Retour à Deepseek R1 Distill
DeepSeek's R1 reasoning distilled into a 7B Qwen base — solid chain-of-thought at a highly deployable size.
164K tokensGratuit / Poids ouvertsTransformerMIT
Benchmarks
GAIA
DeepSeek-R1-Distill-Qwen-7B
25.6%DeepSeek-R1-Distill-Qwen-32B
57.5%DeepSeek-R1-Distill-Llama-8B
27.6%Qwen3-32B-RL system using distill
