Adding Evaluation Results
#1
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -10,4 +10,17 @@ Original models can all be found under KoboldAI w/exception to Pygmalion under P
|
|
| 10 |
|
| 11 |
This 4x merge is not intended for minors as it can produce NC-17+ content.
|
| 12 |
|
| 13 |
-
[R-type/instruct merge variant underway.]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
|
| 11 |
This 4x merge is not intended for minors as it can produce NC-17+ content.
|
| 12 |
|
| 13 |
+
[R-type/instruct merge variant underway.]
|
| 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_digitous__Javalion-GPTJ)
|
| 16 |
+
|
| 17 |
+
| Metric | Value |
|
| 18 |
+
|-----------------------|---------------------------|
|
| 19 |
+
| Avg. | 34.96 |
|
| 20 |
+
| ARC (25-shot) | 41.89 |
|
| 21 |
+
| HellaSwag (10-shot) | 68.69 |
|
| 22 |
+
| MMLU (5-shot) | 26.85 |
|
| 23 |
+
| TruthfulQA (0-shot) | 35.44 |
|
| 24 |
+
| Winogrande (5-shot) | 65.27 |
|
| 25 |
+
| GSM8K (5-shot) | 1.67 |
|
| 26 |
+
| DROP (3-shot) | 4.89 |
|