DeepSeek-R1 · GitHub Models · GitHub

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

DeepSeek-R1 develops on the progress of earlier reasoning-focused designs that enhanced efficiency by extending Chain-of-Thought (CoT) reasoning. DeepSeek-R1 takes things even more by combining support learning (RL) with fine-tuning on carefully selected datasets. It developed from an earlier variation, DeepSeek-R1-Zero, which relied exclusively on RL and revealed strong thinking abilities however had issues like hard-to-read outputs and language inconsistencies. To deal with these limitations, DeepSeek-R1 integrates a small quantity of cold-start information and follows a refined training pipeline that mixes reasoning-oriented RL with monitored fine-tuning on curated datasets, resulting in a model that attains state-of-the-art performance on reasoning criteria.

Usage Recommendations

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

– Avoid including a system prompt; all directions ought to be contained within the user timely.
– For mathematical problems, it is recommended to consist of a regulation in your timely such as: “Please factor action by step, and put your final response within boxed .”.
– When evaluating design efficiency, it is suggested to carry out numerous tests and balance the results.

Additional recommendations

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