Instructions to use TencentBAC/U-MARVEL-Qwen3VL-4B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TencentBAC/U-MARVEL-Qwen3VL-4B-Instruct with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSeq2SeqLM processor = AutoProcessor.from_pretrained("TencentBAC/U-MARVEL-Qwen3VL-4B-Instruct") model = AutoModelForSeq2SeqLM.from_pretrained("TencentBAC/U-MARVEL-Qwen3VL-4B-Instruct", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download figures/zero_shot_image.png from TencentBAC/U-MARVEL-Qwen3VL-4B-Instruct: direct link, hf CLI and curl.
- Browser
- Download file 270 kB
-
https://huggingface.co/TencentBAC/U-MARVEL-Qwen3VL-4B-Instruct/resolve/main/figures/zero_shot_image.png
- Command line
-
hf download hf://TencentBAC/U-MARVEL-Qwen3VL-4B-Instruct/figures/zero_shot_image.png
-
curl -L -o zero_shot_image.png https://huggingface.co/TencentBAC/U-MARVEL-Qwen3VL-4B-Instruct/resolve/main/figures/zero_shot_image.png
270 kB

- Xet hash:
- 44cb5c02abe05db6a8a4f1759b74552bf07def012cfd96230a732569b6c5a1c4
- Size of remote file:
- 270 kB
- SHA256:
- 92b2ed30bba7e219bec916cbec903563a60f594bccfbc3446bb3737bc17a7e10
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.