Github Pages for personal website

Learn Modern AI Assisted Python with Type Hints

Scalable RL solution for advanced reasoning of language models

Reproduce R1 Zero on Logic Puzzle

Clean, minimal, accessible reproduction of DeepSeek R1-Zero

Implementing the 4 agentic patterns from scratch

A reading list on LLM based Synthetic Data Generation 🔥

🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.

Codes and Data for ACL 2024 Paper "Faithful Logical Reasoning via Symbolic Chain-of-Thought".

The project page for "LOGIC-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning"

Awesome Lists for Tenure-Track Assistant Professors and PhD students. (助理教授/博士生生存指南)

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

Skywork series models are pre-trained on 3.2TB of high-quality multilingual (mainly Chinese and English) and code data. We have open-sourced the model, training data, evaluation data, evaluation me…

AgentTuning: Enabling Generalized Agent Abilities for LLMs

Create Customized Software using Natural Language Idea (through Multi-Agent Collaboration)

🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo

中英文敏感词、语言检测、中外手机/电话归属地/运营商查询、名字推断性别、手机号抽取、身份证抽取、邮箱抽取、中日文人名库、中文缩写库、拆字词典、词汇情感值、停用词、反动词表、暴恐词表、繁简体转换、英文模拟中文发音、汪峰歌词生成器、职业名称词库、同义词库、反义词库、否定词库、汽车品牌词库、汽车零件词库、连续英文切割、各种中文词向量、公司名字大全、古诗词库、IT词库、财经词库、成语词库、地名词库、…

SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks

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.

A playbook for systematically maximizing the performance of deep learning models.

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

QLoRA: Efficient Finetuning of Quantized LLMs

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

汇总那些ChatGPT的平替们，仅汇总那些开源代码/模型文件以及对话语料，闭源或者部分闭源的暂时不在统计范围内

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

Making large AI models cheaper, faster and more accessible

Aligning pretrained language models with instruction data generated by themselves.