Adding Evaluation Results

README.md

@@ -16,4 +16,17 @@ can produce NC-17+ content (mostly from Shinen).
 
 GPT-R merge variant will be released if it adds
 value to this already "kitchen sink" level of
-merging.
+merging.
+# [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_digitous__Javelin-GPTJ)
+
+| Metric                | Value                     |
+|-----------------------|---------------------------|
+| Avg.                  | 35.16   |
+| ARC (25-shot)         | 42.66          |
+| HellaSwag (10-shot)   | 70.45    |
+| MMLU (5-shot)         | 26.2         |
+| TruthfulQA (0-shot)   | 36.08   |
+| Winogrande (5-shot)   | 64.17   |
+| GSM8K (5-shot)        | 1.82        |
+| DROP (3-shot)         | 4.77         |