Spaces:

allenai
/

reward-bench

Running

natolambert commited on 15 days ago

Commit

1089af2

1 Parent(s): 75fed94

clean looks

Files changed (1) hide show

leaderboard/md.py CHANGED Viewed

@@ -102,9 +102,7 @@ For more details, see the [dataset](https://huggingface.co/datasets/allenai/rewa
 pacific_tz = pytz.timezone("America/Los_Angeles")
 current_time = datetime.now(pacific_tz).strftime("%H:%M %Z, %d %b %Y")
-TOP_TEXT = """# RewardBench: Evaluating Reward Models
-### Evaluating the capabilities, safety, and pitfalls of reward models
-"""
 CAPTION_V2 = f"""The *new version* of RewardBench that is based on unseen human data and designed to be substantially more difficult!

 pacific_tz = pytz.timezone("America/Los_Angeles")
 current_time = datetime.now(pacific_tz).strftime("%H:%M %Z, %d %b %Y")
+TOP_TEXT = """# RewardBench: Evaluating Reward Models"""
 CAPTION_V2 = f"""The *new version* of RewardBench that is based on unseen human data and designed to be substantially more difficult!