felix
commited on
Commit
•
5669002
1
Parent(s):
0e46dc8
add rescored...
Browse files- app.py +7 -1
- data/20230824_0626/hf_llm_diagramv2.png +0 -0
- data/20230824_0626/hf_llm_diagramv2_rescored.png +0 -0
- data/20230824_0626/hg_average_to_agentbench_compare.png +0 -0
- data/20230824_0626/hg_average_to_alpacaeval_compare.png +0 -0
- data/20230824_0626/hg_average_to_mosaic_compare.png +0 -0
- data/20230824_0626/hg_average_to_mt_bench_compare.png +0 -0
- data/20230824_0626/hg_average_to_opencompass_compare.png +0 -0
app.py
CHANGED
@@ -47,7 +47,8 @@ hf_llm_diagrams = [img for img in imgs if 'hf_llm_diagram' in os.path.basename(i
|
|
47 |
remaining_imgs = [img for img in imgs if 'hf_llm_diagram' not in os.path.basename(img)]
|
48 |
|
49 |
st.write("HuggingFace Open LLM leaderboard by Model Size")
|
50 |
-
st.image(hf_llm_diagrams,use_column_width="auto")
|
|
|
51 |
|
52 |
st.divider()
|
53 |
st.write("HuggingFace and Other Leaderboards: A Comparative Model Evaluation")
|
@@ -76,6 +77,11 @@ st.write(
|
|
76 |
</ul>
|
77 |
""", unsafe_allow_html=True
|
78 |
)
|
|
|
|
|
|
|
|
|
|
|
79 |
st.divider()
|
80 |
st.subheader('About')
|
81 |
st.write('This meta leaderboard is built and maintained by Felix Zaslavskiy. For feedback, correction, suggestions please reach out on X at <a href="https://twitter.com/FZaslavskiy" >@FZaslavskiy</a> or here via community discussions.', unsafe_allow_html=True)
|
|
|
47 |
remaining_imgs = [img for img in imgs if 'hf_llm_diagram' not in os.path.basename(img)]
|
48 |
|
49 |
st.write("HuggingFace Open LLM leaderboard by Model Size")
|
50 |
+
st.image(hf_llm_diagrams[0],use_column_width="auto")
|
51 |
+
|
52 |
|
53 |
st.divider()
|
54 |
st.write("HuggingFace and Other Leaderboards: A Comparative Model Evaluation")
|
|
|
77 |
</ul>
|
78 |
""", unsafe_allow_html=True
|
79 |
)
|
80 |
+
st.divider()
|
81 |
+
|
82 |
+
st.write("TruthfulQA at 10% for HuggingFace Open LLM leaderboard by Model Size")
|
83 |
+
st.image(hf_llm_diagrams[1],use_column_width="auto")
|
84 |
+
|
85 |
st.divider()
|
86 |
st.subheader('About')
|
87 |
st.write('This meta leaderboard is built and maintained by Felix Zaslavskiy. For feedback, correction, suggestions please reach out on X at <a href="https://twitter.com/FZaslavskiy" >@FZaslavskiy</a> or here via community discussions.', unsafe_allow_html=True)
|
data/20230824_0626/hf_llm_diagramv2.png
ADDED
data/20230824_0626/hf_llm_diagramv2_rescored.png
ADDED
data/20230824_0626/hg_average_to_agentbench_compare.png
ADDED
data/20230824_0626/hg_average_to_alpacaeval_compare.png
ADDED
data/20230824_0626/hg_average_to_mosaic_compare.png
ADDED
data/20230824_0626/hg_average_to_mt_bench_compare.png
ADDED
data/20230824_0626/hg_average_to_opencompass_compare.png
ADDED