OpenGVLab / OpenGVLab/Ask-Anything

Train vit and Q-Former again, during which the LLM is frozen

Open
#256 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
3.4k
Forks
268
PR merge metrics
No merged PRs in 30d

Description

Thank you for your great work, would like to ask I want to train vit and Q-Former again with my own data on the basis of the stage4 post-training weights, during which the LLM is frozen, what should I do? If I train on the stage2 training framework, how do I import the weights after the stage4 training?

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by locating the stage2 training framework and the stage4 post-training weights workflow mentioned in the issue. Determine how ViT and Q-Former training with a frozen LLM is configured, how stage4 weights would be imported, and document a reproducible procedure using the requester's own data.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.