Instructions to use deepseek-ai/DeepSeek-R1-0528-Qwen3-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepseek-ai/DeepSeek-R1-0528-Qwen3-8B with Transformers:

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

pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-R1-0528-Qwen3-8B")
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-Qwen3-8B")
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-R1-0528-Qwen3-8B")
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
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use deepseek-ai/DeepSeek-R1-0528-Qwen3-8B 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-Qwen3-8B"
# 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-Qwen3-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B

SGLang

How to use deepseek-ai/DeepSeek-R1-0528-Qwen3-8B 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-Qwen3-8B" \
    --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-Qwen3-8B",
		"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-Qwen3-8B" \
        --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-Qwen3-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deepseek-ai/DeepSeek-R1-0528-Qwen3-8B with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
```

Any plans on gemma series? ;-;

by Nakdesu - opened May 29, 2025

Discussion

Nakdesu

May 29, 2025

•

edited May 29, 2025

gemma has better multilinguality and vision, plus it is generally creative.

tarruda

May 29, 2025

Or better yet: Release the distillation process recipe so anyone can reproduce it in other open models

qe2

May 29, 2025

Gemma has bad license. more like worst.

ggnoy

May 29, 2025

Gemma has bad license. more like worst.

You are not going to deploy this in commercial environment anyway. Might as well get the best. Qwen is overfried on stem and math, has zero capabilities besides those two domains.

Dampfinchen

May 29, 2025

IMO they should make their own architecture again. There's really no need to use Qwen or Gemma, DeepSeek has an incredible architecture they just have to scale it down. They did with Deepseek V2 Lite and I'm not sure why they abandoned this approach. It would also support MLA and have the same training data as the big R1 instead of just training on its outputs.

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