Changyi Yang

@ChangyiYang · User

GitHub profile ↗ · Compare

64 followers34 repositories

Repositories

ChangyiYang/miles

Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.

★ 0Forks 0

ChangyiYang/verl

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

★ 0PythonForks 0

ChangyiYang/sglang-moe-fix

SGLang is a fast serving framework for large language models and vision language models.

★ 0PythonForks 0

ChangyiYang/uni-agent

A unified framework for building, running, and training general agents at scale.

★ 0Forks 0

ChangyiYang/transformers

🤗 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.

★ 0Forks 0

ChangyiYang/ray

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

★ 0Forks 0

ChangyiYang/Length-Value-Model

Official implementation of the paper "Length Value Model: Pretraining Value Model for Scalable Length Prediction and Control"

★ 0Forks 0

ChangyiYang/slime

slime is an LLM post-training framework for RL Scaling.

★ 0PythonForks 0

ChangyiYang/mllms_know

[ICLR'25] Official code for the paper 'MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs'

★ 0Forks 0