Skip to content
New issue

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

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

Already on GitHub? Sign in to your account

GLM4v使用Lora模型微调后,merge模型后运行报错, #1163

Open
hyyuan123 opened this issue Jun 18, 2024 · 3 comments
Open

GLM4v使用Lora模型微调后,merge模型后运行报错, #1163

hyyuan123 opened this issue Jun 18, 2024 · 3 comments

Comments

@hyyuan123
Copy link

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)

使用CUDA_VISIBLE_DEVICES=0 swift infer --ckpt_dir output/glm4v-9b-chat/v1-20240617-191301/checkpoint-150-merged/ --load_dataset_config true 运行程序,报错:
image
但是直接使用命令CUDA_VISIBLE_DEVICES=0 swift infer --ckpt_dir output/glm4v-9b-chat/v1-20240617-191301/checkpoint-150 --load_dataset_config true 运行程序,则正常运行,没有报错
之前使用框架训练internvl-v1.5版本的模型,训练和测试均无问题,想问一下出现问题的原因。怎么修改

@hyyuan123 hyyuan123 changed the title GLMV4使用Lora模型微调后,merge模型后运行报错, GLM4v使用Lora模型微调后,merge模型后运行报错, Jun 18, 2024
@tastelikefeet
Copy link
Collaborator

用的swift版本是什么

@hyyuan123
Copy link
Author

用的swift版本是什么

ms-swift ==2.1.0

@XuRui314
Copy link

请问你的loss是正常的吗

#1091 (comment)

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

No branches or pull requests

3 participants