search

modelscope / ms-swift

Use PEFT or Full-parameter to finetune 300+ LLMs or 80+ MLLMs. (Qwen2, GLM4v, Internlm2.5, Yi, Llama3.1, Llava-Video, Internvl2, MiniCPM-V-2.6, Deepseek, Baichuan2, Gemma2, Phi3-Vision, ...)
https://swift.readthedocs.io/zh-cn/latest/Instruction/index.html
Apache License 2.0
3.41k stars 292 forks source link

GLM4V运行时报错 #1611

Closed det-tu closed 2 weeks ago

det-tu commented 1 month ago

Describe the bug What the bug is, and how to reproduce, better with screenshots(描述bug以及复现过程，最好有截图) 命令：CUDA_VISIBLE_DEVICES=0 swift infer --model_type glm4v-9b-chat --model_id_or_path ../MLLM/GLM4V-9b --template_type glm4v 报错：AssertionError: failed to match chat template, please explicit set chat_template_config image

Your hardware and system info Write your system info like CUDA version/system/GPU/torch version here(在这里给出硬件信息和系统信息，如CUDA版本，系统，GPU型号和torch版本等)

image

Additional context Add any other context about the problem here(在这里补充其他信息)

Jintao-Huang commented 1 month ago

lmdeploy是什么版本

det-tu commented 1 month ago

lmdeploy是什么版本

lmdeploy是0.5.2，swift是2.3.0.dev0

det-tu commented 1 month ago

lmdeploy是什么版本

请问下是版本问题吗，看文档里没写swift对应该装哪个版本的lmdeploy

demoninpiano commented 1 month ago

我用swift2.4.0.dev0， lmdeploy=0.5.3也没办法跑通glm4v 的lmdeploy inference代码

问题是AttributeError: 'AsyncEngine' object has no attribute 'vl_encoder' 看了下lmdeploy代码， 应该是lmdeploy没有成功建立vlAsyncEngine这个类

Jintao-Huang commented 3 weeks ago

Describe the bug What the bug is, and how to reproduce, better with screenshots(描述bug以及复现过程，最好有截图) 命令：CUDA_VISIBLE_DEVICES=0 swift infer --model_type glm4v-9b-chat --model_id_or_path ../MLLM/GLM4V-9b --template_type glm4v 报错：AssertionError: failed to match chat template, please explicit set chat_template_config image

Your hardware and system info Write your system info like CUDA version/system/GPU/torch version here(在这里给出硬件信息和系统信息，如CUDA版本，系统，GPU型号和torch版本等)

image

Additional context Add any other context about the problem here(在这里补充其他信息)

这个问题已经修复了