DeepSeek-R1 · GitHub Models · GitHub

DeepSeek-R1 excels at thinking jobs utilizing a step-by-step training process, such as language, clinical reasoning, and coding tasks. It includes 671B total criteria with 37B active criteria, and 128k context length.

DeepSeek-R1 constructs on the development of earlier reasoning-focused designs that enhanced efficiency by extending Chain-of-Thought (CoT) reasoning. DeepSeek-R1 takes things even more by combining reinforcement learning (RL) with fine-tuning on carefully picked datasets. It evolved from an earlier variation, DeepSeek-R1-Zero, which relied exclusively on RL and showed strong reasoning abilities however had concerns like hard-to-read outputs and language inconsistencies. To attend to these constraints, DeepSeek-R1 integrates a small amount 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 accomplishes modern performance on thinking criteria.

Usage Recommendations

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

– Avoid including a system timely; all instructions should be contained within the user timely.
– For mathematical issues, it is advisable to include a directive in your timely such as: “Please reason action by action, and put your last response within boxed .”.
– When examining model efficiency, it is suggested to conduct numerous tests and balance the results.

Additional recommendations

The model’s thinking output (contained within the tags) might contain more hazardous content than the design’s final action. Consider how your application will utilize or the reasoning output; you might desire to suppress the reasoning output in a production setting.