Stars
OpenWRT 应用商店 固件(Raspberry Pi5 | 4B | 3B+，NanoPi R2S | R4S | R5C | R5S，FastRhino R68S，Orange Pi R1Plus，x86/64) 源码更新自动编译(周更)
Fast and memory-efficient exact attention
Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"
ClickHouse® is a real-time analytics database management system
llama3 implementation one matrix multiplication at a time
Repository hosting code for "Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations" (https://arxiv.org/abs/2402.17152).
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…
A configurable, tunable, and reproducible library for CTR prediction https://fuxictr.github.io
Shoggoth is a peer-to-peer network for publishing and distributing open-source Artificial Intelligence
Curating a list of AutoML-related research, tools, projects and other resources
A professional cross-platform SSH/Sftp/Shell/Telnet/Tmux/Serial terminal.
Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
Minimal web UI for GeminiPro.
Using Low-rank adaptation to quickly fine-tune diffusion models.
《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。
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.
搜索、推荐、广告、用增等工业界实践文章收集（来源：知乎、Datafuntalk、技术公众号）
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…
Google Research
SASRec: Self-Attentive Sequential Recommendation
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
Prompt Engineering | Prompt Versioning | Use GPT or other prompt based models to get structured output. Join our discord for Prompt-Engineering, LLMs and other latest research