Stars
slime is an LLM post-training framework for RL Scaling.
5ire is a cross-platform desktop AI assistant, MCP client. It compatible with major service providers, supports local knowledge base and tools via model context protocol servers .
A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning
verl: Volcano Engine Reinforcement Learning for LLMs
A Survey on Large Language Model-Based Game Agents
LLM/VLM gaming agents and model evaluation through games.
Yelp Simulator for WWW'25 AgentSociety Challenge
[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". A…
[CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis
Interpret Recommendation Models with Sparse Autoencoder
Training Sparse Autoencoders on Language Models
“Chorus” of recommendation models: a light and flexible PyTorch framework for Top-K recommendation.
Sparsify transformers with SAEs and transcoders
A comprehensive library for implementing LLMs, including a unified training pipeline and comprehensive model evaluation.
Benchmarking LLMs with Challenging Tasks from Real Users
[ICML 2024] Selecting High-Quality Data for Training Language Models
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
URS Benchmark: Evaluating LLMs on User Reported Scenarios
MiniCPM4 & MiniCPM4.1: Ultra-Efficient LLMs on End Devices, achieving 3+ generation speedup on reasoning tasks
Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718
A simulation of world using GPTs. (depreciated)