Adding Evaluation Results

README.md

@@ -131,4 +131,17 @@ while True:
     print(output_text)
 ```
 ## Deploying and training the model
-The model has been fine-tuned on a specific input format that goes like this ```"<|USER|> {user prompt} <|ASSISTANT|> {model prediction} <|End|>".``` For the best performance from the model the input text should be as follows ```<|USER|> {user prompt} <|ASSISTANT|> ``` and the target/label should be as follows ```<|USER|> {user prompt} <|ASSISTANT|> {dataset output} <|End|>```
+The model has been fine-tuned on a specific input format that goes like this ```"<|USER|> {user prompt} <|ASSISTANT|> {model prediction} <|End|>".``` For the best performance from the model the input text should be as follows ```<|USER|> {user prompt} <|ASSISTANT|> ``` and the target/label should be as follows ```<|USER|> {user prompt} <|ASSISTANT|> {dataset output} <|End|>```
+# [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_Locutusque__gpt2-conversational-or-qa)
+
+| Metric                | Value                     |
+|-----------------------|---------------------------|
+| Avg.                  | 25.09   |
+| ARC (25-shot)         | 21.42          |
+| HellaSwag (10-shot)   | 27.61    |
+| MMLU (5-shot)         | 26.51         |
+| TruthfulQA (0-shot)   | 47.31   |
+| Winogrande (5-shot)   | 51.14   |
+| GSM8K (5-shot)        | 0.08        |
+| DROP (3-shot)         | 1.55         |