Instructions to use deepseek-ai/DeepSeek-R1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepseek-ai/DeepSeek-R1 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-R1", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-R1", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-R1", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use deepseek-ai/DeepSeek-R1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepseek-ai/DeepSeek-R1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepseek-ai/DeepSeek-R1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepseek-ai/DeepSeek-R1

SGLang

How to use deepseek-ai/DeepSeek-R1 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "deepseek-ai/DeepSeek-R1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepseek-ai/DeepSeek-R1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "deepseek-ai/DeepSeek-R1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepseek-ai/DeepSeek-R1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deepseek-ai/DeepSeek-R1 with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/DeepSeek-R1
```

pezhmansamaniii commited on Apr 28, 2025

Commit

487b933

verified ·

1 Parent(s): 56d4cbb

Update README.md

Browse files

![155544.jpg](https://cdn-uploads.huggingface.co/production/uploads/67e0fdbf05add0af7c42dd4a/vts_n_eNZnGC8ichG06Mr.jpeg)

Files changed (1) hide show

README.md +12 -4

README.md CHANGED Viewed

@@ -138,7 +138,7 @@ We slightly change their configs and tokenizers. Please use our setting to run t
 | | 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 |
@@ -154,16 +154,20 @@ We slightly change their configs and tokenizers. Please use our setting to run t
 ### Distilled Model Evaluation
 <div align="center">
 | 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              |
@@ -201,7 +205,11 @@ You can also easily start a service using [SGLang](https://github.com/sgl-projec
 ```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:**

 | | 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) | 73.3 | 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 |
 ### Distilled Model Evaluation
+from transformers import AutoModelForCausalLM, AutoTokenizer
+model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-R1-Distill-Qwen-32B")
+tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-R1-Distill-Qwen-32B")
 <div align="center">
 | 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                          | 73.3              | 13.4              | 74.6            | 49.9                 | 49.9                 | 759               |
+| Claude-3.5-Sonnet-1022             | 16.0             | 52.7                 | 78.3            | 65.0                 | 93.9                 | 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                 | 83.9                 | 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              |
 ```bash
 python3 -m sglang.launch_server --model deepseek-ai/DeepSeek-R1-Distill-Qwen-32B --trust-remote-code --tp 2
 ```
+# مثال اجرا با Hugging Face بدون نیاز به پیکربندی اضافی
+from transformers import AutoModelForCausalLM, AutoTokenizer
+model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-R1-Distill-Qwen-32B")
+tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-R1-Distill-Qwen-32B")
 ### Usage Recommendations
 **We recommend adhering to the following configurations when utilizing the DeepSeek-R1 series models, including benchmarking, to achieve the expected performance:**