AnswerDotAI / AnswerDotAI/fsdp_qlora
Results after running
- Dominant language
- Jupyter Notebook
- Stars
- 1.6k
- Forks
- 201
- PR merge metrics
- No merged PRs in 30d
Description
Why do I lose a lot of pre training weights after running, and how can I use the trained files for downstream tasks？
Contributor guide
No contributing guide indexed for this repository
Research direction
The issue names no files, tests, or entry points and provides only screenshots from a training run. Start by examining the run outputs and the repository's training workflow; determine whether the apparent loss of pretrained weights is expected and how the trained files can support downstream tasks. Done means both questions have documented, reproducible answers.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- jupyter-notebook
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100