DeepSeek R1 Zero
Model Information
| Slug | deepseek-r1-zero |
|---|---|
| LLMs.txt | View |
| Release Date | January 20, 2025 |
| GPQA | 0.733 |
Organization
| Name | DeepSeek |
|---|---|
| Website | https://www.deepseek.com/ |
Model Description
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](/deepseek/deepseek-r1) for the SFT model.
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](/deepseek/deepseek-r1) for the SFT model.
