Skip to content

Refactor all_text to remaining_text #1658

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

Merged
merged 4 commits into from
Sep 26, 2024
Merged

Refactor all_text to remaining_text #1658

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
478a770
Refactor all_text to remaining_text
xu-song Aug 6, 2024
ee73aec
Merge branch 'main' into patch-1
abetlen Aug 8, 2024
cfe98dd
Merge branch 'main' into patch-1
abetlen Sep 19, 2024
340e58a
Merge branch 'main' into patch-1
abetlen Sep 26, 2024
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
8 changes: 4 additions & 4 deletions llama_cpp/llama.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1519,15 +1519,15 @@ def logit_bias_processor(

if stream:
remaining_tokens = completion_tokens[returned_tokens:]
all_text = self.detokenize(
remaining_text = self.detokenize(
remaining_tokens,
prev_tokens=prompt_tokens + completion_tokens[:returned_tokens],
)
any_stop = [s for s in stop_sequences if s in all_text]
any_stop = [s for s in stop_sequences if s in remaining_text]
if len(any_stop) > 0:
end = min(all_text.index(stop) for stop in any_stop)
end = min(remaining_text.index(stop) for stop in any_stop)
else:
end = len(all_text)
end = len(remaining_text)

token_end_position = 0
for token in remaining_tokens:
Expand Down