aigc-apps / aigc-apps/VideoX-Fun
--resume_from_checkpoint or take weights from a safetensor
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2.3k
- Forks
- 188
- Avg merge
- 2d 22h
- Merged PRs (30d)
- 3
Description
Hi,
I wonder if a lora training can be continue, copying weights from a lora safetensors, that it was already trained.
I usually do --resume_from_checkpoint= as parameter in the train_lora.sh, and it works really well, however I dont keep all the bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt for all the checkpoints.
Is there any way to resume from the lora_diffusion_pytorch_model.safetensors ?
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
Start with train_lora.sh and trace how --resume_from_checkpoint consumes checkpoint files. Compare that flow with the available lora_diffusion_pytorch_model.safetensors file. The work is complete when the project clearly supports, or explicitly rejects, continuing training from those weights and documents the required inputs.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100