Instructions to use RealSafe/RealSafe-R1-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RealSafe/RealSafe-R1-8B with Transformers:

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

pipe = pipeline("text-generation", model="RealSafe/RealSafe-R1-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RealSafe/RealSafe-R1-8B")
model = AutoModelForCausalLM.from_pretrained("RealSafe/RealSafe-R1-8B")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use RealSafe/RealSafe-R1-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RealSafe/RealSafe-R1-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RealSafe/RealSafe-R1-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RealSafe/RealSafe-R1-8B

SGLang

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

Docker Model Runner
How to use RealSafe/RealSafe-R1-8B with Docker Model Runner:
```
docker model run hf.co/RealSafe/RealSafe-R1-8B
```

nielsr HF Staff commited on Apr 19, 2025

Commit

62912d2

verified ·

1 Parent(s): 8421eac

Add pipeline tag and paper link

Browse files

This PR improves the model card by adding the correct paper link as well as updates the pipeline tag, ensuring people can find your model at https://huggingface.co/models?pipeline_tag=text-generation.

Files changed (1) hide show

README.md +7 -4

README.md CHANGED Viewed

@@ -1,12 +1,15 @@
 ---
 library_name: transformers
 license: mit
 languages:
 - en
 - zh
-base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
-tags:
-- safe
 ---
-# RealSafe-R1-8B

 ---
+base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
 library_name: transformers
 license: mit
+tags:
+- safe
 languages:
 - en
 - zh
+pipeline_tag: text-generation
 ---
+# RealSafe-R1-8B
+This model is based on the paper [SemiEvol: Semi-supervised Fine-tuning for LLM Adaptation](https://huggingface.co/papers/2504.10081).