Feature Extraction
Transformers
Safetensors
English
penguinvl_vision_encoder
multi-modal
large-language-model
vision-language-model
vision-encoder
custom_code
Instructions to use Cyril666/Penguin-Encoder-Init with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Cyril666/Penguin-Encoder-Init with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Cyril666/Penguin-Encoder-Init", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Cyril666/Penguin-Encoder-Init", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "auto_map": { | |
| "AutoImageProcessor": "image_processing_penguinvl.PenguinVLImageProcessor" | |
| }, | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_processor_type": "PenguinVLImageProcessor", | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "max_tokens": 16384, | |
| "min_tokens": 16, | |
| "patch_size": 14, | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098 | |
| } | |