Commit
•
df54a99
1
Parent(s):
785793f
Adding Evaluation Results (#1)
Browse files- Adding Evaluation Results (455c1b024881cb06b86bd1aa180eb505c36ff2e9)
Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -2,3 +2,17 @@
|
|
| 2 |
language: en
|
| 3 |
---
|
| 4 |
This is a Hugging Face transformers-compatible conversion of the original dense 13B-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.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
language: en
|
| 3 |
---
|
| 4 |
This is a Hugging Face transformers-compatible conversion of the original dense 13B-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)
|
| 7 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_KoboldAI__fairseq-dense-13B)
|
| 8 |
+
|
| 9 |
+
| Metric | Value |
|
| 10 |
+
|-----------------------|---------------------------|
|
| 11 |
+
| Avg. | 37.53 |
|
| 12 |
+
| ARC (25-shot) | 40.36 |
|
| 13 |
+
| HellaSwag (10-shot) | 75.51 |
|
| 14 |
+
| MMLU (5-shot) | 27.07 |
|
| 15 |
+
| TruthfulQA (0-shot) | 32.83 |
|
| 16 |
+
| Winogrande (5-shot) | 67.96 |
|
| 17 |
+
| GSM8K (5-shot) | 0.0 |
|
| 18 |
+
| DROP (3-shot) | 18.96 |
|