Skip to content

Fix: Handle empty prompt gracefully in make_seq2seq_fields with warning #484

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
markknoffler wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix: Handle empty prompt gracefully in make_seq2seq_fields with warning #484

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 13 additions & 0 deletions gemma/gm/data/_functional.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,8 @@

"""Functional version of the `gm.data` transforms."""

import warnings

from etils import enp
import flax
import jax
Expand Down Expand Up @@ -134,6 +136,17 @@ def make_seq2seq_fields(
Returns:
The input, target and mask, all of length `prompt_len + response_len - 1`.
"""
# Handle empty prompt: issue warning and use a default BOS token (2) as fallback.
if len(prompt) == 0:
warnings.warn(
'Empty prompt provided. Using default BOS token (2) as prompt. '
'Empty prompts are not recommended for sequence-to-sequence training.',
UserWarning,
stacklevel=2,
)
# Use BOS token (2) as a default prompt token for seq2seq compatibility.
prompt = np.array([2], dtype=np.int32)

# Concatenate the prompt and response tokens.
sequence = np.concatenate([prompt, response])

Expand Down