Improving Convolutional Networks via Attention Transfer (ICLR 2017)
- pytorch
- knowledge-distillation
- attention
- deep-learning
142,187 visible repositories in the index
49–72 of 123 · Most stars
Improving Convolutional Networks via Attention Transfer (ICLR 2017)
NLP DNN Toolkit - Building Your NLP DNN Models Like Playing Lego
Run local LLMs like llama, deepseek-distill, kokoro and more inside your browser
Qwen-Image-Lightning: Speed up Qwen-Image model with distillation
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.
Efficient computing methods developed by Huawei Noah's Ark Lab
不在身边的时候,TA 还在这里。Upload real chat logs, rebuild a digital persona — open-source AI companion with persona distillation, an emotion engine, 11 LLM providers, and a graduation mechanism.
Official PyTorch implementation of "EdgeSAM: Prompt-In-the-Loop Distillation for On-Device Deployment of SAM"
♾️ 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)
flixel is a free Actionscript (Flash) library that I distilled from a variety of Flash games that I've worked on over the last couple years, including Gravity Hook, Fathom and Canabalt. It's primary function is to provide some useful base classes that you can extend to make your own game objects.
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
Learning Lightweight Lane Detection CNNs by Self Attention Distillation (ICCV 2019)
🔥 On-Policy Self-Distillation in Diffusion Models
Distill your LLM traces into a fast hybrid System 1 models. Open-source ML + LLM inference with calibrated deferral.
[ICML 2026] Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation" & Causal Forcing++
A Claude Code skill for clean, honest dashboard UI: KPI tiles, charts, date pickers, ranked lists, states, layouts and a screenshot QA pass. Distilled from 127 shipped dashboards.
The repository host gives no description.
This is the repository for the distill web framework
A distilled Segment Anything (SAM) model capable of running real-time with NVIDIA TensorRT