技术栈

deepseek-r1-7b

F_D_Z
1 天前
人工智能·deepseek·deepseek-r1-7b
8K样本在DeepSeek-R1-7B模型上的复现效果7B Model and 8K Examples: Emerging Reasoning with Reinforcement Learning is Both Effective and Effic (notion.site)