deepseek 的网站图标

DeepSeek: DeepSeek R1 Zero

deepseek/deepseek-r1-zero

模型权重

DeepSeek-R1-Zero is a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step. It's 671B parameters in size, with 37B active in an inference pass.

It demonstrates remarkable performance on reasoning. With RL, DeepSeek-R1-Zero naturally emerged with numerous powerful and interesting reasoning behaviors.

DeepSeek-R1-Zero encounters challenges such as endless repetition, poor readability, and language mixing. See DeepSeek R1 for the SFT model.

模态
上下文
164K
发布时间
2025年3月6日
知识截止日期
2024年7月

活动

此模型的 token 用量和请求流量随时间的变化。

目前无法通过 EU 区域内路由使用。 区域内路由文档

常见问题

探索更多模型