infly/inf-o1-pi0
TEXT GENERATIONConcurrency Cost:2Model Size:32.8BQuant:FP8Ctx Length:32kPublished:Jan 3, 2025Architecture:Transformer0.0K Cold

infly/inf-o1-pi0 is a 32.8 billion parameter reasoning foundation large language model developed by INFLY TECH (Shanghai) Co., Ltd., based on the Qwen2.5-32B-Instruct architecture. It is specifically designed to enhance reasoning capabilities across various industrial domains, excelling in mathematics, programming, logic, and safety tasks. The model leverages a meticulously designed data production pipeline with self-verification and backtracking mechanisms to induce robust long-context reasoning.

Loading preview...