#Distillation
Showing 34 of 34 repositories tagged #distillation, ranked by stars
Implement a reasoning LLM in PyTorch from scratch, step by step
Awesome Knowledge Distillation
A unified inference and post-training framework for accelerated video generation.
Awesome Knowledge-Distillation. 分类整理的知识蒸馏paper(2014-2021)。
The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation" and [TPAMI'23] "ViTPose++: Vision Transformer for Generic Body Pose Estimation"
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.
All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.
Reinforcement Learning via Self-Distillation (SDPO)
♾️ 开源数字永生框架 — 从聊天记录蒸馏任何人的七维数字分身。支持微信/飞书/iMessage/Telegram等12+平台，7种角色模板，对齐 OpenClaw Soul Spec 标准。一行指令让你的AI学会蒸馏。
Generate High-Quality Synthetics, Train, Measure, and Evaluate in a Single Pipeline
[ICML 2026] Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation" & Causal Forcing++
Awesome List for On-Policy Distillation
Prompt engineering for developers
irresponsible innovation. Try now at https://chat.dev/
A curated collection of papers, technical reports, frameworks, and tools for on-policy distillation (OPD) of large language models
Official implementation of AsymFlow, pi-Flow, GMFlow
A curated archive of breakthroughs in Agents, Architecture, Training, RAG, and On-Device AI.
The Official Repo for "Quick Start Guide to Large Language Models"
PMetal: high-performance Apple Silicon framework for local LLM inference, LoRA/QLoRA fine-tuning, serving, quantization, and MLX/Metal acceleration.
Pytorch implementation of "EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation"
FasterAI: Prune and Distill your models with FastAI and PyTorch
ComfyUI Nodes for AsymFlow and pi-Flow
[ICLR 2022] Code for Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation (GLNN)
Pytorch implementation of CVPR2021 paper: SuperMix: Supervising the Mixing Data Augmentation
[ECCV2022] Factorizing Knowledge in Neural Networks
Adaptive, interpretable wavelets across domains (NeurIPS 2021)
A recipe that will walk you through using either Meta Llama 3.1 405B or OpenAI GPT-4o deployed on Azure AI to generate a synthetic dataset using UC Berkeley's Gorilla project RAFT method.
Official Implementation for the Paper [AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent](https://arxiv.org/abs/2602.03955)
Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language Models
Interpretable and efficient predictors using pre-trained language models. Scikit-learn compatible.
赛博人物库 · 把中国互联网最有辨识度的人物蒸馏成 AI Skill / Claude Code Skill / LLM character distillation
(ACL 2025 Main) Distilling RAG for SLMs from LLMs to Transfer Knowledge and Mitigate Hallucination via Evidence and Graph-based Distillation
AI-powered personalized IELTS corpus distillation — install-only skill (zero-backend Agent loop) + runnable backend with QMD-RAG. 7-stage pipeline producing schema-validated corpus.json & static profile site.
A place to evaluate public models