Name: DeepSeek R1
Author: deepseek-ai

Overview

DeepSeek R1 is a reasoning-focused model designed to compete with high-end frontier LLMs by implementing advanced reinforcement learning. Unlike standard chat models, R1 excels at complex logic, mathematics, and coding tasks by utilizing a 'chain-of-thought' process, allowing it to self-correct and iterate on its reasoning before delivering a final answer. For developers, this makes it an ideal engine for autonomous agents, complex debugging, and technical synthesis. It is released under the MIT license, offering significant flexibility for commercial integration and local deployment via open-weights, reducing reliance on proprietary APIs without sacrificing state-of-the-art performance in STEM domains.

Highlights

Advanced chain-of-thought reasoning for complex logic and math
Permissive MIT license for flexible commercial deployment
Competitive performance against top-tier proprietary reasoning models
Optimized for coding, technical synthesis, and autonomous agents

Usage

Install

# Install Hugging Face transformers
pip install transformers torch

SDK Usage

# Load model with transformers
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("deepseek-ai/DeepSeek-R1")
tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-R1")

Hugging Face Download

We recommend downloading the model via the Hugging Face CLI or Hub SDK.

Guidance：Before downloading, install huggingface_hub with:

Guidance

pip install -U huggingface_hub

CLI Download

Download the full repository

huggingface-cli download deepseek-ai/DeepSeek-R1

Download a single file to a local folder (e.g. config.json into ./dir)

huggingface-cli download deepseek-ai/DeepSeek-R1 config.json --local-dir ./dir

See the official docs for more CLI options

SDK Download

# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('deepseek-ai/DeepSeek-R1')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://huggingface.co/deepseek-ai/DeepSeek-R1

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/deepseek-ai/DeepSeek-R1

Model files are hosted on the Hugging Face Hub — download directly via HF CLI / SDK / Git, not through this site.

PyTorch / Transformers Usage

Install Transformers

pip install -U transformers torch

Load the model and run inference

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('deepseek-ai/DeepSeek-R1')
tokenizer = AutoTokenizer.from_pretrained('deepseek-ai/DeepSeek-R1')

Model Download

We recommend downloading the model via the ModelScope CLI or SDK.

Guidance：Before downloading, install ModelScope with:

Guidance

pip install modelscope

CLI Download

Download the full repository

modelscope download --model deepseek-ai/DeepSeek-R1

Download a single file to a local folder (e.g. README.md into ./dir)

modelscope download --model deepseek-ai/DeepSeek-R1 README.md --local_dir ./dir

See the docs for more CLI options

SDK Download

# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('deepseek-ai/DeepSeek-R1')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://www.modelscope.cn/deepseek-ai/DeepSeek-R1.git

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/deepseek-ai/DeepSeek-R1.git

ModelScope 模型页直接下载模型文件；无需将模型文件放在本站服务器。

Notebook Quickstart

Install the ModelScope library

pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

Load the model and run inference

from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'deepseek-ai/DeepSeek-R1')

Full Documentation

来源: HuggingFace

---
license: mit
library_name: transformers
---

DeepSeek-R1

<p align="center">
<a href="https://github.com/deepseek-ai/DeepSeek-R1/blob/main/DeepSeek_R1.pdf"><b>Paper Link</b>👁️</a>
</p>

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.

NOTE: Before running DeepSeek-R1 series models locally, we kindly recommend reviewing the Usage Recommendation section.

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 |
| DeepSeek-R1 | 671B | 37B | 128K | 🤗 HuggingFace |

</div>

DeepSeek-R1-Zero & DeepSeek-R1 are trained based on DeepSeek-V3-Base.
For more details regarding the model architecture, please refer to DeepSeek-V3 repository.

DeepSeek-R1-Distill Models

</div>

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 gene