Image-Text-to-Text
PEFT
Safetensors
graph-learning
multimodal-graphs
vision-language-model
qwen-vl
lora
node-classification
link-prediction
Instructions to use oofwite/OMG-VLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use oofwite/OMG-VLM with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-VL-Chat") model = PeftModel.from_pretrained(base_model, "oofwite/OMG-VLM") - Notebooks
- Google Colab
- Kaggle
Download visual_adapter.pth from oofwite/OMG-VLM: direct link, hf CLI and curl.
- Browser
- Download file 1.41 GB
-
https://huggingface.co/oofwite/OMG-VLM/resolve/main/visual_adapter.pth
- Command line
-
hf download hf://oofwite/OMG-VLM/visual_adapter.pth
-
curl -L -o visual_adapter.pth https://huggingface.co/oofwite/OMG-VLM/resolve/main/visual_adapter.pth
1.41 GB
- Xet hash:
- bbc8919c4c61068a15d1760174e121773d70dc1f53ccd3de8c62abceca61b12e
- Size of remote file:
- 1.41 GB
- SHA256:
- 91bca4251f224fb5449b4d71a1048d2638d434b0d9f2d39f7df861854f720481
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.