AI development assistant

AI-Researcher is a research project based on Stanford University's natural language processing team, aiming to assist the generation and management of research ideas through artificial intelligence technology. The tool inputs research topics through natural language and outputs a series of project proposals, ranking and filtering them to help researchers quickly find innovative and feasible research ideas. It includes modules such as related paper search, retrieval-based idea generation, idea deduplication, project proposal generation, project proposal ranking and filtering.

This GitHub repository contains the training and inference code used to replicate our winning solution in the AI ​​Math Olympiad (AIMO) Progress Award 1. Our solution consists of four main parts: a recipe for fine-tuning DeepSeekMath-Base 7B to solve mathematical problems using Tool Integrated Reasoning (TIR); two high-quality training datasets of ~1 million mathematical problems and solutions; a self-consistent decoding algorithm for generating solution candidates with code execution feedback (SC-TIR); and four carefully selected validation sets from AMC, AIME, and MATH to guide model selection and avoid overfitting to public leaderboards.

DeepLearing-Interview-Awesome-2024 is an open source interview question collection project, focusing on interview preparation in the field of deep learning algorithms and large models. This project is jointly maintained by community members and aims to provide the latest analysis of interview questions and answers to help job seekers and researchers gain an in-depth understanding of cutting-edge technologies and applications in the field of deep learning. It contains a wealth of interview questions, covering large language models, visual models, general questions and other aspects. It is a valuable resource for preparing for deep learning-related positions.

LeetCard is an AI intelligent learning tool specially designed for programming interviews. It provides a number of powerful functions, such as: OpenAI-driven intelligent prompts, which can provide accurate guidance for each exercise to ensure that you can easily master all concepts; personalized learning plan, customize the appropriate learning path according to your level; efficient question and note organization function to avoid messy and disorderly problems; smartphone flashcard function, review knowledge points anytime and anywhere; personalized control panel, set learning goals, monitor progress; detailed data analysis, view learning results, find areas for improvement. Whether you are a newbie or a veteran in programming, you can get considerate assistance here and easily cope with interview challenges.

Microsoft AI Journey is an AI skills challenge designed for developers. The activity includes two major modules: in the first module, students learn NLP, visual AI and other skills by completing a series of Azure AI service training; in the second module, they need to pass a series of task assessments and obtain Microsoft certification certificates. Completing the two modules will earn you a VIP pass to participate in the Microsoft AI Tour. The event aims to help developers master AI skills and obtain certificates.

MathCoder is a mathematical reasoning tool based on an open source language model. Through fine-tune models and the generation of high-quality data sets, it realizes the alternation of natural language, code and execution results, and improves mathematical reasoning capabilities. MathCoder models achieve state-of-the-art top scores on MATH and GSM8K datasets, far outperforming other open source alternatives. The MathCoder model not only surpasses ChatGPT-3.5 and PaLM-2 on GSM8K and MATH, but also surpasses GPT-4 on the competition-level MATH data set.