DATEXIS/DeepICD-R1-7B
TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kPublished:Mar 15, 2026License:otherArchitecture:Transformer Cold

DATEXIS/DeepICD-R1-7B is a 7.6 billion parameter clinical reasoning language model, based on Qwen2.5-7B-Instruct, specifically designed for ICD-10-CM diagnosis outcome prediction from admission notes. It utilizes the DeepICD-R1 framework, combining structured reasoning traces with reinforcement learning and hierarchical reward signals. This model excels at generating both a single ICD-10-CM diagnosis code and an interpretable reasoning trace explaining its decision from clinical text. Its 32768 token context length supports processing comprehensive admission notes for medical reasoning research.

Loading preview...