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

feat: add support for vLLM Mistral Tokenizer #142

Merged
merged 1 commit into from
Sep 27, 2024
Merged

feat: add support for vLLM Mistral Tokenizer #142

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
3 changes: 3 additions & 0 deletions lmformatenforcer/integrations/vllm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
try:
import torch
import vllm
from vllm.transformers_utils.tokenizer import MistralTokenizer
from transformers import PreTrainedTokenizerBase
except ImportError:
raise ImportError('vllm is not installed. Please install it with "pip install vllm"')
Expand Down Expand Up @@ -35,6 +36,8 @@ def build_vllm_token_enforcer_tokenizer_data(tokenizer: Union[vllm.LLM, PreTrain
# There are many classes that can be passed here, this logic should work on all of them.
if hasattr(tokenizer, 'get_tokenizer'):
tokenizer = tokenizer.get_tokenizer()
if isinstance(tokenizer, MistralTokenizer):
return build_token_enforcer_tokenizer_data(tokenizer)
if hasattr(tokenizer, 'tokenizer'):
tokenizer = tokenizer.tokenizer
return build_token_enforcer_tokenizer_data(tokenizer)
Expand Down
Loading