Visual Question Answering
Transformers
Safetensors
cvrr_merged
feature-extraction
cvrr
custom_code
latent-reasoning
Instructions to use dmis-lab/Gemma3-12B-CVRR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dmis-lab/Gemma3-12B-CVRR with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("visual-question-answering", model="dmis-lab/Gemma3-12B-CVRR", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("dmis-lab/Gemma3-12B-CVRR", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| CVRR applies a learned recurrent transition to google/gemma-3-12b-it. | |
| Native dense weights are preserved; recurrent projection weights are modified | |
| by merging the trained CVRR LoRA. CVRR-specific code is additional code, not | |
| part of the original backbone distribution. See the included upstream notices. | |
| Gemma is provided under and subject to the Gemma Terms of Use found at ai.google.dev/gemma/terms | |