Skip to content

Fix tokenization edge case where llama output does not start with a space #1375

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 3 commits into from
May 4, 2024
Merged

Fix tokenization edge case where llama output does not start with a space #1375

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
239200a
Fix tokenization edge case where llama output does not start with a s…
noamgat Apr 23, 2024
935e532
Update _internals.py
noamgat Apr 23, 2024
5c9d560
Merge branch 'main' into patch-1
abetlen May 4, 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
4 changes: 2 additions & 2 deletions llama_cpp/_internals.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -203,7 +203,7 @@ def detokenize(self, tokens: List[int], special: bool = False) -> bytes:
# NOTE: Llama1 models automatically added a space at the start of the prompt
# this line removes a leading space if the first token is a beginning of sentence token
return (
output[1:] if len(tokens) > 0 and tokens[0] == self.token_bos() else output
output[1:] if len(tokens) > 0 and tokens[0] == self.token_bos() and output[0:1] == b' ' else output
)

# Extra
Expand Down Expand Up @@ -812,4 +812,4 @@ def sample(
def accept(self, ctx_main: _LlamaContext, id: int, apply_grammar: bool):
if apply_grammar and self.grammar is not None:
ctx_main.grammar_accept_token(self.grammar, id)
self.prev.append(id)
self.prev.append(id)