Text Classification
Transformers
Safetensors
mistral3
image-text-to-text
nvfp4
modelopt
fp4
guardrail
safety-classifier
multimodal
8-bit precision
Instructions to use vroomfondel/Shieldstral-1.0-3B-NVFP4-ModelOpt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use vroomfondel/Shieldstral-1.0-3B-NVFP4-ModelOpt with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="vroomfondel/Shieldstral-1.0-3B-NVFP4-ModelOpt")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("vroomfondel/Shieldstral-1.0-3B-NVFP4-ModelOpt") model = AutoModelForMultimodalLM.from_pretrained("vroomfondel/Shieldstral-1.0-3B-NVFP4-ModelOpt", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "image_break_token": "[IMG_BREAK]", | |
| "image_end_token": "[IMG_END]", | |
| "image_processor": { | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_mean": [ | |
| 0.48145466, | |
| 0.4578275, | |
| 0.40821073 | |
| ], | |
| "image_processor_type": "PixtralImageProcessor", | |
| "image_std": [ | |
| 0.26862954, | |
| 0.26130258, | |
| 0.27577711 | |
| ], | |
| "patch_size": 14, | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "longest_edge": 1540 | |
| } | |
| }, | |
| "image_token": "[IMG]", | |
| "patch_size": 14, | |
| "processor_class": "PixtralProcessor", | |
| "spatial_merge_size": 2 | |
| } | |