Implement a reasoning LLM in PyTorch from scratch, step by step
Repository Index
142,187 visible repositories in the index
1–9 of 9 · Most stars
PyTorch implementation of various methods for continual learning (XdG, EWC, SI, LwF, FROMP, DGR, BI-R, ER, A-GEM, iCaRL, Generative Classifier) in three different scenarios.
- deep-learning
- artificial-neural-networks
- continual-learning
- lifelong-learning
利用pytorch实现图像分类的一个完整的代码,训练,预测,TTA,模型融合,模型部署,cnn提取特征,svm或者随机森林等进行分类,模型蒸馏,一个完整的代码
Improving Convolutional Networks via Attention Transfer (ICLR 2017)
- pytorch
- knowledge-distillation
- attention
- deep-learning
Efficient computing methods developed by Huawei Noah's Ark Lab
- knowledge-distillation
- model-compression
- binary-neural-networks
- pruning
Official PyTorch implementation of "EdgeSAM: Prompt-In-the-Loop Distillation for On-Device Deployment of SAM"
- on-device-ai
- segment-anything
- coreml
Distill your LLM traces into a fast hybrid System 1 models. Open-source ML + LLM inference with calibrated deferral.
mobilev2-yolov5s剪枝、蒸馏,支持ncnn,tensorRT部署。ultra-light but better performence!
- mobile-yolov5s
- distillation
- pruning
- ncnn
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