Stars
A python module to repair invalid JSON from LLMs
Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"
[ICCV 2025] SimVQ: Addressing Representation Collapse in Vector Quantized Models with One Linear Layer
Exercises and projects for Jane Street's OCaml Workshop
[NeurIPS 2025] TTRL: Test-Time Reinforcement Learning
An implementation of the Muon optimizer in pytorch featuring the latest research improvements.
MiniCPM-V 4.5: A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone
OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling
Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation
Implementation of the MuonClip optimizer in PyTorch/JAX based on the Kimi K2 technical report
Flash-Muon: An Efficient Implementation of Muon Optimizer
Muon is an optimizer for hidden layers in neural networks
verl: Volcano Engine Reinforcement Learning for LLMs
FlexTok: Resampling Images into 1D Token Sequences of Flexible Length
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Models
An open-source implementaion for fine-tuning Qwen-VL series by Alibaba Cloud.
Efficient Triton Kernels for LLM Training
A minimal codebase for finetuning large multimodal models, supporting llava-1.5/1.6, llava-interleave, llava-next-video, llava-onevision, llama-3.2-vision, qwen-vl, qwen2-vl, phi3-v etc.
Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
Official PyTorch implementation for "Large Language Diffusion Models"