🧑🏫 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
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.
A unified inference and post-training framework for accelerated video generation.
Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
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
"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
[ICLR 2020] Contrastive Representation Distillation (CRD), and benchmark of recent knowledge distillation methods
The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove.
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"
推荐/广告/搜索领域工业界经典以及最前沿论文集合。A collection of industry classics and cutting-edge papers in the field of recommendation/advertising/search.
- calibration
- causal-inference
- cold-start
- contrastive-learning
EasyNLP: A Comprehensive and Easy-to-use NLP Toolkit
A curated list for Efficient Large Language Models
- compression
- knowledge-distillation
- language-model
- llm
A PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility
Pytorch implementation of various Knowledge Distillation (KD) methods.
- kd-methods
- knowledge-transfer
- knowledge-distillation
- kd