license: apache-2.0 | |
language: | |
- en | |
Base Model: togethercomputer/RedPajama-INCITE-Base-3B-v1 | |
Dataset from: https://github.com/allenai/open-instruct and uncensored it using code in ehartford/wizard_vicuna_70k_unfiltered | |
Usage | |
``` | |
### Human: | |
your instruction | |
### ASSISANT: | |
output will be generated and ended with <|endoftext|> | |
``` | |
# [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_heegyu__RedTulu-Uncensored-3B-0719) | |
| Metric | Value | | |
|-----------------------|---------------------------| | |
| Avg. | 37.47 | | |
| ARC (25-shot) | 40.02 | | |
| HellaSwag (10-shot) | 62.55 | | |
| MMLU (5-shot) | 30.37 | | |
| TruthfulQA (0-shot) | 37.59 | | |
| Winogrande (5-shot) | 62.35 | | |
| GSM8K (5-shot) | 2.27 | | |
| DROP (3-shot) | 27.1 | | |