{"library":"model-compression-toolkit","title":"Model Compression Toolkit","description":"A Model Compression Toolkit (MCT) for neural networks, supporting quantization, pruning, and knowledge distillation. Current version is 2.6.0. Released monthly on PyPI.","language":"python","status":"active","last_verified":"Fri May 01","install":{"commands":["pip install model-compression-toolkit"],"cli":{"name":"mct","version":"sh: 1: mct: not found"}},"imports":["from model_compression_toolkit import pytorch_post_training_quantization","from model_compression_toolkit import pytorch_post_training_quantization as ptq"],"auth":{"required":false,"env_vars":[]},"quickstart":{"code":"import torch\nfrom model_compression_toolkit import pytorch_post_training_quantization as ptq\n\ntmodel = torch.nn.Linear(10, 5)\ntmodel.eval()\nrepresentative_dataset = [torch.randn(1, 10) for _ in range(5)]\nquantized_model, quantization_info = ptq.pytorch_post_training_quantization(\n    model=tmodel,\n    representative_data_gen=representative_dataset,\n    target_platform_name='default'\n)\nprint('Quantization completed, model size saved.')\n","lang":"python","description":"Basic post-training quantization on a PyTorch model using representative data.","tag":null,"tag_description":null,"last_tested":null,"results":[]},"compatibility":null}