Generate High-Quality Synthetics, Train, Measure, and Evaluate in a Single Pipeline
Repository Index
142,187 visible repositories in the index
1–6 of 6 · Most stars
mobilev2-yolov5s剪枝、蒸馏,支持ncnn,tensorRT部署。ultra-light but better performence!
- mobile-yolov5s
- distillation
- pruning
- ncnn
sanoTTS (सानो = 'small' in Nepali): 294k–2.27M-parameter neural TTS that runs on a $3 chip, in the browser, or in Python with low-latency streaming.
高质量中文预训练模型集合:最先进大模型、最快小模型、相似度专门模型
- pretrained-models
- chinese
- bert
- roberta
EfficientSAM3 compresses SAM3 into lightweight, edge-friendly models via progressive knowledge distillation for fast promptable concept segmentation and tracking.
- artificial-intelligence
- computer-vision
- edge-ai
- efficient-ai
A Pytorch Knowledge Distillation library for benchmarking and extending works in the domains of Knowledge Distillation, Pruning, and Quantization.
- knowledge-distillation
- model-compression
- pruning
- quantization