Qwen2.5-3B-Instruct-RG-Math/README.md

library_name, pipeline_tag, base_model

library_name	pipeline_tag	base_model
transformers	text-generation	Qwen/Qwen2.5-3B-Instruct

This model was trained for our Reasoning Gym paper (https://arxiv.org/abs/2505.24760) using our Reasoning Gym repo (https://github.com/open-thought/reasoning-gym)