Adding Evaluation Results
#1
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -6,4 +6,17 @@ This is a 50/50 weight merge of KoboldAI's adventure based
|
|
| 6 |
language model GPT-J-6B-Skein, and PygmalionAI's Pygmalion-6b.
|
| 7 |
|
| 8 |
https://huggingface.co/KoboldAI/GPT-J-6B-Skein
|
| 9 |
-
https://huggingface.co/PygmalionAI/pygmalion-6b
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
language model GPT-J-6B-Skein, and PygmalionAI's Pygmalion-6b.
|
| 7 |
|
| 8 |
https://huggingface.co/KoboldAI/GPT-J-6B-Skein
|
| 9 |
+
https://huggingface.co/PygmalionAI/pygmalion-6b
|
| 10 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 11 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_digitous__Skegma-GPTJ)
|
| 12 |
+
|
| 13 |
+
| Metric | Value |
|
| 14 |
+
|-----------------------|---------------------------|
|
| 15 |
+
| Avg. | 34.87 |
|
| 16 |
+
| ARC (25-shot) | 43.77 |
|
| 17 |
+
| HellaSwag (10-shot) | 69.22 |
|
| 18 |
+
| MMLU (5-shot) | 25.37 |
|
| 19 |
+
| TruthfulQA (0-shot) | 34.67 |
|
| 20 |
+
| Winogrande (5-shot) | 64.64 |
|
| 21 |
+
| GSM8K (5-shot) | 1.52 |
|
| 22 |
+
| DROP (3-shot) | 4.91 |
|