Shane commited on
Commit
db557f0
1 Parent(s): ee71995
Files changed (1) hide show
  1. src/md.py +2 -4
src/md.py CHANGED
@@ -23,17 +23,15 @@ For reproductability, we use greedy decoding for all model generation as default
23
  - **Large**: HREF has the largest evaluation size among similar benchmarks, making its evaluation more reliable.
24
  - **Contamination-resistant**: HREF's evaluation set is hidden and uses public models for both the baseline model and judge model, which makes it completely free of contamination.
25
  - **Task Oriented**: Instead of naturally collected instructions from the user, HREF contains instructions that are written specifically targetting 8 distinct categories that are used in instruction tuning, which allows it to provide more insights about how to improve language models.
26
-
27
  ## Contact Us
28
  TODO
29
  """
30
- """
31
 
32
  # Get Pacific time zone (handles PST/PDT automatically)
33
  pacific_tz = pytz.timezone('America/Los_Angeles')
34
  current_time = datetime.now(pacific_tz).strftime("%H:%M %Z, %d %b %Y")
35
 
36
  TOP_TEXT = f"""# HREF: Human Reference Guided Evaluation for Instructiong Following
37
- [Code]() | [Validation Set]() | [Human Agreement Set]() | [Results]() | [Paper]() | Total models: {{}} | * Unverified models | ⚠️ Dataset Contamination | Last restart (PST): {current_time}
38
-
39
 
 
23
  - **Large**: HREF has the largest evaluation size among similar benchmarks, making its evaluation more reliable.
24
  - **Contamination-resistant**: HREF's evaluation set is hidden and uses public models for both the baseline model and judge model, which makes it completely free of contamination.
25
  - **Task Oriented**: Instead of naturally collected instructions from the user, HREF contains instructions that are written specifically targetting 8 distinct categories that are used in instruction tuning, which allows it to provide more insights about how to improve language models.
 
26
  ## Contact Us
27
  TODO
28
  """
 
29
 
30
  # Get Pacific time zone (handles PST/PDT automatically)
31
  pacific_tz = pytz.timezone('America/Los_Angeles')
32
  current_time = datetime.now(pacific_tz).strftime("%H:%M %Z, %d %b %Y")
33
 
34
  TOP_TEXT = f"""# HREF: Human Reference Guided Evaluation for Instructiong Following
35
+ [Code]() | [Validation Set]() | [Human Agreement Set]() | [Results]() | [Paper]() | Total models: {{}} | Last restart (PST): {current_time}
36
+ """
37