Problem Description

I want to fine tune Video-LLaVA to make it uncensored

Here's the model in a hosted playground: https://replicate.com/nateraw/video-llava

Link to finetune lora script:
https://github.com/PKU-YuanGroup/Video-LLaVA/blob/main/scripts/v1_5/finetune_lora.sh

And their existing video tuning dataset:
https://github.com/PKU-YuanGroup/Video-LLaVA/blob/main/TRAIN_AND_VALIDATE.md

Acceptance Criteria

Set up a fine tuning repo for Video-LLaVa
Model: https://github.com/PKU-YuanGroup/Video-LLaVA

• Ideally in python
• If you tell me the optimal data structure, I can provide the dataset
• It should be set up such that:
  I can import my dataset & train this on a cloud provider
  I can use a script to deploy it to a host

If this works out I can hire you to fine tune this image to text model as well:
https://replicate.com/yorickvp/llava-13b/versions