TokenFormer

A curated list of software and architecture related design patterns.

Making large AI models cheaper, faster and more accessible

A curated and opinionated list of resources for Chief Technology Officers, with the emphasis on startups

Your ultimate Go microservices framework for the cloud-native era.

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

互联网公司技术架构，微信/淘宝/微博/腾讯/阿里/美团点评/百度/OpenAI/Google/Facebook/Amazon/eBay的架构，欢迎PR补充

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 RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.

Open-source web application framework for ASP.NET Core! Offers an opinionated architecture to build enterprise software solutions with best practices on top of the .NET. Provides the fundamental infrastructure, cross-cutting-concern implementations, startup templates, application modules, UI themes, tooling and documentation.