AI agents running research on single-GPU nanochat training automatically

PinchBench is a benchmarking system for evaluating LLM models as OpenClaw coding agents. Made with 🦀 by the humans at https://kilo.ai

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.

An MCP-based chatbot | 一个基于MCP的聊天机器人

An Open Foundation Model and Benchmark to Accelerate Generative Recommendation

An Open-source RL System from ByteDance Seed and Tsinghua AIR

adds Sequence Parallelism into LLaMA-Factory

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

The implementation for the work "GradCraft: Elevating Multi-task Recommendations through Holistic Gradient Crafting".

[AAAI26] Improving Time Series Forecasting by Progressively Learning Residuals

Code for GO4Align: Group Optimization for Multi-Task Alignment

Monocular Depth Estimation Toolbox based on MMSegmentation.

Official implementation for "iTransformer: Inverted Transformers Are Effective for Time Series Forecasting" (ICLR 2024 Spotlight)

RecData: A curated collection of recommendation datasets with trackable dataset IDs

A collection for math word problem (MWP) works, including datasets, algorithms and so on.

ToRA is a series of Tool-integrated Reasoning LLM Agents designed to solve challenging mathematical reasoning problems by interacting with tools [ICLR'24].

Mix of Minimal Optimal Sets (MMOS) of dataset has two advantages for two aspects, higher performance and lower construction costs on math reasoning.

large language model tuning examples

Official repository for ORPO

Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation

A Neural Framework for MT Evaluation

中文 Instruction tuning datasets

AirLLM 70B inference with single 4GB GPU

MS-Agent: a lightweight framework to empower agentic execution of complex tasks

a state-of-the-art-level open visual language model | 多模态预训练模型

A Next-Generation Training Engine Built for Ultra-Large MoE Models

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