2025 február 17, hétfő

Theboardroomslu

Overview

  • Founded Date 2017-02-28
  • Posted Jobs 0
  • Viewed 9

Company Description

DeepSeek’s First-generation Reasoning Models

DeepSeek’s first-generation designs, achieving performance comparable to OpenAI-o1 across mathematics, code, and thinking jobs.

Models

DeepSeek-R1

Distilled models

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

Below are the models produced by means of fine-tuning versus numerous dense designs commonly utilized in the research study neighborhood using thinking information created by DeepSeek-R1. The assessment results demonstrate that the distilled smaller thick models perform remarkably well on standards.

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 assistance industrial usage, enable any adjustments and derivative works, including, however not restricted to, distillation for training other LLMs.

Üdv újra itt!

Jelentkezzen be fiókjába

Jelszó Visszaállítás

Kérjük, adja meg felhasználónevét vagy e-mail címét a jelszó visszaállításához.