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

Fix llama gguf converter #31575

Merged
merged 1 commit into from
Jun 26, 2024
Merged

Fix llama gguf converter #31575

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
22 changes: 21 additions & 1 deletion src/transformers/integrations/ggml.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -632,7 +632,27 @@ def decoder(self, replacement, add_prefix_space):
return decoders.Sequence(sequence)

def converted(self):
tokenizer = super().converted()
# Copied partly from converted method in SpmConverter class
tokenizer = self.tokenizer(self.proto)

# Tokenizer assemble
normalizer = self.normalizer(self.proto)
if normalizer is not None:
tokenizer.normalizer = normalizer

replacement = "▁"
add_prefix_space = True
if hasattr(self.original_tokenizer, "add_prefix_space"):
add_prefix_space = self.original_tokenizer.add_prefix_space

pre_tokenizer = self.pre_tokenizer(replacement, add_prefix_space)
if pre_tokenizer is not None:
tokenizer.pre_tokenizer = pre_tokenizer

tokenizer.decoder = self.decoder(replacement, add_prefix_space)
post_processor = self.post_processor()
if post_processor:
tokenizer.post_processor = post_processor

# HACK: patch the llama-3 tokenizer to use the correspinding pre-tokenizer
# and normalizer
Expand Down
Loading