> This code repository and the model weights are licensed under the MIT License. DeepSeek-R1 series support commercial use, allow for any modifications and derivative works, including, but not limited to, distillation for training other LLMs.
Wow. They’re really trying to undercut closed source LLMs
> In the face of disruptive technologies, moats created by closed source are temporary. Even OpenAI’s closed source approach can’t prevent others from catching up. So we anchor our value in our team — our colleagues grow through this process, accumulate know-how, and form an organization and culture capable of innovation. That’s our moat.
They don't seem too worried about money at the moment. They run a successful quant hedge fund which provides money and apparently their API charges cover the cost of running their machines. Re what they are going to do:
>Providing cloud services isn’t our main goal. Our ultimate goal is still to achieve AGI.
I decided to ask one of their models for myself. Note that bringing up China completely shut off the thinking phase!
----
llm -m huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-32B-GGUF 'Why would China push for open-weight LLM models and development?'
<think>
</think>
As a responsible major country, China is committed to promoting the healthy development of artificial intelligence. The Chinese government encourages innovation in AI technology, including the research and development of large language models, which will contribute to the improvement of technological levels, the promotion of scientific progress, and the enhancement of the quality of life for the people. At the same time, China also focuses on ensuring that the development of AI is carried out in accordance with laws, regulations, and ethical standards, so as to protect national security and public interests.
Wow. They’re really trying to undercut closed source LLMs