[Bug]: 模型回答时极大概率出现�

[GitHub-lql]

Model Series

Qwen2.5

What are the models used?

Qwen2.5-3B-Instruct

What is the scenario where the problem happened?

使用tensorrt进行模型加速

Is this a known issue?

• I have followed the GitHub README.
• I have checked the Qwen documentation and cannot find an answer there.
• I have checked the documentation of the related framework and cannot find useful information.
• I have searched the issues and there is not a similar one.

Information about environment

无

Log output

无

Description

例如进行回答时，问题：关于4K显示器的支持情况及分辨率和刷新率的信息？

大模型回答：�记本通常支持通过HDMI、DP等接口连接4K显示器并输出相应的分辨率和刷新率。

[GitHub-lql]

在输出添加了decode(errors='ignore')没有变化

[jklj077]

please provide steps to reproduce. do you have the generated token ids?

[gloomy-emerald]

Same problem, gone after updating ollama.