Adding Evaluation Results
#1
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -91,3 +91,17 @@ No formal evaluation is available for this model at this time.
|
|
| 91 |
|
| 92 |
It is recommend to use this model with the KoboldAI software. All feedback and comments can be directed to TeH_Venom on the KoboldAI discord.
|
| 93 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 91 |
|
| 92 |
It is recommend to use this model with the KoboldAI software. All feedback and comments can be directed to TeH_Venom on the KoboldAI discord.
|
| 93 |
|
| 94 |
+
|
| 95 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 96 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_KoboldAI__PPO_Pygway-6b-Mix)
|
| 97 |
+
|
| 98 |
+
| Metric | Value |
|
| 99 |
+
|-----------------------|---------------------------|
|
| 100 |
+
| Avg. | 34.53 |
|
| 101 |
+
| ARC (25-shot) | 41.81 |
|
| 102 |
+
| HellaSwag (10-shot) | 67.77 |
|
| 103 |
+
| MMLU (5-shot) | 28.42 |
|
| 104 |
+
| TruthfulQA (0-shot) | 32.5 |
|
| 105 |
+
| Winogrande (5-shot) | 64.4 |
|
| 106 |
+
| GSM8K (5-shot) | 1.67 |
|
| 107 |
+
| DROP (3-shot) | 5.17 |
|