Adding Evaluation Results
#3
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -82,4 +82,17 @@ Link for the filtered dataset used to make this model are bellow:
|
|
| 82 |
|
| 83 |
The original posting for this model was uploaded at the link bellow.
|
| 84 |
|
| 85 |
-
- https://huggingface.co/andreaskoepf/llama2-13b-megacode2_min100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 82 |
|
| 83 |
The original posting for this model was uploaded at the link bellow.
|
| 84 |
|
| 85 |
+
- https://huggingface.co/andreaskoepf/llama2-13b-megacode2_min100
|
| 86 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 87 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_rombodawg__LosslessMegaCoder-llama2-13b-mini)
|
| 88 |
+
|
| 89 |
+
| Metric | Value |
|
| 90 |
+
|-----------------------|---------------------------|
|
| 91 |
+
| Avg. | 49.92 |
|
| 92 |
+
| ARC (25-shot) | 60.58 |
|
| 93 |
+
| HellaSwag (10-shot) | 81.26 |
|
| 94 |
+
| MMLU (5-shot) | 57.92 |
|
| 95 |
+
| TruthfulQA (0-shot) | 48.89 |
|
| 96 |
+
| Winogrande (5-shot) | 76.95 |
|
| 97 |
+
| GSM8K (5-shot) | 15.92 |
|
| 98 |
+
| DROP (3-shot) | 7.89 |
|