Overview

  • Founded Date June 18, 1971
  • Sectors فنيين
  • Posted Jobs 0
  • Viewed 5

Company Description

DeepSeek’s First-generation Reasoning Models

DeepSeek’s first-generation thinking models, achieving performance equivalent to OpenAI-o1 throughout math, code, and thinking tasks.

Models

DeepSeek-R1

Distilled designs

DeepSeek team has actually demonstrated that the thinking patterns of larger designs can be distilled into smaller designs, resulting in better efficiency compared to the thinking patterns found through RL on small models.

Below are the models produced via fine-tuning against several dense designs commonly utilized in the research neighborhood using reasoning information by DeepSeek-R1. The examination results demonstrate that the distilled smaller dense designs carry out incredibly well on benchmarks.

DeepSeek-R1-Distill-Qwen-1.5 B

DeepSeek-R1-Distill-Qwen-7B

DeepSeek-R1-Distill-Llama-8B

DeepSeek-R1-Distill-Qwen-14B

DeepSeek-R1-Distill-Qwen-32B

DeepSeek-R1-Distill-Llama-70B

License

The model weights are certified under the MIT License. DeepSeek-R1 series support commercial use, enable for any modifications and acquired works, including, but not limited to, distillation for training other LLMs.