG) | |
| [Request more models](https://github.com/RichardErkhov/quant_request) | |
| Llama-2-7b-hf-eli5-cleaned-1024_qlora_merged - bnb 8bits | |
| - Model creator: https://huggingface.co/dhmeltzer/ | |
| - Original model: https://huggingface.co/dhmeltzer/Llama-2-7b-hf-eli5-cleaned-1024_qlora_merged/ | |
| Original model description: | |
| # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) | |
| Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_dhmeltzer__Llama-2-7b-hf-eli5-cleaned-1024_qlora_merged) | |
| | Metric | Value | | |
| |-----------------------|---------------------------| | |
| | Avg. | 44.13 | | |
| | ARC (25-shot) | 53.67 | | |
| | HellaSwag (10-shot) | 78.21 | | |
| | MMLU (5-shot) | 45.9 | | |
| | TruthfulQA (0-shot) | 46.13 | | |
| | Winogrande (5-shot) | 73.8 | | |
| | GSM8K (5-shot) | 4.7 | | |
| | DROP (3-shot) | 6.53 | | |