Image-Text-to-Text
PEFT
Safetensors
medical
vision-language
surgical-ai
pituitary-surgery
qwen2-vl
lora
spatial-localization
conversational
Instructions to use mmrech/pitvqa-qwen2vl-spatial with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use mmrech/pitvqa-qwen2vl-spatial with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-VL-2B-Instruct") model = PeftModel.from_pretrained(base_model, "mmrech/pitvqa-qwen2vl-spatial") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- a8abecc949b0114c5188e4945c032244ddd059d6610377334771ca7ccccd875b
- Size of remote file:
- 11.4 MB
- SHA256:
- 19097527d5277c96d93c0ca1a66b36fa77e5491e99c84c6a27db02bba1ff2288
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.