Shane
commited on
Commit
•
db557f0
1
Parent(s):
ee71995
fixed bug
Browse files
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: {{}} |
|
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 |
|