Implementation of a custom architecture on nanoRWKV: A nanoGPT-style adaptation of the RWKV Language Model, which combines the simplicity of RNNs with GPT-level performance for large language models (LLMs).
Support for running RWKV 4/5 World models locally from the command line for conversation and small talk. Support is provided through the prompt.txt defines the prompt for the model. Support Mirostat algorithm and traditional Top-k, Top-p for decoding.
LineRWKV predictive compression of hyperspectral images
A repository to deploy RWKV model to serverless APIs such as Runpod.io
使用 rwkv 架構的大型語言模型運作的 Discord 聊天機器人，擁有辨識維基百科條目名並將其當作關鍵字抽取出的能力，並且還會將此關鍵字用於爬取維基百科，並將條目內容回傳給自身參考。近期更新串接API版本。
tinygrad port of the RWKV large language model.
SORSA: Singular Values and Orthonormal Regularized Singular Vectors Adaptation of Large Language Models
RWKV-TS: Beyond Traditional Recurrent Neural Network for Time Series Tasks
Restore-RWKV: Efficient and Effective Medical Image Restoration with RWKV
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
LLaMa/RWKV onnx models, quantization and testcase
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
Add a description, image, and links to the rwkv topic page so that developers can more easily learn about it.
To associate your repository with the rwkv topic, visit your repo's landing page and select "manage topics."