#knowledge-distillation Repositories
Discover 35 active open source GitHub repositories tagged with #knowledge-distillation, accumulating 102,336 total stars (averaging 2,923 stars per project). Leading this topic is titanwings/distilly with 26,745 stars.
35 repositories total
Distilly โ Distill how they think into reusable Skills for any Agent or Bot. Formerly Colleague Skill (originally โColleague Skillโ).
Distill high-value content from books, long-form videos, podcasts, and more into executable Agent Skills
Some scripts for object detection and code with improvement ideas; please see readme.md for details.
A treasure chest for visual classification and recognition powered by PaddlePaddle
Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.
Implementation of Segnet, FCN, UNet, PSPNet and other models in Keras.
SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime
A coding-free framework built on PyTorch for reproducible deep learning studies. PyTorch Ecosystem. ๐ 28 knowledge distillation methods presented at TPAMI, CVPR, ICLR, ECCV, NeurIPS, ICCV, AAAI, etc. have been implemented so far. ๐ Trained models, training logs, and configurations are available to ensure reproducibility and benchmarking.
This repository collects papers for "A Survey on Knowledge Distillation of Large Language Models". We break down KD into Knowledge Elicitation and Distillation Algorithms, and explore the Skill & Vertical Distillation of LLMs.
Collection of recent methods on (deep) neural network compression and acceleration.
A curated collection of papers, technical reports, frameworks, and tools for on-policy distillation (OPD) of large language models
An Extendible (General) Continual Learning Framework based on Pytorch - official codebase of Dark Experience for General Continual Learning
sanoTTS (เคธเคพเคจเฅ = โsmallโ in Nepali): a 294kโ2.27M-parameter neural TTS system that runs on a $3 chip, in the browser, or in Python, with low-latency streaming.
[ICCV 2023] MI-GAN: A Simple Baseline for Image Inpainting on Mobile Devices
The repo for "Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator"
A curated collection of papers and resources on On-Policy Distillation for Large Language Models.
Summary, Code for Deep Neural Network Quantization
From teacher to tiles โ a from-scratch LLM distillation & serving engine: custom Triton/CUDA kernels, FSDP distillation, paged-KV continuous batching, speculative decoding, a Rust gateway, a JAX oracle, and interpretability tooling.
Frequently Asked Questions
What is the most popular #knowledge-distillation repository on GitHub?
The top ranked open source #knowledge-distillation project on GitHub is titanwings/distilly with 26,745 stars. Distilly โ Distill how they think into reusable Skills for any Agent or Bot. Formerly Colleague Skill (originally โColleague Skillโ).
Which programming languages are most used in #knowledge-distillation repositories?
Among the top ranked #knowledge-distillation projects on GitHub, the most common programming languages are Python, Jupyter Notebook, C.
How is the #knowledge-distillation repository ranking calculated?
We track 35 active open source repositories tagged with #knowledge-distillation (500+ stars), totaling 102,336 stars with an average of 2,923 stars per repository. Rankings update daily from the GitHub API.