Adding Evaluation Results
#5
by
leaderboard-pr-bot
- opened
README.md
CHANGED
@@ -131,4 +131,17 @@ while True:
|
|
131 |
print(output_text)
|
132 |
```
|
133 |
## Deploying and training the model
|
134 |
-
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|>```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
131 |
print(output_text)
|
132 |
```
|
133 |
## Deploying and training the model
|
134 |
+
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|>```
|
135 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
136 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Locutusque__gpt2-conversational-or-qa)
|
137 |
+
|
138 |
+
| Metric | Value |
|
139 |
+
|-----------------------|---------------------------|
|
140 |
+
| Avg. | 25.09 |
|
141 |
+
| ARC (25-shot) | 21.42 |
|
142 |
+
| HellaSwag (10-shot) | 27.61 |
|
143 |
+
| MMLU (5-shot) | 26.51 |
|
144 |
+
| TruthfulQA (0-shot) | 47.31 |
|
145 |
+
| Winogrande (5-shot) | 51.14 |
|
146 |
+
| GSM8K (5-shot) | 0.08 |
|
147 |
+
| DROP (3-shot) | 1.55 |
|