Coolcair
Add a reviewOverview
-
Sectors Digital & Creative
-
Posted Jobs 0
Company Description
DeepSeek’s First-generation Reasoning Models
DeepSeek’s first-generation designs, attaining performance similar to OpenAI-o1 across mathematics, code, and thinking tasks.
Models
DeepSeek-R1
(1).pngL.jpg){kind=logo}
Distilled designs
DeepSeek team has demonstrated that the reasoning patterns of bigger designs can be distilled into smaller sized models, leading to better performance compared to the reasoning patterns discovered through RL on small designs.
Below are the designs created through fine-tuning against a number of dense designs widely used in the research study neighborhood utilizing reasoning data produced by DeepSeek-R1. The examination results demonstrate that the distilled smaller dense models carry out exceptionally 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 support business usage, permit any modifications and acquired works, including, however not restricted to, distillation for training other LLMs.
