xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-23 09:05:42 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix] Fix multi-round chat error when mistral tokenizer is used (#12859)

Browse Source 
Signed-off-by: Zifei Tong <zifeitong@gmail.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
This commit is contained in:
zifeitong 2025-02-07 23:04:34 -08:00 committed by GitHub
parent cc01223f3b
commit d01f66b039
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 10 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
vllm/transformers_utils/tokenizers/mistral.py
View File

@ -291,6 +291,16 @@ class MistralTokenizer:
from mistral_common.protocol.instruct.request import ( from mistral_common.protocol.instruct.request import (
ChatCompletionRequest) ChatCompletionRequest)
# mistral-common requires AssistantMessage content to be string [1].
#
# [1]: https://github.com/mistralai/mistral-common/blob/f4a06998b75ed78bbf5aaf569590b772ea26c9f6/src/mistral_common/protocol/instruct/messages.py#L80
for message in messages:
if message.get("role") == "assistant":
content = message.get("content")
if isinstance(content, list):
content = "\n".join(chunk.get("text") for chunk in content)
message["content"] = content
request = ChatCompletionRequest(messages=messages, request = ChatCompletionRequest(messages=messages,
tools=tools) # type: ignore[type-var] tools=tools) # type: ignore[type-var]
encoded = self.mistral.encode_chat_completion(request) encoded = self.mistral.encode_chat_completion(request)