DeepSeek-R1 is a first-generation reasoning model trained using large-scale reinforcement learning (RL) to solve complex reasoning tasks across domains such as math, code, and language.
End of Support — "This artifact is no longer supported. NVIDIA strongly recommends artifacts that are up to date and supported"
Model Overview
Description:
DeepSeek-R1 is a first-generation reasoning model trained using large-scale reinforcement learning (RL) to solve complex reasoning tasks across domains such as math, code, and language. The model leverages RL to develop reasoning capabilities, which are further enhanced through supervised fine-tuning (SFT) to improve readability and coherence. DeepSeek-R1 achieves state-of-the-art results in various benchmarks and offers both its base models and distilled versions for community use.
This model is ready for both research and commercial use. For more details, visit the DeepSeek website.
Third-Party Community Consideration:
This model is not owned or developed by NVIDIA. It is a community-driven model created by DeepSeek AI. See the official DeepSeek-R1 Model Card on Hugging Face for further details.
License/Terms of Use:
GOVERNING TERMS: This trial service is governed by the NVIDIA API Trial Terms of Service. Use of this model is governed by the MIT License.
References:
Model Architecture:
Architecture Type: Mixture of Experts (MoE)
Network Architecture:
- Base Model: DeepSeek-V3-Base
- Activated Parameters: 37 billion
- Total Parameters: 671 billion
- Distilled Models: Smaller, fine-tuned versions based on Qwen and Llama architectures.
- Context Length: 128K tokens
Input:
Input Type(s): Text
Input Format(s): String
Input Parameters: (1D)
Other Properties Related to Input:
DeepSeek recommends adhering to the following configurations when utilizing the DeepSeek-R1 series models, including benchmarking, to achieve the expected performance:
- Set the temperature within the range of 0.5-0.7 (0.6 is recommended) to prevent endless repetitions or incoherent outputs.
- Avoid adding a system prompt; all instructions should be contained within the user prompt.
- For mathematical problems, it is advisable to include a directive in your prompt such as: "Please reason step by step, and put your final answer within \boxed{}."
- When evaluating model performance, it is recommended to conduct multiple tests and average the results.
Output:
Output Type(s): Text
Output Format: String
Output Parameters: (1D)
Software Integration:
Runtime Engine(s): vLLM and SGLang
Supported Hardware Microarchitecture Compatibility: NVIDIA's Ampere, Blackwell, Jetson, Hopper, Lovelace, Pascal, Turing, and Volta architectures
[Preferred/Supported] Operating System(s): Linux
Model Version(s):
DeepSeek-R1 V1.0
Training, Testing, and Evaluation Datasets:
Training Dataset:
Data Collection Method by dataset: Hybrid: Human, Automated
**Labeling Method by dataset:**Hybrid: Human, Automated
Properties: The dataset contains a large number of samples, with specific numbers mentioned for each model in the evaluation results.
Testing Dataset:
Data Collection Method by dataset: HHybrid: Human, Automated
Labeling Method by dataset: Hybrid: Human, Automated
Properties: The dataset contains a large number of samples, with specific numbers mentioned for each model in the evaluation results.
Evaluation Dataset:
Data Collection Method by dataset: Hybrid: Human, Automated
Labeling Method by dataset: Hybrid: Human, Automated
Properties: The dataset contains a large number of samples, with specific numbers mentioned for each model in the evaluation results.
Inference:
Engine: TensorRT-LLM Test Hardware: NVIDIA Ampere
Ethical Considerations:
NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. Please report security vulnerabilities or NVIDIA AI Concerns here.
You are responsible for ensuring that your use of NVIDIA AI Foundation Models complies with all applicable laws.
Get Help
NVIDIA Developer Community Forum
For support, Visit the NVIDIA Developer Community Forum