gguk2on/qwen2.5-7B-rlar_g8_b512_v2
TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kPublished:Mar 27, 2026Architecture:Transformer Cold

The gguk2on/qwen2.5-7B-rlar_g8_b512_v2 is a 7.6 billion parameter language model, fine-tuned from Qwen/Qwen2.5-7B using the GRPO method. This model is specifically optimized for mathematical reasoning, leveraging techniques introduced in the DeepSeekMath paper. It is designed to enhance performance in complex mathematical tasks and problem-solving.

Loading preview...