DontPlanToEnd commited on
Commit
27f577f
1 Parent(s): e26581e

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +18 -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 🏆', 'Willingness👍', 'Unruly', 'Internet', 'CrimeStats', 'Stories/Jokes', 'Pol Contro'
7
  ]
8
 
9
  # Load the leaderboard data from a CSV file
@@ -57,11 +57,26 @@ def update_table(df: pd.DataFrame, query: str, param_ranges: dict) -> pd.DataFra
57
  demo = gr.Blocks()
58
 
59
  with demo:
60
- gr.Markdown("## UGI Leaderboard", elem_classes="text-lg")
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
61
  with gr.Column():
62
  with gr.Row():
63
  search_bar = gr.Textbox(placeholder=" 🔍 Search for a model...", show_label=False)
64
- with gr.Row():
65
  gr.Markdown("Model sizes (in billions of parameters)", elem_classes="text-sm")
66
  param_range_1 = gr.Checkbox(label="~1.5", value=False)
67
  param_range_2 = gr.Checkbox(label="~3", value=False)
 
3
 
4
  # Define the columns for the UGI Leaderboard
5
  UGI_COLS = [
6
+ '#P', 'Model', 'UGI 🏆', 'Willingness👍', 'Unruly', 'Internet', 'CrimeStats', 'Stories/Jokes', 'PolContro'
7
  ]
8
 
9
  # Load the leaderboard data from a CSV file
 
57
  demo = gr.Blocks()
58
 
59
  with demo:
60
+ gr.Markdown("## UGI Leaderboard", elem_classes="text-lg text-center")
61
+ gr.Markdown("""
62
+ 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.
63
+
64
+ Willingness: A more narrow score, solely measuring the LLM's willingness to answer controversial questions.
65
+
66
+ Unruly: Knowledge of activities that are generally frowned upon.
67
+
68
+ Internet: Knowledge of various internet information, from professional to deviant.
69
+
70
+ CrimeStats: Knowledge of crime statistics which are uncomfortable to talk about.
71
+
72
+ Stories/Jokes: Ability to write offensive stories and jokes.
73
+
74
+ PolContro: Knowledge of politically/socially controversial information.
75
+ """)
76
  with gr.Column():
77
  with gr.Row():
78
  search_bar = gr.Textbox(placeholder=" 🔍 Search for a model...", show_label=False)
79
+ with gr.Row(variant="compact"):
80
  gr.Markdown("Model sizes (in billions of parameters)", elem_classes="text-sm")
81
  param_range_1 = gr.Checkbox(label="~1.5", value=False)
82
  param_range_2 = gr.Checkbox(label="~3", value=False)