Core ML tools contain supporting tools for Core ML model conversion, editing, and validation.
-
Updated
Aug 18, 2026 - Python
Core ML tools contain supporting tools for Core ML model conversion, editing, and validation.
Pytorch to Keras/Tensorflow/TFLite conversion made intuitive
Convert 3d model (STL/IGES/STEP/OBJ/FBX) to gltf and compression
Gradio based tool to run opensource LLM models directly from Huggingface
A practical lab for exploring Apple's Core AI framework, model assets, specialization, and on-device inference.
Automated converter for ONNX models (particularly ESRGAN) to RKNN format for Rockchip NPUs. Features include Docker-based conversion and GitHub Actions automation.
A flexible utility for converting tensor precision in PyTorch models and safetensors files, enabling efficient deployment across various platforms.
Demonstrates how to divide a DL model into multiple IR model files (division) and introduce a simplest way to implement a custom layer works with OpenVINO IR models.
Serving YOLOv8 detection model with tf-serving
Transpile PyTorch modules to runnable JAX or MLX artifacts through ONNX, generating backend Python code and weights.
This sample shows how to convert TensorFlow model to OpenVINO IR model and how to quantize OpenVINO model.
This project demonstrates how to download a model from Hugging Face, convert it to GGUF format, and upload it back to Hugging Face using a Colab notebook.
MLX Porting Toolkit — an agent-guided, evidence-gated pipeline (scaffold → convert → parity → benchmark) plus a portable skill for porting PyTorch/Hugging Face models to Apple MLX.
Evidence-bounded framework for testing whether model transformations preserve declared operational behavior.
UMC — The ffmpeg of AI models. Convert any model format to any other format (GGUF, ONNX, SafeTensors, CoreML, TensorRT...) without quality loss, at maximum speed, with mathematical proof. Built in Rust.
A tiny, containerized conversion appliance that attempts to convert pickles to safetensors without exposing the host to the dangers of actually loading the pickles.
Tools and experiments for converting Human Activity Recognition (HAR) models to TensorFlow Lite for efficient on-device inference on mobile and wearable devices.
Model operations workspace discover models, explore datasets, and fine tune with LoRA/QLoRA
Add a description, image, and links to the model-conversion topic page so that developers can more easily learn about it.
To associate your repository with the model-conversion topic, visit your repo's landing page and select "manage topics."