Instructions to use deepseek-ai/DeepSeek-R1-0528 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepseek-ai/DeepSeek-R1-0528 with Transformers:

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

pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-R1-0528", 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-R1-0528", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-R1-0528", 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-R1-0528 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepseek-ai/DeepSeek-R1-0528"
# 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-R1-0528",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepseek-ai/DeepSeek-R1-0528

SGLang

How to use deepseek-ai/DeepSeek-R1-0528 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-R1-0528" \
    --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-R1-0528",
		"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-R1-0528" \
        --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-R1-0528",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deepseek-ai/DeepSeek-R1-0528 with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/DeepSeek-R1-0528
```

fantastic 👍👍👍

#19

by AIARCHAEA - opened May 28, 2025

Discussion

AIARCHAEA

May 28, 2025

way better than the OG. and performs significantly better in creative writing when it skips its own reasoning. 👍 love it.

Dampfinchen

May 28, 2025

•

edited May 28, 2025

Yeah creative writing got a nice boost.

What I did notice though and the other deepseek models is that character traits for shorter chat turns get repeated over and over instead of moving the roleplay forward in interesting ways. Basically if you have character X do Y for a few turns, the character will continue to do Y while other models may have moved on to something more interesting and less repetitive.

AIARCHAEA

May 28, 2025

Yeah creative writing got a nice boost.

What I did notice though and the other deepseek models is that character traits for shorter chat turns get repeated over and over instead of moving the roleplay forward in interesting ways. Basically if you have character X do Y for a few turns, the character will continue to do Y while other models may have moved on to something more interesting and less repetitive.

Can't say I've had that experience but I usually have rather long responses and allow the model to talk for user (story writing with a dash of roleplay), so overall its doing more and pushes the story forward really well. It hasn't stalled at all. But perhaps its due to the fact I give it a CoD like "thinking" format to follow instead of its own reasoning which mentions story progression.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment