This repo is an exploratory experiment to enable frozen pretrained RWKV language models to accept speech modality input. We followed the idea of SLAM_ASR and used the RWKV language model as the LLM…

字幕共享计划

The libmamba based solver for conda.

A simple Python Pydantic model for Honkai: Star Rail parsed data from the Mihomo API.

A highly customizable, full scale web backend for web-rwkv, built on axum with websocket protocol.

Implementation of the RWKV language model in pure WebGPU/Rust.

RWKV infctx trainer, for training arbitary context sizes, to 10k and beyond!

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,…

Github Trending榜高赞与趣味项目速览。主理人：同济子豪兄

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

👺 基于Yolov5的Apex Legend游戏 AI 辅瞄外挂

ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型

ChatGPT 中文语料库 对话语料 小说语料 客服语料 用于训练大模型

实现Blip2RWKV+QFormer的多模态图文对话大模型，使用Two-Step Cognitive Psychology Prompt方法，仅3B参数的模型便能够出现类人因果思维链。对标MiniGPT-4，ImageBind等图文对话大语言模型，力求以更小的算力和资源实现更好的智能效果。

RWKV centralised docs for the community

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

闻达：一个大型语言模型调用平台。目前支持chatGLM-6B、chatRWKV、chatYuan和chatGLM-6B模型下的chatPDF（自建知识库查找）

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

为ChatGLM设计的微调数据集生成工具，速来制作自己的猫娘。

基于ChatGLM-6B + LoRA的Fintune方案

人工精调的中文对话数据集和一段chatglm的微调代码

RWKV is a 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, …