An Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone

A Latex style and template for paper preprints (based on NIPS style)

LLM4OR homepage project.

Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"

Muon is an optimizer for hidden layers in neural networks

Muon is Scalable for LLM Training

An open-source AI agent that brings the power of Gemini directly into your terminal.

NETLIB LP dataset in .mps format, containing 114 feasible and 29 infeasible instances.

基于selenium的SJTU体育场馆预约脚本

Recent research papers about Foundation Models for Combinatorial Optimization

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

FlashMLA: Efficient Multi-head Latent Attention Kernels

Fully open reproduction of DeepSeek-R1

Train transformer language models with reinforcement learning.

verl: Volcano Engine Reinforcement Learning for LLMs

An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & TIS & vLLM & Ray & Dynamic Sampling & Async Agentic RL)

Minimal reproduction of DeepSeek R1-Zero

Optimization Modeling Using mip Solvers and large language models

Let your Claude able to think

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

A library to generate LaTeX expression from Python code.

A series of math-specific large language models of our Qwen2 series.

Code for the paper: Why Transformers Need Adam: A Hessian Perspective

Code for the paper "Language Models are Unsupervised Multitask Learners"

Production-ready platform for agentic workflow development.

ORLM: Training Large Language Models for Optimization Modeling

Code for Adam-mini: Use Fewer Learning Rates To Gain More https://arxiv.org/abs/2406.16793

The simplest and most practical Node.js backend template, suitable for quickly setting up small-scale backends. | 最爽的方式起个Nodejs小后端