DontPlanToEnd commited on
Commit
b2f72d4
β€’
1 Parent(s): 44bdb77

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +3 -3
app.py CHANGED
@@ -3,7 +3,7 @@ import pandas as pd
3
 
4
  # Define the columns for the UGI Leaderboard
5
  UGI_COLS = [
6
- '#P', 'Model', 'UGI πŸ†', 'Willingness πŸ‘', 'Unruly', 'Internet', 'CrimeStats', 'Stories/Jokes', 'PolContro'
7
  ]
8
 
9
  # Load the leaderboard data from a CSV file
@@ -61,9 +61,9 @@ GraInter = gr.Blocks()
61
  with GraInter:
62
  gr.HTML("""<h1 align="center">UGI Leaderboard</h1>""")
63
  gr.Markdown("""
64
- UGI: Uncensored General Intelligence. The average of 5 different subjects that LLMs are commonly steered away from. The leaderboard is made from roughly 60 questions overall, measuring both "willingness to answer" and "accuracy" in fact-based controversial questions.
65
 
66
- Willingness: A more narrow, 10-point score, solely measuring the LLM's willingness to answer controversial questions.
67
 
68
  Unruly: Knowledge of activities that are generally frowned upon.
69
 
 
3
 
4
  # Define the columns for the UGI Leaderboard
5
  UGI_COLS = [
6
+ '#P', 'Model', 'UGI πŸ†', 'W/10 πŸ‘', 'Unruly', 'Internet', 'CrimeStats', 'Stories/Jokes', 'PolContro'
7
  ]
8
 
9
  # Load the leaderboard data from a CSV file
 
61
  with GraInter:
62
  gr.HTML("""<h1 align="center">UGI Leaderboard</h1>""")
63
  gr.Markdown("""
64
+ UGI: Uncensored General Intelligence. The average of 5 different subjects that LLMs are commonly steered away from. The leaderboard is made of roughly 60 questions/tasks, measuring both "willingness to answer" and "accuracy" in fact-based controversial questions.
65
 
66
+ W/10: A more narrow, 10-point score, solely measuring the LLM's Willingness to answer controversial questions.
67
 
68
  Unruly: Knowledge of activities that are generally frowned upon.
69