Adding Evaluation Results
#3
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -5,3 +5,17 @@ license: other
|
|
| 5 |
This contains the weights for the LLaMA-13b model. This model is under a non-commercial license (see the LICENSE file).
|
| 6 |
You should only use this repository if you have been granted access to the model by filling out [this form](https://docs.google.com/forms/d/e/1FAIpQLSfqNECQnMkycAp2jP4Z9TFX0cGR4uf7b_fBxjY_OjhJILlKGA/viewform?usp=send_form) but either lost your copy of the weights or got some trouble converting them to the Transformers format.
|
| 7 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
This contains the weights for the LLaMA-13b model. This model is under a non-commercial license (see the LICENSE file).
|
| 6 |
You should only use this repository if you have been granted access to the model by filling out [this form](https://docs.google.com/forms/d/e/1FAIpQLSfqNECQnMkycAp2jP4Z9TFX0cGR4uf7b_fBxjY_OjhJILlKGA/viewform?usp=send_form) but either lost your copy of the weights or got some trouble converting them to the Transformers format.
|
| 7 |
|
| 8 |
+
|
| 9 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 10 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_huggyllama__llama-13b)
|
| 11 |
+
|
| 12 |
+
| Metric | Value |
|
| 13 |
+
|-----------------------|---------------------------|
|
| 14 |
+
| Avg. | 44.81 |
|
| 15 |
+
| ARC (25-shot) | 56.14 |
|
| 16 |
+
| HellaSwag (10-shot) | 80.92 |
|
| 17 |
+
| MMLU (5-shot) | 47.61 |
|
| 18 |
+
| TruthfulQA (0-shot) | 39.48 |
|
| 19 |
+
| Winogrande (5-shot) | 76.24 |
|
| 20 |
+
| GSM8K (5-shot) | 7.58 |
|
| 21 |
+
| DROP (3-shot) | 5.66 |
|