Lightning-AI / Lightning-AI/lit-llama
Export finetuned lora weights to base model
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 6.1k
- Forks
- 517
- PR merge metrics
- No merged PRs in 30d
Description
Hi
Is there an easy way to map the finetuned lora weights to the base litllama model? I see that the lora finetuning saves checkpoints that include only the finetuned weights ("lora.A" and "lora.B"). I couldn't find a method that maps these back to the original base litllama model.
Thank you!
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
No file, test, or entry point is named. Start by locating the LoRA fine-tuning checkpoint save/load path and the base litllama model code, then define completion as an export path that maps the saved lora.A and lora.B weights into a usable base-model checkpoint.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100