LongMIT: Essential Factors in Crafting Effective Long Context Multi-Hop Instruction Datasets

基于大模型的智能对话客服工具，支持微信、拼多多、千牛、哔哩哔哩、抖音企业号、抖音、抖店、微博聊天、小红书专业号运营、小红书、知乎等平台接入，可选择 GPT3.5/GPT4.0/ 懒人百宝箱 （后续会支持更多平台），能处理文本、语音和图片，通过插件访问操作系统和互联网等外部资源，支持基于自有知识库定制企业 AI 应用。

Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024)

Must-read Papers on LLM Agents.

Research Trends in LLM-guided Multimodal Learning.

使用peft库，对chatGLM-6B/chatGLM2-6B实现4bit的QLoRA高效微调，并做lora model和base model的merge及4bit的量化（quantize）。

PromptCBLUE: a large-scale instruction-tuning dataset for multi-task and few-shot learning in the medical domain in Chinese

Collection of papers, benchmarks and newest trends in the domain of End-to-end ToDs

😎 Awesome list of tools and projects with the awesome LangChain framework

Tuning LLMs with no tears💦; Sample Design Engineering (SDE) for more efficient downstream-tuning.

This project collects awesome resources (e.g., papers, open-source models) for large language model (LLM)

Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

A collection of open-source dataset to train instruction-following LLMs (ChatGPT,LLaMA,Alpaca)

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

ChatGLM-6B 指令学习|指令数据|Instruct

ChatGPT爆火，开启了通往AGI的关键一步，本项目旨在汇总那些ChatGPT的开源平替们，包括文本大模型、多模态大模型等，为大家提供一些便利

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

骆驼(Luotuo): Open Sourced Chinese Language Models. Developed by 陈启源 @ 华中师范大学 & 李鲁鲁 @ 商汤科技 & 冷子昂 @ 商汤科技

Chat on GPT public event - 18 April 2023

Convert natural language to LaTeX within Overleaf using LLMs

A project page template for academic papers. Demo at https://eliahuhorwitz.github.io/Academic-project-page-template/

ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

Inference code for Llama models