Skip to content
New issue

Have a question about this project? # for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “#”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? # to your account

Multiturn chat demo 多轮对话的示例 #410

Open
wants to merge 2 commits into
base: main
Choose a base branch
from

Conversation

gxlover0625
Copy link

主要贡献

  • 修改readme中没有多轮对话示例的问题
  • 将所有的推理代码封装成类的形式,提升封装性

具体工作

设计了Qwen2VL类,将推理代码进一步的封装,
用户只需要通过传递自然语言形式的query、图片的路径imgs、前文的对话history给chat接口,就可以完成多轮对话。简单如下:

chat_model = Qwen2VL(model_path="local path/repo id")

# First turn
history = None
response, history = chat_model.chat(query="hello", history=history)
print(response, history)

# Second turn
# For image type, (imgae_url, local_image_path, base64)
# For image count, ([image], [image1, image2], ...)
response, history = chat_model.chat(query="please describe the image", imgs=["image_url"], history=history)
print(response, history)

对于新手小白会更加友好,无需关心如何构造messages,就跟我们跟gpt打交道一样,用自然语言表述我们的需求、在浏览器端上传图片,同时保留历史对话。

自我介绍

最后小小的自我介绍一下,我是一名浙江大学的研究生,同时也在淘天集团的大模型岗位实习过,主要工作集中在多模态大模型,对Qwen2VLQwenVLInternVL比较熟悉,因为学校开设的开源课程,对开源社区贡献比较感兴趣,第一次提交pr,无论是否被merge,都算是一次勇敢的尝试哈哈

# for free to join this conversation on GitHub. Already have an account? # to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant