haoyang
commited on
Commit
•
c36313e
1
Parent(s):
741e393
Update about.py
Browse files- src/display/about.py +8 -1
src/display/about.py
CHANGED
@@ -27,6 +27,13 @@ TITLE = """<h1 align="center" id="space-title">NPHardEval leaderboard</h1>"""
|
|
27 |
|
28 |
# What does your leaderboard evaluate?
|
29 |
INTRODUCTION_TEXT = """
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
30 |
NPHardEval serves as a comprehensive benchmark for assessing the reasoning abilities of large language models (LLMs) through the lens of computational complexity classes.
|
31 |
"""
|
32 |
|
@@ -58,7 +65,7 @@ The following figure shows their relation regarding computational complexity in
|
|
58 |
|
59 |
<div align="center">
|
60 |
<img
|
61 |
-
src="https://raw.githubusercontent.com/casmlab/NPHardEval/main/NP-hard.jpg"
|
62 |
style="width: 50%;"
|
63 |
alt="Selected problems and the Euler diagram of computational complexity classes"
|
64 |
>
|
|
|
27 |
|
28 |
# What does your leaderboard evaluate?
|
29 |
INTRODUCTION_TEXT = """
|
30 |
+
<div align="center">
|
31 |
+
<img
|
32 |
+
src="https://raw.githubusercontent.com/casmlab/NPHardEval/main/NPHardEval_text_right.jpg"
|
33 |
+
style="width: 80%;"
|
34 |
+
alt="Selected problems and the Euler diagram of computational complexity classes"
|
35 |
+
>
|
36 |
+
</div>
|
37 |
NPHardEval serves as a comprehensive benchmark for assessing the reasoning abilities of large language models (LLMs) through the lens of computational complexity classes.
|
38 |
"""
|
39 |
|
|
|
65 |
|
66 |
<div align="center">
|
67 |
<img
|
68 |
+
src="https://raw.githubusercontent.com/casmlab/NPHardEval/main/figure/NP-hard.jpg"
|
69 |
style="width: 50%;"
|
70 |
alt="Selected problems and the Euler diagram of computational complexity classes"
|
71 |
>
|