mobiuslabsgmbh/DeepSeek-R1-ReDistill-Llama3-8B-v1.1

The mobiuslabsgmbh/DeepSeek-R1-ReDistill-Llama3-8B-v1.1 is a re-distilled version of the DeepSeek-R1-Distill-Llama3-8B model, developed by mobiuslabsgmbh. This 8B parameter model demonstrates improved performance across various benchmarks, including MMLU, TruthfulQA-MC2, Winogrande, and notably GSM8K, where it achieves 75.66%. It is optimized for enhanced reasoning and general knowledge tasks, making it suitable for applications requiring robust analytical capabilities.