Visual Question Answering
Transformers
Safetensors
cvrr_merged
feature-extraction
cvrr
custom_code
latent-reasoning
Instructions to use dmis-lab/Gemma3-4B-CVRR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dmis-lab/Gemma3-4B-CVRR with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "visual-question-answering" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("visual-question-answering", model="dmis-lab/Gemma3-4B-CVRR", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("dmis-lab/Gemma3-4B-CVRR", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download native_backbone/tokenizer.json from dmis-lab/Gemma3-4B-CVRR: direct link, hf CLI and curl.
- Browser
- Download file 33.4 MB
-
https://huggingface.co/dmis-lab/Gemma3-4B-CVRR/resolve/main/native_backbone/tokenizer.json
- Command line
-
hf download hf://dmis-lab/Gemma3-4B-CVRR/native_backbone/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/dmis-lab/Gemma3-4B-CVRR/resolve/main/native_backbone/tokenizer.json
33.4 MB
- Xet hash:
- c4c7aa84fb94a696d78f2bde62590a25b6741b7365ed842f9310b5dcab71d95d
- Size of remote file:
- 33.4 MB
- SHA256:
- 4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.