rwkv - 技术专题

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.

ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.

A RWKV management and startup tool, full automation, only 8MB. And provides an interface compatible with the OpenAI API. RWKV is a large language model that is fully open source and available for commercial use.

闻达：一个LLM调用平台。目标为针对特定环境的高效内容生成，同时考虑个人和中小企业的计算资源局限性，以及知识安全和私密性问题

仅需Python基础，从0构建大语言模型；从0逐步构建GLM4\Llama3\RWKV6， 深入理解大模型原理

llama and other large language models on iOS and MacOS offline using GGML library.

INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model

Believe in AI democratization. llama for nodejs backed by llama-rs, llama.cpp and rwkv.cpp, work locally on your laptop CPU. support llama/alpaca/gpt4all/vicuna/rwkv model.

Android 17 local LLM prototype with Jetpack Compose and ONNX Runtime for offline AI inference experiments.

The all-in-one RWKV runtime box with embed, RAG, AI agents, and more.

LLaMa/RWKV onnx models, quantization and testcase

Swift library to work with llama and other large language models.

A benchmark for spaced repetition schedulers/algorithms

A curated list of papers on the applications of RWKV in computer vision. Please raise an issue if you suggest new qualified project.

VisualRWKV is the visual-enhanced version of the RWKV language model, enabling RWKV to handle various visual tasks.

PDF解析（文字，章节，表格，图片，参考），基于大模型(ChatGLM2-6B, RWKV)+langchain+streamlit的PDF问答，摘要，信息抽取

Making offline AI models accessible to all types of edge devices.

Restore-RWKV: Efficient and Effective Medical Image Restoration with RWKV

Cross-platform, local-first RWKV chat built with Flutter for Android, iOS, Windows, macOS, and Linux.

RWKV-TS: Beyond Traditional Recurrent Neural Network for Time Series Tasks