A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 and reasoning techniques.

🔥中文 prompt 精选🔥，ChatGPT 使用指南，提升 ChatGPT 可玩性和可用性！🚀

Examples and guides for using the OpenAI API

ToRA is a series of Tool-integrated Reasoning LLM Agents designed to solve challenging mathematical reasoning problems by interacting with tools [ICLR'24].

Large Language Model based Multi-Agents: A Survey of Progress and Challenges

Official implementation of DPFM @ ICLR 2024 paper "Autonomous Data Selection with Language Models for Mathematical Texts" (Huggingface Daily Papers: https://huggingface.co/papers/2402.07625)

A multi-purpose LLM framework for RAG and data creation.

[ACL 2024 Findings] MathBench: A Comprehensive Multi-Level Difficulty Mathematics Evaluation Dataset

Tools for merging pretrained large language models.

A toolkit for inference and evaluation of 'mixtral-8x7b-32kseqlen' from Mistral AI

The paper list of the 86-page paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.

leaked prompts of GPTs

This repository contains the paper list for the paper: Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents

Generative Agents: Interactive Simulacra of Human Behavior

Train transformer language models with reinforcement learning.

方糖全栈路线图2023，为「从螺丝钉到一人企业」补全技能栈

LongLLaMA is a large language model capable of handling long contexts. It is based on OpenLLaMA and fine-tuned with the Focused Transformer (FoT) method.

An open-source educational chat model from ICALK, East China Normal University. 开源中英教育对话大模型。(通用基座模型，GPU部署，数据清理) 致敬: LLaMA, MOSS, BELLE, Ziya, vLLM

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Aligning Large Language Models with Human: A Survey

Official implementation of our NeurIPS 2023 paper "Augmenting Language Models with Long-Term Memory".

🤖 AgentVerse 🪐 is designed to facilitate the deployment of multiple LLM-based agents in various applications, which primarily provides two frameworks: task-solving and simulation

Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

旨在对当前主流LLM进行一个直观、具体、标准的评测

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

Benchmarking large language models' complex reasoning ability with chain-of-thought prompting

This repo includes ChatGPT prompt curation to use ChatGPT better.

Official github repo for C-Eval, a Chinese evaluation suite for foundation models [NeurIPS 2023]

A Multi-Turn Dialogue Corpus based on Alpaca Instructions