DeepSeek-R1 · GitHub Models · GitHub

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

DeepSeek-R1 builds on the development of earlier reasoning-focused designs that improved efficiency by extending Chain-of-Thought (CoT) . DeepSeek-R1 takes things further by integrating reinforcement learning (RL) with fine-tuning on carefully chosen datasets. It developed from an earlier variation, DeepSeek-R1-Zero, which relied entirely on RL and showed strong reasoning abilities however had issues like hard-to-read outputs and language inconsistencies. To deal with these constraints, DeepSeek-R1 incorporates a little amount of cold-start data and follows a refined training pipeline that mixes reasoning-oriented RL with supervised fine-tuning on curated datasets, resulting in a design that attains cutting edge efficiency on thinking criteria.

Usage Recommendations

We advise sticking to the following configurations when using the DeepSeek-R1 series designs, including benchmarking, to achieve the expected efficiency:

– Avoid adding a system prompt; all instructions ought to be included within the user timely.
– For mathematical problems, it is suggested to consist of a regulation in your prompt such as: „Please factor action by step, and put your final answer within boxed .“.
– When evaluating model performance, it is suggested to carry out numerous tests and balance the outcomes.

Additional recommendations

The model’s reasoning output (included within the tags) might include more harmful material than the model’s final response. Consider how your application will use or display the thinking output; you may want to suppress the reasoning output in a production setting.