neromous

RWKV_Pytorch

This is an inference framework for the RWKV large language model implemented purely in native PyTorch. The official native implementation is overly complex and lacks extensibility. Let's join the flexible PyTorch ecosystem and open-source it together!

RWKV-PEFT

gptcore

Fast modular code to create and train cutting edge LLMs

RWKV-LM-LISA

Layerwise Importance Sampled AdamW for RWKV, aiming for RWKV-5 and 6. SFT, Aligning(DPO,ORPO). Cuda and Rocm6.0. can train 7b on 24GB GPU!

QAnything

Question and Answer based on Anything.

WikiChat

WikiChat stops the hallucination of large language models by retrieving data from Wikipedia.

special_token_json2binidx_tool

A tookit converts a jsonl dataset into a binidx dataset, accompanied by the ssg-dataset-format definition and the addition of special tokens.

RWKV-infctx-trainer

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

RWKV-Light-API

A Lightweight and Extensible RWKV API for Inference

TrainChatGalRWKV

RWKV_UNKNOWN

RWKV implementation with pure torch and deepspeed.

AgentsChainer-ALM

由RWKV\Fay\Wenda等多方联合打造的一体型高度拟人心智化的智能体工程，拥有与生物智能相似的脑神经科学结构原理机制与学习认知规律，同时是一款可用于研究各种人体或类人体行为及心理的模拟器，当前版本为ALM版，即Automatic learning machine

RWKV-LM

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.

RWKV-Drama

基于RWKV模型的角色扮演，实际上是个改的妈都不认识的 RWKV_Role_Playing

rwkv-contrib

Chinese-LLaMA-Alpaca

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

AgentGPT

🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.

Llama-X

Open Academic Research on Improving LLaMA to SOTA LLM

lit-llama

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

BELLE

BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）

llama-chat

Chat with Meta's LLaMA models at home made easy

Open-Assistant

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

status-mobile

a free (libre) open source, mobile OS for Ethereum

puck

ClojureScript wrapper around Pixi.js, plus other game dev utils

specter

Clojure(Script)'s missing piece

emacs-application-framework

EAF, an extensible framework that revolutionizes the graphical capabilities of Emacs

emacs-webkit

An Emacs Dynamic Module for WebKit, aka a fully fledged browser inside emacs

reagent-material-ui

Reagent wrapper for MUI (formerly Material UI) v5

reitit

A fast data-driven routing library for Clojure/Script

oz

Data visualizations in Clojure and ClojureScript using Vega and Vega-lite