Instructions to use tarekziade/yolos-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tarekziade/yolos-tiny with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("object-detection", model="tarekziade/yolos-tiny")# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, AutoModelForObjectDetection processor = AutoImageProcessor.from_pretrained("tarekziade/yolos-tiny") model = AutoModelForObjectDetection.from_pretrained("tarekziade/yolos-tiny", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download quantize_config.json from tarekziade/yolos-tiny: direct link, hf CLI and curl.
- Browser
- Download file 887 Bytes
-
https://huggingface.co/tarekziade/yolos-tiny/resolve/main/quantize_config.json
- Command line
-
hf download hf://tarekziade/yolos-tiny/quantize_config.json
-
curl -L -o quantize_config.json https://huggingface.co/tarekziade/yolos-tiny/resolve/main/quantize_config.json
887 Bytes
| { | |
| "per_channel": true, | |
| "reduce_range": true, | |
| "per_model_config": { | |
| "model": { | |
| "op_types": [ | |
| "Slice", | |
| "Mul", | |
| "Resize", | |
| "Div", | |
| "ConstantOfShape", | |
| "Equal", | |
| "Sqrt", | |
| "Unsqueeze", | |
| "Erf", | |
| "Expand", | |
| "Sigmoid", | |
| "Gather", | |
| "Concat", | |
| "Cast", | |
| "Reshape", | |
| "Transpose", | |
| "ReduceMean", | |
| "Constant", | |
| "Conv", | |
| "Shape", | |
| "Softmax", | |
| "Pow", | |
| "MatMul", | |
| "Where", | |
| "Add", | |
| "Relu", | |
| "Sub" | |
| ], | |
| "weight_type": "QUInt8" | |
| } | |
| } | |
| } |