Instructions to use AI-ISL/DeepSeek-R1-Distill-Qwen-7B-SP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AI-ISL/DeepSeek-R1-Distill-Qwen-7B-SP with Transformers:

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

pipe = pipeline("text-generation", model="AI-ISL/DeepSeek-R1-Distill-Qwen-7B-SP")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AI-ISL/DeepSeek-R1-Distill-Qwen-7B-SP")
model = AutoModelForCausalLM.from_pretrained("AI-ISL/DeepSeek-R1-Distill-Qwen-7B-SP")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AI-ISL/DeepSeek-R1-Distill-Qwen-7B-SP with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AI-ISL/DeepSeek-R1-Distill-Qwen-7B-SP"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AI-ISL/DeepSeek-R1-Distill-Qwen-7B-SP",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AI-ISL/DeepSeek-R1-Distill-Qwen-7B-SP

SGLang

How to use AI-ISL/DeepSeek-R1-Distill-Qwen-7B-SP 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 "AI-ISL/DeepSeek-R1-Distill-Qwen-7B-SP" \
    --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": "AI-ISL/DeepSeek-R1-Distill-Qwen-7B-SP",
		"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 "AI-ISL/DeepSeek-R1-Distill-Qwen-7B-SP" \
        --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": "AI-ISL/DeepSeek-R1-Distill-Qwen-7B-SP",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AI-ISL/DeepSeek-R1-Distill-Qwen-7B-SP with Docker Model Runner:
```
docker model run hf.co/AI-ISL/DeepSeek-R1-Distill-Qwen-7B-SP
```

SAFEPATH-R-7B

This model is the SAFEPATH-aligned version of DeepSeek-R1-Distill-Qwen-7B, fine-tuned using prefix-only safety priming.

Model Description

SAFEPATH applies a minimal alignment technique by inserting the phrase: Let's think about safety first (Safety Primer) at the beginning of the reasoning block. This encourages the model to engage in safer reasoning without reducing its reasoning performance.

🔐 Improved Safety: Reduces harmful outputs (e.g., StrongReject, BeaverTails) and is robust to jailbreak attacks
🧠 Preserved Reasoning: Maintains accuracy on MATH500, GPQA, and AIME24
⚡ Efficiency: Fine-tuned with only 100 steps