🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
TranslatedThe next employee you want to distill doesn't have to be a coworker. Distill anyone's way of thinking: mental models, decision heuristics, expression DNA. Distill how anyone thinks.
TranslatedDistilly — Distill how they think into reusable Skills for any Agent or Bot. Formerly Colleague Skill (formerly 同事 Skill).
TranslatedDistill high-value content from books, long-form videos, podcasts, and more into executable Agent Skills
- agent-workflows
- ai-skills
- automation
- book-to-skill
Implement a reasoning LLM in PyTorch from scratch, step by step
A treasure chest for visual classification and recognition powered by PaddlePaddle
OpenClaw-RL: Train any agent simply by talking
- async
- memory-systems
- open-claw
- openclaw-skills
A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.
The power of webpack, distilled for the rest of us.
A unified inference and post-training framework for accelerated video generation.
Curated list of Agent Skills centered on people, relationships, commemorative scenes, and methodological perspectives
Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.
Awesome Knowledge Distillation
- knowledge-distillation
- knowledge-transfer
- teacher-student
- co-training
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
TranslatedWriting DNA Distiller - distill and recreate any writing style as an agent skill
DAMO-YOLO: a fast and accurate object detection method with some new techs, including NAS backbones, efficient RepGFPN, ZeroHead, AlignedOTA, and distillation enhancement.
Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.
- knowledge-distillation
- model-compression
- quantization
- pretrained-models
AI Powered Knowledge Graph Generator
Collection of AWESOME vision-language models for vision tasks
Simplify deployments in Elixir with OTP releases!
"Effective Whole-body Pose Estimation with Two-stages Distillation" (ICCV 2023, CV4Metaverse Workshop)
- controlnet
- knowledge-distillation
- pose-estimation
- stable-diffusion-webui
Images to inference with no labeling (use foundation models to train supervised models).
SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime
- low-precision
- pruning
- sparsity
- auto-tuning
Awesome Knowledge-Distillation. 分类整理的知识蒸馏paper(2014-2021)。