DeepSeek-R1 · GitHub Models · GitHub

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

DeepSeek-R1 builds on the development of earlier reasoning-focused designs that enhanced performance 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 evolved from an earlier variation, DeepSeek-R1-Zero, which relied exclusively on RL and revealed strong reasoning skills however had concerns like hard-to-read outputs and language inconsistencies. To resolve these restrictions, DeepSeek-R1 integrates a percentage of cold-start data and follows a refined training pipeline that blends reasoning-oriented RL with supervised fine-tuning on curated datasets, leading to a design that achieves cutting edge efficiency on reasoning standards.

Usage Recommendations

We advise adhering to the following configurations when making use of the DeepSeek-R1 series designs, including benchmarking, to accomplish the expected efficiency:

– Avoid adding a system prompt; all directions must be contained within the user prompt.
– For mathematical problems, it is advisable to include a regulation in your timely such as: “Please factor step by step, and put your final response within boxed .”.
– When assessing model efficiency, it is advised to perform numerous tests and balance the results.

Additional recommendations

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