OpenGVLab / OpenGVLab/Ask-Anything
Question about freeze_mhra
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 3.4k
- Forks
- 268
- PR merge metrics
- No merged PRs in 30d
Description
Can I train with freeze_mhra=True? (in config_7b_stage1.py)
In other words can I totally freeze the visual encoder and train a model that works?
Thanks
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 by reading config_7b_stage1.py and tracing the freeze_mhra=True setting through the training configuration. Determine whether the visual encoder can be totally frozen while training a working model, and document the result or the additional requirements needed.
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
- 20/100