Adding Evaluation Results

README.md

@@ -133,4 +133,17 @@ The code in this project is open-source under the [Apache-2.0](LICENSE) license,
 ## Acknowledgements
 - In this project, we used model weights from BigScience's [bloomz-7b1-mt](https://huggingface.co/bigscience/bloomz-7b1-mt) and Meta's [Llama 2](https://huggingface.co/meta-llama) series as initialization weights, along with vocabulary expansion.
 - The training code in this project was inspired by Databricks' [dolly](https://github.com/databrickslabs/dolly) project and Huggingface's [transformers](https://github.com/huggingface/transformers) library.
-- Distributed training in this project utilized Microsoft's [DeepSpeed](https://github.com/microsoft/deepspeed) distributed training tool and configuration files from Huggingface transformers' [ZeRO stage 2](https://huggingface.co/docs/transformers/main_classes/deepspeed#zero2-config).
+- Distributed training in this project utilized Microsoft's [DeepSpeed](https://github.com/microsoft/deepspeed) distributed training tool and configuration files from Huggingface transformers' [ZeRO stage 2](https://huggingface.co/docs/transformers/main_classes/deepspeed#zero2-config).
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_wenge-research__yayi-7b)
+
+| Metric                | Value                     |
+|-----------------------|---------------------------|
+| Avg.                  | 37.99   |
+| ARC (25-shot)         | 46.33          |
+| HellaSwag (10-shot)   | 61.72    |
+| MMLU (5-shot)         | 36.34         |
+| TruthfulQA (0-shot)   | 43.7   |
+| Winogrande (5-shot)   | 62.27   |
+| GSM8K (5-shot)        | 0.91        |
+| DROP (3-shot)         | 14.67         |