Corey Morris
commited on
Commit
•
28d4d6a
1
Parent(s):
8474e43
Updated updated date
Browse files
app.py
CHANGED
@@ -50,7 +50,7 @@ data_provider = ResultDataProcessor()
|
|
50 |
|
51 |
# st.title('Model Evaluation Results including MMLU by task')
|
52 |
st.title('MMLU-by-Task Evaluation Results for 700+ Open Source Models')
|
53 |
-
st.markdown("""***Last updated August
|
54 |
st.markdown("""
|
55 |
Hugging Face has run evaluations on over 500 open source models and provides results on a
|
56 |
[publicly available leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) and [dataset](https://huggingface.co/datasets/open-llm-leaderboard/results).
|
@@ -58,7 +58,7 @@ st.markdown("""
|
|
58 |
[Preliminary analysis of MMLU-by-Task data](https://coreymorrisdata.medium.com/preliminary-analysis-of-mmlu-evaluation-data-insights-from-500-open-source-models-e67885aa364b)
|
59 |
""")
|
60 |
|
61 |
-
filters = st.checkbox('Select Models and Evaluations')
|
62 |
|
63 |
# Initialize selected columns with "Parameters" and "MMLU_average" if filters are checked
|
64 |
selected_columns = ['Parameters', 'MMLU_average'] if filters else data_provider.data.columns.tolist()
|
|
|
50 |
|
51 |
# st.title('Model Evaluation Results including MMLU by task')
|
52 |
st.title('MMLU-by-Task Evaluation Results for 700+ Open Source Models')
|
53 |
+
st.markdown("""***Last updated August 10th***""")
|
54 |
st.markdown("""
|
55 |
Hugging Face has run evaluations on over 500 open source models and provides results on a
|
56 |
[publicly available leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) and [dataset](https://huggingface.co/datasets/open-llm-leaderboard/results).
|
|
|
58 |
[Preliminary analysis of MMLU-by-Task data](https://coreymorrisdata.medium.com/preliminary-analysis-of-mmlu-evaluation-data-insights-from-500-open-source-models-e67885aa364b)
|
59 |
""")
|
60 |
|
61 |
+
filters = st.checkbox('Select Models and/or Evaluations')
|
62 |
|
63 |
# Initialize selected columns with "Parameters" and "MMLU_average" if filters are checked
|
64 |
selected_columns = ['Parameters', 'MMLU_average'] if filters else data_provider.data.columns.tolist()
|