# DeepSeek-R1
DeepSeek-V3
Homepage Chat Hugging Face
Discord Wechat Twitter Follow
Code License Model License

Paper Link👁️

## 1. Introduction We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step, demonstrated remarkable performance on reasoning. With RL, DeepSeek-R1-Zero naturally emerged with numerous powerful and interesting reasoning behaviors. However, DeepSeek-R1-Zero encounters challenges such as endless repetition, poor readability, and language mixing. To address these issues and further enhance reasoning performance, we introduce DeepSeek-R1, which incorporates cold-start data before RL. DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks. To support the research community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six dense models distilled from DeepSeek-R1 based on Llama and Qwen. DeepSeek-R1-Distill-Qwen-32B outperforms OpenAI-o1-mini across various benchmarks, achieving new state-of-the-art results for dense models.

## 2. Model Summary --- **Post-Training: Large-Scale Reinforcement Learning on the Base Model** - We directly apply reinforcement learning (RL) to the base model without relying on supervised fine-tuning (SFT) as a preliminary step. This approach allows the model to explore chain-of-thought (CoT) for solving complex problems, resulting in the development of DeepSeek-R1-Zero. DeepSeek-R1-Zero demonstrates capabilities such as self-verification, reflection, and generating long CoTs, marking a significant milestone for the research community. Notably, it is the first open research to validate that reasoning capabilities of LLMs can be incentivized purely through RL, without the need for SFT. This breakthrough paves the way for future advancements in this area. - We introduce our pipeline to develop DeepSeek-R1. The pipeline incorporates two RL stages aimed at discovering improved reasoning patterns and aligning with human preferences, as well as two SFT stages that serve as the seed for the model's reasoning and non-reasoning capabilities. We believe the pipeline will benefit the industry by creating better models. --- **Distillation: Smaller Models Can Be Powerful Too** - We demonstrate that the reasoning patterns of larger models can be distilled into smaller models, resulting in better performance compared to the reasoning patterns discovered through RL on small models. The open source DeepSeek-R1, as well as its API, will benefit the research community to distill better smaller models in the future. - Using the reasoning data generated by DeepSeek-R1, we fine-tuned several dense models that are widely used in the research community. The evaluation results demonstrate that the distilled smaller dense models perform exceptionally well on benchmarks. We open-source distilled 1.5B, 7B, 8B, 14B, 32B, and 70B checkpoints based on Qwen2.5 and Llama3 series to the community. ## 3. Model Downloads ### DeepSeek-R1 Models
| **Model** | **#Total Params** | **#Activated Params** | **Context Length** | **Download** | | :------------: | :------------: | :------------: | :------------: | :------------: | | DeepSeek-R1-Zero | 671B | 37B | 128K | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Zero) | | DeepSeek-R1 | 671B | 37B | 128K | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1) |
DeepSeek-R1-Zero & DeepSeek-R1 are trained based on DeepSeek-V3-Base. For more details regrading the model architecture, please refer to [DeepSeek-V3](https://github.com/deepseek-ai/DeepSeek-V3) repository. ### DeepSeek-R1-Distill Models
| **Model** | **Base Model** | **Download** | | :------------: | :------------: | :------------: | | DeepSeek-R1-Distill-Qwen-1.5B | [Qwen2.5-Math-1.5B](https://huggingface.co/Qwen/Qwen2.5-Math-1.5B) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) | | DeepSeek-R1-Distill-Qwen-7B | [Qwen2.5-Math-7B](https://huggingface.co/Qwen/Qwen2.5-Math-7B) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) | | DeepSeek-R1-Distill-Llama-8B | [Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B) | | DeepSeek-R1-Distill-Qwen-14B | [Qwen2.5-14B](https://huggingface.co/Qwen/Qwen2.5-14B) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B) | |DeepSeek-R1-Distill-Qwen-32B | [Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B) | | DeepSeek-R1-Distill-Llama-70B | [Llama-3.3-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B) |
DeepSeek-R1-Distill models are fine-tuned based on open-source models, using samples generated by DeepSeek-R1. We slightly change their configs and tokenizers. Please use our setting to run these models. ## 4. Evaluation Results ### DeepSeek-R1-Evaluation For all our models, the maximum generation length is set to 32,768 tokens. For benchmarks requiring sampling, we use a temperature of $0.6$, a top-p value of $0.95$, and generate 64 responses per query to estimate pass@1.
| Category | Benchmark (Metric) | Claude-3.5-Sonnet-1022 | GPT-4o 0513 | DeepSeek V3 | OpenAI o1-mini | OpenAI o1-1217 | DeepSeek R1 | |----------|-------------------|----------------------|------------|--------------|----------------|------------|--------------| | | Architecture | - | - | MoE | - | - | MoE | | | # Activated Params | - | - | 37B | - | - | 37B | | | # Total Params | - | - | 671B | - | - | 671B | | English | MMLU (Pass@1) | 88.3 | 87.2 | 88.5 | 85.2 | **91.8** | 90.8 | | | MMLU-Redux (EM) | 88.9 | 88.0 | 89.1 | 86.7 | - | **92.9** | | | MMLU-Pro (EM) | 78.0 | 72.6 | 75.9 | 80.3 | - | **84.0** | | | DROP (3-shot F1) | 88.3 | 83.7 | 91.6 | 83.9 | 90.2 | **92.2** | | | IF-Eval (Prompt Strict) | **86.5** | 84.3 | 86.1 | 84.8 | - | 83.3 | | | GPQA-Diamond (Pass@1) | 65.0 | 49.9 | 59.1 | 60.0 | **75.7** | 71.5 | | | SimpleQA (Correct) | 28.4 | 38.2 | 24.9 | 7.0 | **47.0** | 30.1 | | | FRAMES (Acc.) | 72.5 | 80.5 | 73.3 | 76.9 | - | **82.5** | | | AlpacaEval2.0 (LC-winrate) | 52.0 | 51.1 | 70.0 | 57.8 | - | **87.6** | | | ArenaHard (GPT-4-1106) | 85.2 | 80.4 | 85.5 | 92.0 | - | **92.3** | | Code | LiveCodeBench (Pass@1-COT) | 33.8 | 34.2 | - | 53.8 | 63.4 | **65.9** | | | Codeforces (Percentile) | 20.3 | 23.6 | 58.7 | 93.4 | **96.6** | 96.3 | | | Codeforces (Rating) | 717 | 759 | 1134 | 1820 | **2061** | 2029 | | | SWE Verified (Resolved) | **50.8** | 38.8 | 42.0 | 41.6 | 48.9 | 49.2 | | | Aider-Polyglot (Acc.) | 45.3 | 16.0 | 49.6 | 32.9 | **61.7** | 53.3 | | Math | AIME 2024 (Pass@1) | 16.0 | 9.3 | 39.2 | 63.6 | 79.2 | **79.8** | | | MATH-500 (Pass@1) | 78.3 | 74.6 | 90.2 | 90.0 | 96.4 | **97.3** | | | CNMO 2024 (Pass@1) | 13.1 | 10.8 | 43.2 | 67.6 | - | **78.8** | | Chinese | CLUEWSC (EM) | 85.4 | 87.9 | 90.9 | 89.9 | - | **92.8** | | | C-Eval (EM) | 76.7 | 76.0 | 86.5 | 68.9 | - | **91.8** | | | C-SimpleQA (Correct) | 55.4 | 58.7 | **68.0** | 40.3 | - | 63.7 |
### Distilled Model Evaluation
| Model | AIME 2024 pass@1 | AIME 2024 cons@64 | MATH-500 pass@1 | GPQA Diamond pass@1 | LiveCodeBench pass@1 | CodeForces rating | |------------------------------------------|------------------|-------------------|-----------------|----------------------|----------------------|-------------------| | GPT-4o-0513 | 9.3 | 13.4 | 74.6 | 49.9 | 32.9 | 759 | | Claude-3.5-Sonnet-1022 | 16.0 | 26.7 | 78.3 | 65.0 | 38.9 | 717 | | o1-mini | 63.6 | 80.0 | 90.0 | 60.0 | 53.8 | **1820** | | QwQ-32B-Preview | 44.0 | 60.0 | 90.6 | 54.5 | 41.9 | 1316 | | DeepSeek-R1-Distill-Qwen-1.5B | 28.9 | 52.7 | 83.9 | 33.8 | 16.9 | 954 | | DeepSeek-R1-Distill-Qwen-7B | 55.5 | 83.3 | 92.8 | 49.1 | 37.6 | 1189 | | DeepSeek-R1-Distill-Qwen-14B | 69.7 | 80.0 | 93.9 | 59.1 | 53.1 | 1481 | | DeepSeek-R1-Distill-Qwen-32B | **72.6** | 83.3 | 94.3 | 62.1 | 57.2 | 1691 | | DeepSeek-R1-Distill-Llama-8B | 50.4 | 80.0 | 89.1 | 49.0 | 39.6 | 1205 | | DeepSeek-R1-Distill-Llama-70B | 70.0 | **86.7** | **94.5** | **65.2** | **57.5** | 1633 |
## 5. Chat Website & API Platform You can chat with DeepSeek-R1 on DeepSeek's official website: [chat.deepseek.com](https://chat.deepseek.com), and switch on the button "DeepThink" We also provide OpenAI-Compatible API at DeepSeek Platform: [platform.deepseek.com](https://platform.deepseek.com/) ## 6. How to Run Locally ### DeepSeek-R1 Models Please visit [DeepSeek-V3](https://github.com/deepseek-ai/DeepSeek-V3) repo for more information about running DeepSeek-R1 locally. ### DeepSeek-R1-Distill Models DeepSeek-R1-Distill models can be utilized in the same manner as Qwen or Llama models. For instance, you can easily start a service using [vLLM](https://github.com/vllm-project/vllm): ```shell vllm serve deepseek-ai/DeepSeek-R1-Distill-Qwen-32B --tensor-parallel-size 2 --max-model-len 32768 --enforce-eager ``` You can also easily start a service using [SGLang](https://github.com/sgl-project/sglang) ```bash python3 -m sglang.launch_server --model deepseek-ai/DeepSeek-R1-Distill-Qwen-32B --trust-remote-code --tp 2 ``` ### Usage Recommendations **We recommend adhering to the following configurations when utilizing the DeepSeek-R1 series models, including benchmarking, to achieve the expected performance:** 1. Set the temperature within the range of 0.5-0.7 (0.6 is recommended) to prevent endless repetitions or incoherent outputs. 2. Avoid adding a system prompt; all instructions should be contained within the user prompt. 3. For mathematical problems, it is advisable to include a directive in your prompt such as: "put your final answer within \boxed{}". 4. When evaluating model performance, it is recommended to conduct multiple tests and average the results. ## 7. Function Calling and Structured Outputs ### Current Status - As of now, **DeepSeek R1 does not natively support function calling or structured outputs**. - The model is primarily optimized for **reasoning-heavy tasks** (e.g., math, code, and STEM) and follows a conversational format. ### Future Plans - We recognize the importance of **function calling** and **structured outputs** for many use cases, such as API integrations, automation, and data extraction. - We are actively exploring ways to add support for these features in future updates. This includes: - Extending the model’s capabilities to handle structured data formats (e.g., JSON, XML). - Adding support for function calling to enable seamless integration with external tools and APIs. ### Timeline - While we don’t have a specific release date yet, we aim to roll out these features in the **next major update**. - We will keep the community updated on our progress through GitHub announcements and release notes. ### Workarounds for Now If you need structured outputs or function-like behavior in the meantime, here are some workarounds: 1. **Post-Processing Outputs:** - Use a script to parse the model’s responses into structured formats (e.g., JSON). - Example: ```python import json response = model.generate("Extract the following data as JSON: ...") structured_data = json.loads(response) ``` 2. **Prompt Engineering:** - Design prompts to guide the model to produce outputs in a specific format. - Example: ``` Extract the following information and format it as JSON: - Name: ... - Age: ... - Location: ... ``` 3. **Custom Wrapper:** - Build a custom wrapper around the model to simulate function calling behavior. - Example: ```python def call_function(model, function_name, args): prompt = f"Call function {function_name} with args {args} and return the result." return model.generate(prompt) ``` ### Community Feedback We appreciate the enthusiasm from the community (x2 + 5 and counting!). Your feedback is invaluable in shaping the future of DeepSeek R1. If you have specific use cases or feature requests related to function calling and structured outputs, please share them in this thread. ### Next Steps - We will prioritize this feature based on community demand and provide updates as development progresses. - Stay tuned for announcements and feel free to contribute ideas or suggestions! Thank you for your patience and support as we work to make DeepSeek R1 even better! Let us know if you have further questions or need additional assistance. ## 8. License This code repository and the model weights are licensed under the [MIT License](https://github.com/deepseek-ai/DeepSeek-R1/blob/main/LICENSE). DeepSeek-R1 series support commercial use, allow for any modifications and derivative works, including, but not limited to, distillation for training other LLMs. Please note that: - DeepSeek-R1-Distill-Qwen-1.5B, DeepSeek-R1-Distill-Qwen-7B, DeepSeek-R1-Distill-Qwen-14B and DeepSeek-R1-Distill-Qwen-32B are derived from [Qwen-2.5 series](https://github.com/QwenLM/Qwen2.5), which are originally licensed under [Apache 2.0 License](https://huggingface.co/Qwen/Qwen2.5-1.5B/blob/main/LICENSE), and now finetuned with 800k samples curated with DeepSeek-R1. - DeepSeek-R1-Distill-Llama-8B is derived from Llama3.1-8B-Base and is originally licensed under [llama3.1 license](https://huggingface.co/meta-llama/Llama-3.1-8B/blob/main/LICENSE). - DeepSeek-R1-Distill-Llama-70B is derived from Llama3.3-70B-Instruct and is originally licensed under [llama3.3 license](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct/blob/main/LICENSE). ## 9. Citation ``` ``` ## 10. Contact If you have any questions, please raise an issue or contact us at [service@deepseek.com](service@deepseek.com).