Lists (1)
Stars
siiRL: Shanghai Innovation Institute RL Framework for Advanced LLMs and Multi-Agent Systems
slime is an LLM post-training framework for RL Scaling.
RewardBench: the first evaluation tool for reward models.
Toolkit to segment text into sentences or other semantic units in a robust, efficient and adaptable way.
主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题
verl: Volcano Engine Reinforcement Learning for LLMs
Official implementation of "TimeBridge: Non-Stationarity Matters for Long-term Time Series Forecasting" (ICML 2025)
[NeurIPS 2025 Spotlight] TPA: Tensor ProducT ATTenTion Transformer (T6) (https://arxiv.org/abs/2501.06425)
Simple (slightly optimized) implementation of Tensor Product Attention from the T6 paper with a KV cache
[ICLR & NeurIPS 2025] Repository for Show-o series, One Single Transformer to Unify Multimodal Understanding and Generation.
整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。
Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Build Conversational AI in minutes ⚡️
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。
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
pyKT: A Python Library to Benchmark Deep Learning based Knowledge Tracing Models
EDM 2025, Using Large Multimodal Models to Extract Knowledge Components for Knowledge Tracing from Multimedia Question Information
程序员在家做饭方法指南。Programmer's guide about how to cook at home (Simplified Chinese only).