Visual Question Answering
Transformers
Safetensors
cvrr_merged
feature-extraction
cvrr
custom_code
latent-reasoning
Instructions to use dmis-lab/Gemma4-31B-CVRR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dmis-lab/Gemma4-31B-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/Gemma4-31B-CVRR", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("dmis-lab/Gemma4-31B-CVRR", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download native_backbone/processor_config.json from dmis-lab/Gemma4-31B-CVRR: direct link, hf CLI and curl.
- Browser
- Download file 1.69 kB
-
https://huggingface.co/dmis-lab/Gemma4-31B-CVRR/resolve/main/native_backbone/processor_config.json
- Command line
-
hf download hf://dmis-lab/Gemma4-31B-CVRR/native_backbone/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/dmis-lab/Gemma4-31B-CVRR/resolve/main/native_backbone/processor_config.json
1.69 kB
| { | |
| "audio_ms_per_token": 40, | |
| "audio_seq_length": 750, | |
| "feature_extractor": { | |
| "dither": 0.0, | |
| "feature_extractor_type": "Gemma4AudioFeatureExtractor", | |
| "feature_size": 128, | |
| "fft_length": 512, | |
| "fft_overdrive": false, | |
| "frame_length": 320, | |
| "hop_length": 160, | |
| "input_scale_factor": 1.0, | |
| "max_frequency": 8000.0, | |
| "mel_floor": 0.001, | |
| "min_frequency": 0.0, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "per_bin_mean": null, | |
| "per_bin_stddev": null, | |
| "preemphasis": 0.0, | |
| "preemphasis_htk_flavor": true, | |
| "return_attention_mask": true, | |
| "sampling_rate": 16000 | |
| }, | |
| "image_processor": { | |
| "do_convert_rgb": true, | |
| "do_normalize": false, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_mean": [ | |
| 0.0, | |
| 0.0, | |
| 0.0 | |
| ], | |
| "image_processor_type": "Gemma4ImageProcessor", | |
| "image_seq_length": 280, | |
| "image_std": [ | |
| 1.0, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "max_soft_tokens": 280, | |
| "patch_size": 16, | |
| "pooling_kernel_size": 3, | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098 | |
| }, | |
| "image_seq_length": 280, | |
| "processor_class": "Gemma4Processor", | |
| "video_processor": { | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "do_sample_frames": true, | |
| "image_mean": [ | |
| 0.0, | |
| 0.0, | |
| 0.0 | |
| ], | |
| "image_std": [ | |
| 1.0, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "max_soft_tokens": 70, | |
| "num_frames": 32, | |
| "patch_size": 16, | |
| "pooling_kernel_size": 3, | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "return_metadata": false, | |
| "video_processor_type": "Gemma4VideoProcessor" | |
| } | |
| } | |