All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.
- computer-vision
- contrastive-learning
- deep-learning
- distillation
142,187 visible repositories in the index
25–48 of 79 · Most stars
All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.
A PyTorch-based knowledge distillation toolkit for natural language processing
OpenMMLab Model Compression Toolbox and Benchmark.
A coding-free framework built on PyTorch for reproducible deep learning studies. PyTorch Ecosystem. 🏆28 knowledge distillation methods presented at TPAMI, CVPR, ICLR, ECCV, NeurIPS, ICCV, AAAI, etc are implemented so far. 🎁 Trained models, training logs and configurations are available for ensuring the reproducibiliy and benchmark.
PaddleSlim is an open-source library for deep model compression and architecture search.
ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation (NeurIPS 2023 Spotlight)
yolov3 yolov4 channel and layer pruning, Knowledge Distillation 层剪枝,通道剪枝,知识蒸馏
(NeurIPS 2024 Oral 🔥) Improved Distribution Matching Distillation for Fast Image Synthesis
NLP DNN Toolkit - Building Your NLP DNN Models Like Playing Lego
Qwen-Image-Lightning: Speed up Qwen-Image model with distillation
♾️ 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。
Reinforcement Learning via Self-Distillation (SDPO)
NVIDIA FastGen: Fast Generation from Diffusion Models
Industrial audio online policy distillation (OPD) training stack for ASR and TTS, distilling compact audio models from stronger teacher models.
致你忘不掉的那个TA,你们干大模型都是码圣 It's giving rebirth era. Welcome to Digital Life 1.0. 🫶
An Open Source Toolkit For LLM Distillation
[TMLR] Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
🔥 On-Policy Self-Distillation in Diffusion Models
[ICML 2026] Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation" & Causal Forcing++
The repository host gives no description.
A distilled Segment Anything (SAM) model capable of running real-time with NVIDIA TensorRT
A minimalist SOTA LaTeX OCR model with only 20M parameters, running in browser. Full training pipeline available for self-reproduction. | 超轻量SOTA LaTeX公式识别模型,仅20M参数量,可在浏览器中运行。训练全流程代码开源,以便自学复现。
Official implementation for "Towards a Unified Self-Distillation Framework for Large Language Models" (https://arxiv.org/abs/2605.06597).
Generate High-Quality Synthetics, Train, Measure, and Evaluate in a Single Pipeline