Spaces:
Running
Running
Update app.py
Browse files
app.py
CHANGED
@@ -105,7 +105,7 @@ def main():
|
|
105 |
# About tab
|
106 |
with tab2:
|
107 |
st.markdown('''
|
108 |
-
|
109 |
|
110 |
Popularized by [Teknium](https://huggingface.co/teknium) and [NousResearch](https://huggingface.co/NousResearch), this benchmark suite aggregates four benchmarks:
|
111 |
|
@@ -114,9 +114,16 @@ def main():
|
|
114 |
* [**TruthfulQA**](https://arxiv.org/abs/2109.07958) (0-shot): `truthfulqa_mc`
|
115 |
* [**Bigbench**](https://arxiv.org/abs/2206.04615) (0-shot): `bigbench_causal_judgement,bigbench_date_understanding,bigbench_disambiguation_qa,bigbench_geometric_shapes,bigbench_logical_deduction_five_objects,bigbench_logical_deduction_seven_objects,bigbench_logical_deduction_three_objects,bigbench_movie_recommendation,bigbench_navigate,bigbench_reasoning_about_colored_objects,bigbench_ruin_names,bigbench_salient_translation_error_detection,bigbench_snarks,bigbench_sports_understanding,bigbench_temporal_sequences,bigbench_tracking_shuffled_objects_five_objects,bigbench_tracking_shuffled_objects_seven_objects,bigbench_tracking_shuffled_objects_three_objects`
|
116 |
|
117 |
-
|
118 |
|
119 |
You can easily reproduce these results using [🧐 LLM AutoEval](https://github.com/mlabonne/llm-autoeval/tree/master), a colab notebook that automates the evaluation process (benchmark: `nous`). This will upload the results to GitHub as gists. You can find the entire table with the links to the detailed results [here](https://gist.github.com/mlabonne/90294929a2dbcb8877f9696f28105fdf).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
120 |
''')
|
121 |
|
122 |
if __name__ == "__main__":
|
|
|
105 |
# About tab
|
106 |
with tab2:
|
107 |
st.markdown('''
|
108 |
+
### Nous benchmark suite
|
109 |
|
110 |
Popularized by [Teknium](https://huggingface.co/teknium) and [NousResearch](https://huggingface.co/NousResearch), this benchmark suite aggregates four benchmarks:
|
111 |
|
|
|
114 |
* [**TruthfulQA**](https://arxiv.org/abs/2109.07958) (0-shot): `truthfulqa_mc`
|
115 |
* [**Bigbench**](https://arxiv.org/abs/2206.04615) (0-shot): `bigbench_causal_judgement,bigbench_date_understanding,bigbench_disambiguation_qa,bigbench_geometric_shapes,bigbench_logical_deduction_five_objects,bigbench_logical_deduction_seven_objects,bigbench_logical_deduction_three_objects,bigbench_movie_recommendation,bigbench_navigate,bigbench_reasoning_about_colored_objects,bigbench_ruin_names,bigbench_salient_translation_error_detection,bigbench_snarks,bigbench_sports_understanding,bigbench_temporal_sequences,bigbench_tracking_shuffled_objects_five_objects,bigbench_tracking_shuffled_objects_seven_objects,bigbench_tracking_shuffled_objects_three_objects`
|
116 |
|
117 |
+
### Reproducibility
|
118 |
|
119 |
You can easily reproduce these results using [🧐 LLM AutoEval](https://github.com/mlabonne/llm-autoeval/tree/master), a colab notebook that automates the evaluation process (benchmark: `nous`). This will upload the results to GitHub as gists. You can find the entire table with the links to the detailed results [here](https://gist.github.com/mlabonne/90294929a2dbcb8877f9696f28105fdf).
|
120 |
+
|
121 |
+
### Clone this space
|
122 |
+
|
123 |
+
You can create your own leaderboard with your LLM AutoEval results on GitHub Gist. You just need to clone this space and specify two variables:
|
124 |
+
|
125 |
+
* Change the `gist_id` in [yall.py](https://huggingface.co/spaces/mlabonne/Yet_Another_LLM_Leaderboard/blob/main/yall.py#L126).
|
126 |
+
* Create "New Secret" in Settings > Variables and secrets (name: "github", value: [your GitHub token](https://github.com/settings/tokens))
|
127 |
''')
|
128 |
|
129 |
if __name__ == "__main__":
|