Instructions to use immanuelpeter/Gemma4-31B-Vision with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use immanuelpeter/Gemma4-31B-Vision with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="immanuelpeter/Gemma4-31B-Vision")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("immanuelpeter/Gemma4-31B-Vision") model = AutoModel.from_pretrained("immanuelpeter/Gemma4-31B-Vision", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from immanuelpeter/Gemma4-31B-Vision: direct link, hf CLI and curl.
- Browser
- Download file 446 Bytes
-
https://huggingface.co/immanuelpeter/Gemma4-31B-Vision/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://immanuelpeter/Gemma4-31B-Vision/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/immanuelpeter/Gemma4-31B-Vision/resolve/main/preprocessor_config.json
446 Bytes
| { | |
| "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, | |
| "processor_class": "AutoImageProcessor" | |
| } | |