DRAFT-UV-27 - Fine-tune TinyLlama and Qwen2.5-coder models for Magistrala and Prism codebase #29
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
|
We will not change TinyLlama with Qwen unless we prove that fine-tuning is equally simple. So please go through fine-tuning procedure and compare the approaches. This tool: https://github.com/yamadashy/repopack can be useful to pack Magistrala and CocosAI repos for fine-tuning of moels, but probably there are other tools - so also existing tools and approaches must be studied in order to find the most suitable one. |
Signed-off-by: JeffMboya <[email protected]>
|
Let's keep TinyLlama for now, it is super fast on CPU, which is good for demos. |
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Outdated suggestions cannot be applied.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.
What type of PR is this?
This is a feature
What does this do?
This PR fine tunes TinyLlama:1.1b and Qwen2.5-coder:1.5b for Magistrala and Prism codebase
Which issue(s) does this PR fix/relate to?
Have you included tests for your changes?
No, manually tested
Did you document any new/modified features?
No
Notes
Fine tuned model under test located at: https://huggingface.co/J1997/fine_tuned_qwen_2.5_coder_1.5b