Commit
•
dfdad19
1
Parent(s):
dd51a3b
Adding Evaluation Results (#1)
Browse files- Adding Evaluation Results (4d67a2e6f7baf239562bf6ac241be4a8ce69126b)
Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -10,4 +10,17 @@ I have no idea what I'm doing
|
|
| 10 |
|
| 11 |
Anyways I finetune Llama 2 7b base hf with Guanaco Unfiltered dataset
|
| 12 |
|
| 13 |
-
It's probably horrible
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
|
| 11 |
Anyways I finetune Llama 2 7b base hf with Guanaco Unfiltered dataset
|
| 12 |
|
| 13 |
+
It's probably horrible
|
| 14 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 15 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Lazycuber__L2-7b-Base-Guanaco-Uncensored)
|
| 16 |
+
|
| 17 |
+
| Metric | Value |
|
| 18 |
+
|-----------------------|---------------------------|
|
| 19 |
+
| Avg. | 44.06 |
|
| 20 |
+
| ARC (25-shot) | 52.22 |
|
| 21 |
+
| HellaSwag (10-shot) | 79.08 |
|
| 22 |
+
| MMLU (5-shot) | 46.63 |
|
| 23 |
+
| TruthfulQA (0-shot) | 42.97 |
|
| 24 |
+
| Winogrande (5-shot) | 74.51 |
|
| 25 |
+
| GSM8K (5-shot) | 7.28 |
|
| 26 |
+
| DROP (3-shot) | 5.75 |
|