陈俊杰
commited on
Commit
·
ca3e812
1
Parent(s):
79a93c9
fontSize
Browse files
app.py
CHANGED
|
@@ -124,7 +124,7 @@ st.markdown("""
|
|
| 124 |
<style>
|
| 125 |
/* 应用到所有的Markdown渲染文本 */
|
| 126 |
div[data-testid="stMarkdownContainer"] p,
|
| 127 |
-
div[data-testid="stMarkdownContainer"]
|
| 128 |
div[data-testid="stMarkdownContainer"] span,
|
| 129 |
div[data-testid="stMarkdownContainer"] li {
|
| 130 |
font-size: 24px;
|
|
@@ -257,13 +257,13 @@ elif page == "LeaderBoard":
|
|
| 257 |
st.header("LeaderBoard")
|
| 258 |
# # 描述
|
| 259 |
st.markdown("""
|
| 260 |
-
<
|
| 261 |
This leaderboard is used to show the performance of the <strong>automatic evaluation methods of LLMs</strong> submitted by the <strong>AEOLLM team</strong> on four tasks:
|
| 262 |
<p class='main-text'>1. Dialogue Generation (DG)</p>
|
| 263 |
<p class='main-text'>2. Text Expansion (TE)</p>
|
| 264 |
<p class='main-text'>3. Summary Generation (SG)</p>
|
| 265 |
<p class='main-text'>4. Non-Factoid QA (NFQA)</p>
|
| 266 |
-
</
|
| 267 |
""", unsafe_allow_html=True)
|
| 268 |
# 创建示例数据
|
| 269 |
|
|
@@ -314,19 +314,19 @@ This leaderboard is used to show the performance of the <strong>automatic evalua
|
|
| 314 |
tab1, tab2, tab3, tab4 = st.tabs(["DG", "TE", "SG", "NFQA"])
|
| 315 |
|
| 316 |
with tab1:
|
| 317 |
-
st.markdown("""<
|
| 318 |
st.dataframe(df1, use_container_width=True)
|
| 319 |
|
| 320 |
with tab2:
|
| 321 |
-
st.markdown("""<
|
| 322 |
st.dataframe(df2, use_container_width=True)
|
| 323 |
|
| 324 |
with tab3:
|
| 325 |
-
st.markdown("""<
|
| 326 |
st.dataframe(df3, use_container_width=True)
|
| 327 |
|
| 328 |
with tab4:
|
| 329 |
-
st.markdown("""<
|
| 330 |
st.dataframe(df4, use_container_width=True)
|
| 331 |
elif page == "Organisers":
|
| 332 |
st.header("Organisers")
|
|
|
|
| 124 |
<style>
|
| 125 |
/* 应用到所有的Markdown渲染文本 */
|
| 126 |
div[data-testid="stMarkdownContainer"] p,
|
| 127 |
+
div[data-testid="stMarkdownContainer"] table,
|
| 128 |
div[data-testid="stMarkdownContainer"] span,
|
| 129 |
div[data-testid="stMarkdownContainer"] li {
|
| 130 |
font-size: 24px;
|
|
|
|
| 257 |
st.header("LeaderBoard")
|
| 258 |
# # 描述
|
| 259 |
st.markdown("""
|
| 260 |
+
<p class='main-text'>
|
| 261 |
This leaderboard is used to show the performance of the <strong>automatic evaluation methods of LLMs</strong> submitted by the <strong>AEOLLM team</strong> on four tasks:
|
| 262 |
<p class='main-text'>1. Dialogue Generation (DG)</p>
|
| 263 |
<p class='main-text'>2. Text Expansion (TE)</p>
|
| 264 |
<p class='main-text'>3. Summary Generation (SG)</p>
|
| 265 |
<p class='main-text'>4. Non-Factoid QA (NFQA)</p>
|
| 266 |
+
</p>
|
| 267 |
""", unsafe_allow_html=True)
|
| 268 |
# 创建示例数据
|
| 269 |
|
|
|
|
| 314 |
tab1, tab2, tab3, tab4 = st.tabs(["DG", "TE", "SG", "NFQA"])
|
| 315 |
|
| 316 |
with tab1:
|
| 317 |
+
st.markdown("""<p class='main-text'>Task: Dialogue Generation; Dataset: DialyDialog</p>""", unsafe_allow_html=True)
|
| 318 |
st.dataframe(df1, use_container_width=True)
|
| 319 |
|
| 320 |
with tab2:
|
| 321 |
+
st.markdown("""<p class='main-text'>Task: Text Expansion; Dataset: WritingPrompts</p>""", unsafe_allow_html=True)
|
| 322 |
st.dataframe(df2, use_container_width=True)
|
| 323 |
|
| 324 |
with tab3:
|
| 325 |
+
st.markdown("""<p class='main-text'>Task: Summary Generation; Dataset: Xsum</p>""", unsafe_allow_html=True)
|
| 326 |
st.dataframe(df3, use_container_width=True)
|
| 327 |
|
| 328 |
with tab4:
|
| 329 |
+
st.markdown("""<p class='main-text'>Task: Non-Factoid QA; Dataset: NF_CATS</p>""", unsafe_allow_html=True)
|
| 330 |
st.dataframe(df4, use_container_width=True)
|
| 331 |
elif page == "Organisers":
|
| 332 |
st.header("Organisers")
|