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.

Sign up for GitHub

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

Jump to bottom

Question about fine-tuning LLaMa #2

Open
LeoArtaza opened this issue Mar 18, 2023 · 1 comment
Open

Question about fine-tuning LLaMa #2

LeoArtaza opened this issue Mar 18, 2023 · 1 comment

Comments

@LeoArtaza
Copy link

I was wondering if we could fine-tune LLaMa with our own training data and then apply this to transform it into Alpaca and it would work, or would it be better to fine-tune Alpaca directly? Is it possible at all?
@sergevar
Copy link
Contributor

The dataset that the Stanford team generated has 52K entries: https://github.com/tatsu-lab/stanford_alpaca

Alpaca gives you a much better performance than raw LLaMA, so unless you have a very good dataset, it would make sense to further finetune Alpaca on your data.

Meaning, if you have just a few json files, it definitely doesn't make sense to tune LLaMA on it, it will probably be worse than the base model.

sswam added a commit to sswam/barbarella that referenced this issue Sep 22, 2024
@sswam
feat(docs): add project-claude-advice.md with task prompts
c7cea93 
- Create new file with improved task pointnetwork#1 prompt
- Add new task pointnetwork#2 prompt for structured technical overview
- Include additional task ideas based on git log analysis
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@LeoArtaza @sergevar