DeepSeek-R1 · GitHub Models · GitHub

DeepSeek-R1 stands out at reasoning jobs using a detailed training procedure, such as language, clinical reasoning, and coding tasks. It features 671B total specifications with 37B active criteria, and 128k context length.

DeepSeek-R1 develops on the progress of earlier reasoning-focused models that improved performance by extending Chain-of-Thought (CoT) thinking. DeepSeek-R1 takes things further by combining support learning (RL) with fine-tuning on carefully chosen datasets. It progressed from an earlier version, DeepSeek-R1-Zero, which relied solely on RL and showed strong reasoning skills but had concerns like hard-to-read outputs and language disparities. To deal with these restrictions, DeepSeek-R1 includes a little quantity of cold-start data and follows a refined training pipeline that blends reasoning-oriented RL with supervised fine-tuning on curated datasets, resulting in a model that achieves cutting edge efficiency on reasoning standards.

Usage Recommendations

We advise sticking to the following configurations when making use of the DeepSeek-R1 series designs, benchmarking, to attain the expected performance:

– Avoid including a system prompt; all guidelines ought to be contained within the user prompt.
– For mathematical issues, it is suggested to include a regulation in your prompt such as: “Please factor action by action, and put your last response within boxed .”.
– When examining design efficiency, it is recommended to conduct several tests and balance the outcomes.

Additional recommendations

The design’s reasoning output (contained within the tags) might include more damaging material than the model’s last reaction. Consider how your application will utilize or show the reasoning output; you may desire to reduce the reasoning output in a production setting.