Any-to-Any
Transformers
Safetensors
qwen2_5_vl
image-text-to-text
custom_code
text-generation-inference
Instructions to use modelscope/Nexus-Gen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use modelscope/Nexus-Gen with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("modelscope/Nexus-Gen", trust_remote_code=True) model = AutoModelForMultimodalLM.from_pretrained("modelscope/Nexus-Gen", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download assets/illustrations/architecture.png from modelscope/Nexus-Gen: direct link, hf CLI and curl.
- Browser
- Download file 567 kB
-
https://huggingface.co/modelscope/Nexus-Gen/resolve/main/assets/illustrations/architecture.png
- Command line
-
hf download hf://modelscope/Nexus-Gen/assets/illustrations/architecture.png
-
curl -L -o architecture.png https://huggingface.co/modelscope/Nexus-Gen/resolve/main/assets/illustrations/architecture.png
567 kB

- Xet hash:
- f875c875d22e133a705774914164dda30046b1265b1c411dfec9241ef51a80c0
- Size of remote file:
- 567 kB
- SHA256:
- f1c25ffc3402814c00e66c4b7d611d47670577082de4e7f89759ecf82e489b24
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.