-
Notifications
You must be signed in to change notification settings - Fork 433
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 LoRA-GA #2650
Merged
Merged
Support LoRA-GA #2650
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
@@ -0,0 +1,24 @@ | |||
CUDA_VISIBLE_DEVICES=0 \ |
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.
Add here to show how to infer
swift/llm/argument/tuner_args.py
Outdated
@@ -29,6 +29,12 @@ class TunerArguments: | |||
use_rslora (bool): Flag to indicate if RSLora is used. Default is False. | |||
use_dora (bool): Flag to indicate if Dora is used. Default is False. | |||
init_weights (str): Initialization method for weights of supported tuners. Default is 'true'. | |||
lora_ga_batch_size (int): Batch size when estimate gradient for LoRA GA. Default is 2. |
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.
doc zh/en
tastelikefeet
approved these changes
Dec 14, 2024
tastelikefeet
added a commit
to tastelikefeet/swift
that referenced
this pull request
Dec 14, 2024
* main: Support LoRA-GA (modelscope#2650) fix swift/Infinity-Instruct (modelscope#2651) update truncation_strategy (modelscope#2647) fix bugs (modelscope#2645) Fix post encode (modelscope#2643) fix app-ui (modelscope#2641) fix bugs & support openbuddy llama3.3 & update docs (modelscope#2638) fix dataset (modelscope#2636) fix add_default_tag (modelscope#2631) support reward model (modelscope#2628)
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
PR type
PR information
Support LoRA-GA. Use
--init_weights lora-ga
.