You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
if llm_kwargs["llm_model"] in ["glm-4v"]:
have_recent_file, image_paths = have_any_recent_upload_image_files(chatbot)
if not have_recent_file:
chatbot.append((inputs, "没有检测到任何近期上传的图像文件,请上传jpg格式的图片,此外,请注意拓展名需要小写"))
yield from update_ui(chatbot=chatbot, history=history, msg="等待图片") # 刷新界面
return
if have_recent_file:
inputs = make_media_input(inputs, image_paths)
chatbot[-1] = [inputs, ""]
yield from update_ui(chatbot=chatbot, history=history)
Class | 类型
大语言模型
Feature Request | 功能请求
现状
glm-4
和glm-3-turbo
支持,上述模型没有直接解读图片的能力。glm-4v
可以解读图片(虽然)。glm-4v
的上下文长度仅有2kglm-4v
尚无完整支持。bridge_zhipu.py (Line 77)
bridge_all.py
(暂无
glm-4v
相关代码)com_zhipuglm.py
(似乎也没有呢)
参考
GLM-4模型文档节选(完整文档)
另:GLM-4V完整文档
The text was updated successfully, but these errors were encountered: