#
Starred repositories
Trae Agent is an LLM-based agent for general purpose software engineering tasks.
A Python package for converting PDFs to markdown while extracting images and tables, generate descriptive text descriptions for extracted tables/images using several LLM clients. And many more func…
Python tool for converting files and office documents to Markdown.
Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL
🔧Tool-Star: Empowering LLM-brained Multi-Tool Reasoner via Reinforcement Learning
CYaRon: Yet Another Random Olympic-iNformatics test data generator
Successor to splatnet2statink. Takes battle data from the SplatNet 3 app and uploads it to stat.ink!
Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving
the data download script of the-stack-v2, which is the training data of StarCoder2.
R1-searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
Official Repository of ACL 2025 paper OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference
Sky-T1: Train your own O1 preview model within $450
AI Logging for Interpretability and Explainability🔬
Source Code for ASE-24 paper "Contextualized Data-Wrangling Code Generation in Computational Notebooks".
Longitudinal Evaluation of LLMs via Data Compression
[ICLR 2025] Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. Your efficient and high-quality synthetic data generation pipeline!
Awesome Pretrained Chinese NLP Models，高质量中文预训练模型&大模型&多模态模型&大语言模型集合
Curated list of datasets and tools for post-training.
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.