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)

# pip install -U transformers accelerate
# 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, device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

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
```

Evaluation of DeepSeek-R1 on Continuous Dynamic Systems & Stiff Regimes (LaplaceReason Benchmark)

#258

by pabloenrique - opened 1 day ago

Discussion

pabloenrique

1 day ago

•

edited 1 day ago

Hi DeepSeek team & community,

We evaluated DeepSeek-R1 on continuous dynamic systems and high-order ODEs ($K > 18$) using deterministically certified ground-truth solutions ($|R|_\infty < 10^{-14}$) without root-finding.

While R1 excels at discrete mathematics (MATH/AIME), it exhibits phase drift and structural divergence on multiscale stiff systems when polynomial conditioning collapses (Wilkinson regime).

We have released the open evaluation split and deterministic verifier here:
• Dataset: https://huggingface.co/datasets/pabloenrique/LaplaceReason-Continuous-Dynamics
• Preprint (DOI CERN/Zenodo): https://doi.org/10.5281/zenodo.23760958
• ResearchGate Paper:https://www.researchgate.net/publication/417149835_LaplaceReason_A_Certified_Benchmark_and_Continuous_Dynamic_Systems_Reasoning_Suite_for_Frontier_Large_Language_Models

We invite the community and the DeepSeek team to evaluate reasoning trajectories on continuous dynamics!

ZwinZ

1 day ago

•

edited 1 day ago

Support 💪

pabloenrique

1 day ago

Thanks for the support @ZwinZ !

We have just deployed an interactive live Space featuring the full empirical Leaderboard and a real-time ZeroGPU multi-model stress-tester (comparing DeepSeek-R1, Claude 3.5 Sonnet, and Qwen): 🔗 https://huggingface.co/spaces/pabloenrique/LaplaceReason-Leaderboard

Anyone in the community can test the stability limits and evaluate the open benchmark split. Looking forward to your feedback!

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