Adding Evaluation Results

#4
Files changed (1) hide show
  1. README.md +14 -1
README.md CHANGED
@@ -67,4 +67,17 @@ Outputs might often be factually wrong or misleading.
67
  ## Acknowledgements
68
  We would like to thank [SpicyChat](https://spicychat.ai/) for sponsoring the training for this model.
69
 
70
- [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
67
  ## Acknowledgements
68
  We would like to thank [SpicyChat](https://spicychat.ai/) for sponsoring the training for this model.
69
 
70
+ [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
71
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
72
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_PygmalionAI__pygmalion-2-7b)
73
+
74
+ | Metric | Value |
75
+ |-----------------------|---------------------------|
76
+ | Avg. | 44.66 |
77
+ | ARC (25-shot) | 54.01 |
78
+ | HellaSwag (10-shot) | 78.23 |
79
+ | MMLU (5-shot) | 49.11 |
80
+ | TruthfulQA (0-shot) | 43.78 |
81
+ | Winogrande (5-shot) | 75.14 |
82
+ | GSM8K (5-shot) | 6.37 |
83
+ | DROP (3-shot) | 5.98 |