DeepSeek-R1 · GitHub Models · GitHub

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

DeepSeek-R1 constructs on the progress of earlier reasoning-focused models that improved performance by extending Chain-of-Thought (CoT) reasoning. DeepSeek-R1 takes things further by combining support learning (RL) with fine-tuning on carefully chosen datasets. It from an earlier variation, DeepSeek-R1-Zero, which relied entirely on RL and revealed strong thinking abilities but had problems 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 monitored fine-tuning on curated datasets, leading to a model that attains modern performance on reasoning standards.

Usage Recommendations

We suggest adhering to the following configurations when making use of the DeepSeek-R1 series designs, consisting of benchmarking, to achieve the expected performance:

– Avoid adding a system prompt; all guidelines ought to be contained within the user prompt.
– For mathematical problems, it is a good idea to consist of an instruction in your timely such as: “Please reason action by action, and put your last response within boxed .”.
– When examining design performance, it is recommended to carry out numerous tests and average the results.

Additional recommendations

The design’s reasoning output (consisted of within the tags) may contain more harmful content than the model’s last action. Consider how your application will use or display the thinking output; you may want to reduce the thinking output in a production setting.