R-4B

In this repo, we present **R-4B**, a multimodal large language model designed for general-purpose auto-thinking, autonomously switching between step-by-step thinking and direct response generation based on task complexity. This capability enables R-4B to deliver high-quality responses while significantly improving inference efficiency and reducing computational costs. The development of R-4B follows a two-stage training paradigm: (1) Bi-mode Annealing, which establishes both thinking and non-thinking capabilities for VQA; and (2) Bi-mode Policy Optimization (BPO), which enables the model to adaptively switch between thinking and non-thinking modes based on input demands. > [!NOTE] > Users can dynamically control the model's response by selecting one of three modes (`auto-thinking`, `thinking`, or `non-thinking`) with `thinking_mode`. `thinking_mode=auto` for `auto-thinking` mode; `thinking_mode=long` for `thinking` mode; `thinking_mode=short` for `non-thinking` mode. > Default is `auto-thinking`.