| language: en | |
| This is a Hugging Face transformers-compatible conversion of the original dense 6.7B-parameter model from the paper "[Efficient Large Scale Language Modeling with Mixtures of Experts](https://arxiv.org/abs/2112.10684)" from Artetxe et al. Please refer to the original model card, which can be found at https://github.com/facebookresearch/fairseq/blob/main/examples/moe_lm/model_card.md. | |
| # [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_KoboldAI__fairseq-dense-6.7B) | |
| | Metric | Value | | |
| |-----------------------|---------------------------| | |
| | Avg. | 36.09 | | |
| | ARC (25-shot) | 39.42 | | |
| | HellaSwag (10-shot) | 71.26 | | |
| | MMLU (5-shot) | 26.91 | | |
| | TruthfulQA (0-shot) | 32.73 | | |
| | Winogrande (5-shot) | 65.27 | | |
| | GSM8K (5-shot) | 0.0 | | |
| | DROP (3-shot) | 17.05 | | |