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
```

Fix broken chat template

#80

by erichartford - opened May 31, 2025

base: refs/heads/main

←

from: refs/pr/80

Discussion Files changed

-1

Fix broken chat template9adb7fdb

erichartford

May 31, 2025

•

edited May 31, 2025

{% if add_generation_prompt and not ns.is_last_user and not ns.is_tool %}

Should be

{% if add_generation_prompt and ns.is_last_user and not ns.is_tool %}

Thanks to Hot Aisle for lending me the excelent mi300x node used to validate this.

erichartford

May 31, 2025

Please also see:

https://huggingface.co/deepseek-ai/DeepSeek-R1-0528/discussions/69

yasu-oh

Jun 1, 2025

There is also an operational bug.
In the current chat template, even when tool_calls == [], it is incorrectly treated as if there is a tool call.

{%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %}

Wouldn't it be better to add a length check and store the presence or absence of a tool call as a separate variable, as shown below?

{% set has_tools = message['tool_calls'] is defined and message['tool_calls'] is not none and message['tool_calls']|length > 0 %}
{%- if has_tools and message['role'] == 'assistant' %}
  [Code for the case when tools are present]
{%- endif %}
{%- if not has_tools and message['role'] == 'assistant' %}
  [Code for the case when no tools are present]
{%- endif %}
{%- if message['role'] == 'tool' %}

yasu-oh

Jun 1, 2025

Here is the updated template that addresses the two reported issues. Please refer to it for your reference.
https://huggingface.co/spaces/huggingfacejs/chat-template-playground?modelId=yasu-oh%2FLlama-3-Swallow-Infused-R1776-70B

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

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment