agentrl/ReSearch-Qwen-7B-Instruct
TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kPublished:Mar 27, 2025License:mitArchitecture:Transformer0.0K Open Weights Cold

The agentrl/ReSearch-Qwen-7B-Instruct is a 7.6 billion parameter instruction-tuned language model developed by agentrl, based on the Qwen2.5 architecture, with a notable 131072 token context length. This model is specifically trained using a novel Reinforcement Learning framework called ReSearch, which teaches LLMs to reason with search operations without supervised reasoning data. It excels at complex question answering and reasoning tasks by integrating search capabilities directly into its thought process.

Loading preview...