Llm phi #979
Open
Llm phi #979
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
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Outdated suggestions cannot be applied.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.
A jupyter notebook to demo finetuning with the Phi3 LLM model. https://huggingface.co/docs/transformers/main/en/model_doc/phi3
We use the math_10k dataset https://github.com/AGI-Edgerunners/LLM-Adapters/tree/main
We download the dataset from github and check its hash and preprocess the dataset.
We load the phi model and prepare it for PEFT training.
Then we create a workflow that extracts the peft parameters and excludes sending the full model to the collaborators, the collaborators reconstruct the model from the original model and only modify the peft parameters. And after training and evaluation return the peft parameters again to be used with fed average.