Supported Model Formats

1. CNTK Models: Models saved in Microsoft Cognitive Toolkit format.
2. Flax Models: Models created with Flax, a neural network library for JAX.
3. GGUF Models: General-purpose model format using GGUF.
4. Keras Models:
   • Legacy Keras Models: Older Keras models, often saved with HDF5.
   • Keras 3 Models: Newer Keras models using the latest Keras version.
   • Keras Pickle Models: Keras models saved with Python pickle.
   • Keras H5 Models: Models in HDF5 format, compatible with legacy and newer versions.
   • Keras Weights: Separate files storing only model weights.
   • Keras JSON: Models saved in JSON format for architecture storage.
   • Keras Metadata: Auxiliary files that store metadata for Keras models.
5. KModel: KModel files specific to Keras.
6. LightGBM Models: Gradient boosting models using LightGBM.
7. MS Lite Models: Microsoft Lite format for lightweight models.
8. MXNet Models: Models saved in Apache MXNet format.
9. Numpy Models:
   • Numpy Array Files: Arrays saved in .npy format.
   • Numpy Zip Files: Arrays compressed in .npz format.
   • Numpy Pickle Files: Arrays serialized with pickle.
10. OM Models: Models in Huawei Ascend's OM format.
11. ONNX Models: Models saved in Open Neural Network Exchange format.
12. OpenVINO Models:
    • OpenVINO Binary Files: Compiled binary files for OpenVINO.
    • OpenVINO XML Files: XML files storing OpenVINO model metadata.
13. Pickle Files: Models serialized using Python's pickle.
14. PyTorch Models:
    • Various PyTorch Versions: Models saved with different PyTorch versions.
    • TorchScript: PyTorch's format for serializing models.
    • PyTorch Archives: Archived files containing serialized models.
15. RKNN Models: Models saved in Rockchip Neural Network (RKNN) format.
16. Safetensors:
    • Safetensors Models: Models saved using safetensors format for secure tensor storage.
    • Safetensors Index: Index files for safetensors.
17. SKLearn Models: Scikit-learn models serialized for deployment.
18. TensorRT Models: NVIDIA's TensorRT models optimized for inference.
19. TensorFlow Models:
    • SavedModel: TensorFlow's standard saved model format.
    • TFHub: Models from TensorFlow Hub.
    • MetaGraph: TensorFlow's MetaGraph format for exporting graphs.
    • TFLite: Lightweight format for mobile and embedded devices.
    • TFJS: TensorFlow.js format for models running in the browser.
20. Torch Models: General format for PyTorch models.
21. JSON Files: JSON-based configurations or model descriptions.