Instructions to use IAAR-Shanghai/MemPrivacy-4B-RL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use IAAR-Shanghai/MemPrivacy-4B-RL with Transformers:

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

pipe = pipeline("text-generation", model="IAAR-Shanghai/MemPrivacy-4B-RL")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("IAAR-Shanghai/MemPrivacy-4B-RL")
model = AutoModelForCausalLM.from_pretrained("IAAR-Shanghai/MemPrivacy-4B-RL")
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 IAAR-Shanghai/MemPrivacy-4B-RL with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "IAAR-Shanghai/MemPrivacy-4B-RL"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "IAAR-Shanghai/MemPrivacy-4B-RL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/IAAR-Shanghai/MemPrivacy-4B-RL

SGLang

How to use IAAR-Shanghai/MemPrivacy-4B-RL 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 "IAAR-Shanghai/MemPrivacy-4B-RL" \
    --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": "IAAR-Shanghai/MemPrivacy-4B-RL",
		"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 "IAAR-Shanghai/MemPrivacy-4B-RL" \
        --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": "IAAR-Shanghai/MemPrivacy-4B-RL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use IAAR-Shanghai/MemPrivacy-4B-RL with Docker Model Runner:
```
docker model run hf.co/IAAR-Shanghai/MemPrivacy-4B-RL
```

Robot2050 commited on 14 days ago

Commit

ba8411d

verified ·

1 Parent(s): e2cc7d0

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -1

README.md CHANGED Viewed

@@ -88,7 +88,12 @@ JSON
 ]
 ```
-### Usage
 ```py
 import json

 ]
 ```
+### Structured Privacy Extraction with vLLM
+This example shows how to use vLLM to perform structured privacy information extraction from user-AI dialogues. The model is guided by a privacy classification prompt and constrained by a JSON schema to return only PL2, PL3, and PL4 sensitive information.
+The output schema enforces a consistent array format containing the original text, privacy type, and privacy level for each extracted item. Low-temperature sampling and structured output decoding are used to improve reliability and make the results easier to parse in downstream applications.
 ```py
 import json