You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
parser.add_argument(
"--reward-model",
type=lambda x: x.replace("facebook/opt-", ""),
default="350m",
choices=("350m"),
help="Which facebook/opt-* model to use for Reward (step 2)",
)
The choices argument is mistakenly defined as a string instead of a tuple. This causes choices to be interpreted as a sequence of characters ('3', '5', '0', 'm') rather than a single valid choice.
Solution:
To fix the issue, define choices as a tuple by adding a trailing comma:
choices=("350m",)
This ensures that choices is correctly interpreted as a tuple containing a single element, "350m".
The text was updated successfully, but these errors were encountered:
Issue:
In the original code:
e2e_rlhf.py
line 68The choices argument is mistakenly defined as a string instead of a tuple. This causes choices to be interpreted as a sequence of characters
('3', '5', '0', 'm')
rather than a single valid choice.Solution:
To fix the issue, define choices as a tuple by adding a trailing comma:
choices=("350m",)
This ensures that choices is correctly interpreted as a tuple containing a single element, "350m".
The text was updated successfully, but these errors were encountered: