陈俊杰
commited on
Commit
•
d6304fe
1
Parent(s):
f0dd2c2
cjj: teamId
Browse files
app.py
CHANGED
@@ -32,9 +32,10 @@ Details of AEOLLLM can be found at the link: [https://aeollm.github.io/](https:/
|
|
32 |
""", unsafe_allow_html=True)
|
33 |
# 创建示例数据
|
34 |
|
|
|
35 |
DG = {
|
|
|
36 |
"methods": ["chatglm3-6b", "baichuan2-13b", "chatglm-pro", "gpt-4o-mini"],
|
37 |
-
"team": ["baseline", "baseline", "baseline", "baseline"],
|
38 |
"accuracy": [0.5806, 0.5483, 0.6001, 0.6472],
|
39 |
"kendall's tau": [0.3243, 0.1739, 0.3042, 0.4167],
|
40 |
"spearman": [0.3505, 0.1857, 0.3264, 0.4512]
|
@@ -45,8 +46,8 @@ for col in df1.select_dtypes(include=['float64', 'int64']).columns:
|
|
45 |
df1[col] = df1[col].apply(lambda x: f"{x:.4f}")
|
46 |
|
47 |
TE = {
|
|
|
48 |
"methods": ["chatglm3-6b", "baichuan2-13b", "chatglm-pro", "gpt-4o-mini"],
|
49 |
-
"team": ["baseline", "baseline", "baseline", "baseline"],
|
50 |
"accuracy": [0.5107, 0.5050, 0.5461, 0.5581],
|
51 |
"kendall's tau": [0.1281, 0.0635, 0.2716, 0.3864],
|
52 |
"spearman": [0.1352, 0.0667, 0.2867, 0.4157]
|
@@ -56,8 +57,8 @@ for col in df2.select_dtypes(include=['float64', 'int64']).columns:
|
|
56 |
df2[col] = df2[col].apply(lambda x: f"{x:.4f}")
|
57 |
|
58 |
SG = {
|
|
|
59 |
"methods": ["chatglm3-6b", "baichuan2-13b", "chatglm-pro", "gpt-4o-mini"],
|
60 |
-
"team": ["baseline", "baseline", "baseline", "baseline"],
|
61 |
"accuracy": [0.6504, 0.6014, 0.7162, 0.7441],
|
62 |
"kendall's tau": [0.3957, 0.2688, 0.5092, 0.5001],
|
63 |
"spearman": [0.4188, 0.2817, 0.5403, 0.5405],
|
@@ -67,8 +68,8 @@ for col in df3.select_dtypes(include=['float64', 'int64']).columns:
|
|
67 |
df3[col] = df3[col].apply(lambda x: f"{x:.4f}")
|
68 |
|
69 |
NFQA = {
|
|
|
70 |
"methods": ["chatglm3-6b", "baichuan2-13b", "chatglm-pro", "gpt-4o-mini"],
|
71 |
-
"team": ["baseline", "baseline", "baseline", "baseline"],
|
72 |
"accuracy": [0.5935, 0.5817, 0.7000, 0.7203],
|
73 |
"kendall's tau": [0.2332, 0.2389, 0.4440, 0.4235],
|
74 |
"spearman": [0.2443, 0.2492, 0.4630, 0.4511]
|
@@ -80,12 +81,10 @@ for col in df4.select_dtypes(include=['float64', 'int64']).columns:
|
|
80 |
# 创建标签页
|
81 |
tab1, tab2, tab3, tab4 = st.tabs(["DG", "TE", "SG", "NFQA"])
|
82 |
|
83 |
-
# 在标签页 3 中添加内容
|
84 |
with tab1:
|
85 |
st.markdown("""Task: Dialogue Generation; Dataset: DialyDialog""", unsafe_allow_html=True)
|
86 |
st.dataframe(df1, use_container_width=True)
|
87 |
|
88 |
-
# 在标签页 4 中添加内容
|
89 |
with tab2:
|
90 |
st.markdown("""Task: Text Expansion; Dataset: WritingPrompts""", unsafe_allow_html=True)
|
91 |
st.dataframe(df2, use_container_width=True)
|
@@ -94,7 +93,6 @@ with tab3:
|
|
94 |
st.markdown("""Task: Summary Generation; Dataset: Xsum""", unsafe_allow_html=True)
|
95 |
st.dataframe(df3, use_container_width=True)
|
96 |
|
97 |
-
# 在标签页 2 中添加内容
|
98 |
with tab4:
|
99 |
st.markdown("""Task: Non-Factoid QA; Dataset: NF_CATS""", unsafe_allow_html=True)
|
100 |
st.dataframe(df4, use_container_width=True)
|
|
|
32 |
""", unsafe_allow_html=True)
|
33 |
# 创建示例数据
|
34 |
|
35 |
+
# teamId 唯一标识码
|
36 |
DG = {
|
37 |
+
"teamId": ["baseline1", "baseline2", "baseline3", "baseline4"],
|
38 |
"methods": ["chatglm3-6b", "baichuan2-13b", "chatglm-pro", "gpt-4o-mini"],
|
|
|
39 |
"accuracy": [0.5806, 0.5483, 0.6001, 0.6472],
|
40 |
"kendall's tau": [0.3243, 0.1739, 0.3042, 0.4167],
|
41 |
"spearman": [0.3505, 0.1857, 0.3264, 0.4512]
|
|
|
46 |
df1[col] = df1[col].apply(lambda x: f"{x:.4f}")
|
47 |
|
48 |
TE = {
|
49 |
+
"teamId": ["baseline1", "baseline2", "baseline3", "baseline4"],
|
50 |
"methods": ["chatglm3-6b", "baichuan2-13b", "chatglm-pro", "gpt-4o-mini"],
|
|
|
51 |
"accuracy": [0.5107, 0.5050, 0.5461, 0.5581],
|
52 |
"kendall's tau": [0.1281, 0.0635, 0.2716, 0.3864],
|
53 |
"spearman": [0.1352, 0.0667, 0.2867, 0.4157]
|
|
|
57 |
df2[col] = df2[col].apply(lambda x: f"{x:.4f}")
|
58 |
|
59 |
SG = {
|
60 |
+
"teamId": ["baseline1", "baseline2", "baseline3", "baseline4"],
|
61 |
"methods": ["chatglm3-6b", "baichuan2-13b", "chatglm-pro", "gpt-4o-mini"],
|
|
|
62 |
"accuracy": [0.6504, 0.6014, 0.7162, 0.7441],
|
63 |
"kendall's tau": [0.3957, 0.2688, 0.5092, 0.5001],
|
64 |
"spearman": [0.4188, 0.2817, 0.5403, 0.5405],
|
|
|
68 |
df3[col] = df3[col].apply(lambda x: f"{x:.4f}")
|
69 |
|
70 |
NFQA = {
|
71 |
+
"teamId": ["baseline1", "baseline2", "baseline3", "baseline4"],
|
72 |
"methods": ["chatglm3-6b", "baichuan2-13b", "chatglm-pro", "gpt-4o-mini"],
|
|
|
73 |
"accuracy": [0.5935, 0.5817, 0.7000, 0.7203],
|
74 |
"kendall's tau": [0.2332, 0.2389, 0.4440, 0.4235],
|
75 |
"spearman": [0.2443, 0.2492, 0.4630, 0.4511]
|
|
|
81 |
# 创建标签页
|
82 |
tab1, tab2, tab3, tab4 = st.tabs(["DG", "TE", "SG", "NFQA"])
|
83 |
|
|
|
84 |
with tab1:
|
85 |
st.markdown("""Task: Dialogue Generation; Dataset: DialyDialog""", unsafe_allow_html=True)
|
86 |
st.dataframe(df1, use_container_width=True)
|
87 |
|
|
|
88 |
with tab2:
|
89 |
st.markdown("""Task: Text Expansion; Dataset: WritingPrompts""", unsafe_allow_html=True)
|
90 |
st.dataframe(df2, use_container_width=True)
|
|
|
93 |
st.markdown("""Task: Summary Generation; Dataset: Xsum""", unsafe_allow_html=True)
|
94 |
st.dataframe(df3, use_container_width=True)
|
95 |
|
|
|
96 |
with tab4:
|
97 |
st.markdown("""Task: Non-Factoid QA; Dataset: NF_CATS""", unsafe_allow_html=True)
|
98 |
st.dataframe(df4, use_container_width=True)
|