squall/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

set&get llm internal tokenizer instead of the TokenizerGroup (#2741)

Browse Source 
Co-authored-by: shujunhua1 <shujunhua1@jd.com>
This commit is contained in:
dancingpipi 2024-02-05 06:25:36 +08:00 committed by GitHub
parent 5ed704ec8c
commit 51cd22ce56
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/entrypoints/llm.py
View File

@ -111,13 +111,13 @@ class LLM:
def get_tokenizer(
self) -> Union[PreTrainedTokenizer, PreTrainedTokenizerFast]:
return self.llm_engine.tokenizer
return self.llm_engine.tokenizer.tokenizer
def set_tokenizer(
self,
tokenizer: Union[PreTrainedTokenizer, PreTrainedTokenizerFast],
) -> None:
self.llm_engine.tokenizer = tokenizer
self.llm_engine.tokenizer.tokenizer = tokenizer
def generate(
self,