luzhongqiu

agents

An Open-source Framework for Autonomous Language Agents

alignment-handbook

Robust recipes for to align language models with human and AI preferences

Alpaca-CoT

We extend CoT data to Alpaca to boost its reasoning ability. We are constantly expanding our collection of instruction-tuning data, and integrating more LLMs together for easy use. （我们将CoT数据扩展到Alpaca以提高其推理能力，同时我们将不断收集更多的instruction-tuning数据集,并在我们框架下集成进更多的LLM。）

alpaca-lora

Instruct-tune LLaMA on consumer hardware

awesome-marketing-datascience

Collection of useful Datascience things across the web

chatglm.cpp

C++ implementation of ChatGLM-6B & ChatGLM2-6B & more LLMs

Chinese-LLaMA-Alpaca-2

中文LLaMA-2 & Alpaca-2大模型二期项目 + 16K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs, including 16K long context models)

chineseocr_lite

超轻量级中文ocr，支持竖排文字识别, 支持ncnn、mnn、tnn推理 ( dbnet(1.8M) + crnn(2.5M) + anglenet(378KB)) 总模型仅4.7M

ColossalAI

Making large AI models cheaper, faster and more accessible

ComfyUI

The most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface.

corpora

Parallel corpora for the biomedical domain

excalidraw

Virtual whiteboard for sketching hand-drawn like diagrams

FastChat

The release repo for "Vicuna: An Open Chatbot Impressing GPT-4"

funNLP

GPT-4-LLM

GraphGPT

Extrapolating knowledge graphs from unstructured text using GPT-3 🕵️‍♂️

knowledge-graph-from-GPT-3

Using GPT-3 to organize and access information, and generate questions. Long term goal is to make an agent-like research assistant.

LabelFast

中文世界的NLP自动标注开源工具，简单样本，交给LabelFast。

llama.cpp

Port of Facebook's LLaMA model in C/C++

llama2.c

Inference Llama 2 in one file of pure C

MiniGPT-4

MiniGPT-4: Enhancing Vision-language Understanding with Advanced Large Language Models

nevergrad

A Python toolbox for performing gradient-free optimization

nougat

Implementation of Nougat Neural Optical Understanding for Academic Documents

open_flamingo

An open-source framework for training large multimodal models

qlora

QLoRA: Efficient Finetuning of Quantized LLMs

RWKV-Runner

A RWKV management and startup tool, full automation, only 6MB. 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.

TigerBot

TigerBot: A multi-language multi-task LLM

trl

Train transformer language models with reinforcement learning.

vocab-coverage

语言模型中文认知能力分析

wenda

闻达：一个LLM调用平台。为小模型外挂知识库查找和设计自动执行动作，实现不亚于于大模型的生成能力