Skip to content
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

Jump to bottom

Fixing stream stopping at wrong location #898

Merged
merged 2 commits into from
May 17, 2024
Merged

Fixing stream stopping at wrong location #898

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
66ee234
Fixing stream stopping at wrong location
isamu-isozaki May 17, 2024
a24f50b
Ran precommit
isamu-isozaki May 17, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
28 changes: 19 additions & 9 deletions outlines/generate/api.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -340,15 +340,6 @@ def token_generator() -> Iterator[Union[List[str], str, List[List[str]]]]:
return
generated_token_ids = sequence.token_ids[:, -num_generated:]
generated_sequences = self.tokenizer.decode(generated_token_ids)
next_tokens = [
token[len(sequence) :] if not stop else ""
for token, sequence, stop in zip(
generated_sequences,
previously_generated_sequences,
is_stop_at_reached,
)
]
previously_generated_sequences = generated_sequences
if stop_sequences:
is_stop_at_reached = [
stop
Expand All @@ -360,6 +351,25 @@ def token_generator() -> Iterator[Union[List[str], str, List[List[str]]]]:
)
]

generated_sequences = [
self.format_sequence(
self.strip_stop_sequences(sequence, stop_sequences)
)
if stop
else sequence
for sequence, stop in zip(
generated_sequences, is_stop_at_reached
)
]
next_tokens = [
token[len(sequence) :]
for token, sequence, stop in zip(
generated_sequences,
previously_generated_sequences,
is_stop_at_reached,
)
]
previously_generated_sequences = generated_sequences
# We reshape the output to (batch_size, sample_size)
output: List[List[str]] = list()
for i in range(batch_size):
Expand Down