IntelLabs / IntelLabs/lvlm-interpret
Usage for other hf models & fine-tuned models
- Dominant language
- Jupyter Notebook
- Stars
- 0
- Forks
- 0
- PR merge metrics
- No merged PRs in 30d
Description
Hi @shaoyent-IL 👋
First of all, great work!
I have noticed that the link to the HF Space demo no longer works.
Also, I would like to use the repo for the successor model [LLaVA-OneVision-7b](https://huggingface.co/llava-hf/llava-onevision-qwen2-7b-ov-hf) and another model called [Phi-3.5-Vision-instruct](https://huggingface.co/microsoft/Phi-3.5-vision-instruct) (uses remote code). Do you think this is possible out of the box?
Furthermore, I would find it interesting to look at the attention maps for fine-tuned models, which are available in the form of pytorch .ckpt. Is it possible to directly load the .ckpt files in the repo?
Thanks for your help 😊
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.