Visual Question Answering
Transformers
Safetensors
cvrr_merged
feature-extraction
cvrr
custom_code
latent-reasoning
Instructions to use dmis-lab/Gemma4-12B-CVRR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dmis-lab/Gemma4-12B-CVRR with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("visual-question-answering", model="dmis-lab/Gemma4-12B-CVRR", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("dmis-lab/Gemma4-12B-CVRR", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "name": "CVRR-Gemma-4-12B", | |
| "base_model": "google/gemma-4-12B-it", | |
| "ell_star": 32, | |
| "recurrent_layer": 33, | |
| "upper_decoder_start": 34, | |
| "inference_T": 4, | |
| "inference_beta": 0.33, | |
| "lora_rank": 32, | |
| "lora_alpha": 12.0, | |
| "lora_dropout": 0.01, | |
| "checkpoint_step": 500, | |
| "format": "cvrr_native_plus_merged_transition_v1", | |
| "merged_weight_dtype": "float32", | |
| "native_weight_bytes": 23919460448, | |
| "status": "gpu_vstar_comparison_completed", | |
| "upload_ready": true, | |
| "hub_model_id": "dmis-lab/Gemma4-12B-CVRR" | |
| } | |