-
Notifications
You must be signed in to change notification settings - Fork 390
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
support internlm-xcomposer2d5-7b #1932
Conversation
|
||
## Lora Model | ||
|
||
InternLM-XComposer-2.5 trained the LoRA weights for webpage creation and article writing. As TurboMind backend doesn't support slora, only one LoRA model can be deployed at a time, and the LoRA weights need to be merged when deploying the model. LMDeploy provides the corresponding conversion script, which is used as follows: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Since we support plora, can we support lora directly without merging it?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
For specific task, there are actually two LoRA weights(plora + lora) and we can only support one.
https://huggingface.co/internlm/internlm-xcomposer2d5-7b/blob/main/build_mlp.py#L227-L243
Currently, the hf model can't be used with transformers api due to InternLM/InternLM-XComposer#354 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM after some typos are fixed
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
Motivation
support internlm-xcomposer2d5-7b
related issues #1920