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
```

Improve model card metadata and paper referencing

by nielsr HF Staff - opened about 14 hours ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+31

-320

nielsr

about 14 hours ago

Hi! I'm Niels from the community science team at Hugging Face.

This PR aims to improve the model card for MemPrivacy-4B-RL by:

Adding library_name: transformers to the YAML metadata to enable the automated code snippet feature on the Hub.
Moving the ArXiv ID from the YAML metadata to the Markdown content section, as per Hugging Face documentation guidelines.
Cleaning up the metadata for better discoverability.

The model is based on the paper MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents.

Improve model card metadata and paper referencing80427924

Robot2050

Memtensor Research Group org about 11 hours ago

Thank you for the feedback. We’ve made the requested updates to better align the model card with Hugging Face metadata standards.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Cannot merge

This branch has merge conflicts in the following files:

README.md

· Sign up or log in to comment