Adding Evaluation Results

#4
Files changed (1) hide show
  1. README.md +14 -1
README.md CHANGED
@@ -71,4 +71,17 @@ As such, it was **not** fine-tuned to be safe and harmless: the base model _and_
71
  ## Acknowledgements
72
  We would like to thank [SpicyChat](https://spicychat.ai/) for sponsoring the training for the [Pygmalion-2 13B](https://huggingface.co/PygmalionAI/pygmalion-2-13b) model.
73
 
74
- [<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
  ## Acknowledgements
72
  We would like to thank [SpicyChat](https://spicychat.ai/) for sponsoring the training for the [Pygmalion-2 13B](https://huggingface.co/PygmalionAI/pygmalion-2-13b) model.
73
 
74
+ [<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)
75
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
76
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_PygmalionAI__mythalion-13b)
77
+
78
+ | Metric | Value |
79
+ |-----------------------|---------------------------|
80
+ | Avg. | 49.41 |
81
+ | ARC (25-shot) | 61.26 |
82
+ | HellaSwag (10-shot) | 83.81 |
83
+ | MMLU (5-shot) | 56.53 |
84
+ | TruthfulQA (0-shot) | 46.56 |
85
+ | Winogrande (5-shot) | 77.43 |
86
+ | GSM8K (5-shot) | 13.27 |
87
+ | DROP (3-shot) | 7.01 |