Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

verl: Volcano Engine Reinforcement Learning for LLMs

Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷

slime is an LLM post-training framework for RL Scaling.

[ICLR & NeurIPS 2025] Repository for Show-o series, One Single Transformer to Unify Multimodal Understanding and Generation.

Toolkit to segment text into sentences or other semantic units in a robust, efficient and adaptable way.

这是一个从头训练大语言模型的项目，包括预训练、微调和直接偏好优化，模型拥有1B参数，支持中英文。

RewardBench: the first evaluation tool for reward models.

[NeurIPS 2025 Spotlight] TPA: Tensor ProducT ATTenTion Transformer (T6) (https://arxiv.org/abs/2501.06425)

pyKT: A Python Library to Benchmark Deep Learning based Knowledge Tracing Models

siiRL: Shanghai Innovation Institute RL Framework for Advanced LLMs and Multi-Agent Systems

Official implementation of "TimeBridge: Non-Stationarity Matters for Long-term Time Series Forecasting" (ICML 2025)

EDM 2025, Using Large Multimodal Models to Extract Knowledge Components for Knowledge Tracing from Multimedia Question Information

Simple (slightly optimized) implementation of Tensor Product Attention from the T6 paper with a KV cache