KoboldAI/fairseq-dense-355M

1---2language: en3---4This is a Hugging Face transformers-compatible conversion of the original dense 355M-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.5 6# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)7Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_KoboldAI__fairseq-dense-355M)8 9| Metric                | Value                     |10|-----------------------|---------------------------|11| Avg.                  | 27.99   |12| ARC (25-shot)         | 25.43          |13| HellaSwag (10-shot)   | 46.67    |14| MMLU (5-shot)         | 25.3         |15| TruthfulQA (0-shot)   | 39.19   |16| Winogrande (5-shot)   | 52.88   |17| GSM8K (5-shot)        | 0.0        |18| DROP (3-shot)         | 6.48         |19