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

Libraries

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

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

pipe = pipeline("text-generation", model="IAAR-Shanghai/MemPrivacy-4B-SFT")
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-SFT")
model = AutoModelForCausalLM.from_pretrained("IAAR-Shanghai/MemPrivacy-4B-SFT", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Use Docker

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

SGLang

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

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

MemPrivacy-4B-SFT

Commit History

Update README.md

6b4ac5f
verified

apocryphal commited on May 15

Update README.md

3a2d966
verified

Robot2050 commited on May 14

Update README.md

1d50f41
verified

Robot2050 commited on May 14

Update README.md

3a20ee8
verified

Robot2050 commited on May 14

Update README.md

98315d1
verified

Robot2050 commited on May 14

Update README.md

d5b6855
verified

Ding Chen commited on May 13

Update README.md

ab6e5f7
verified

Ding Chen commited on May 12

Update README.md

3a655d3
verified

Ding Chen commited on May 12

Update README.md

4c67cc5
verified

Robot2050 commited on May 11

Update README.md

133ff43
verified

Robot2050 commited on May 11

Update README.md

d7faab2
verified

Robot2050 commited on May 10

Upload MemPrivacy-4B-SFT

2de14ac
verified

Robot2050 commited on May 9

Update README.md

c736700
verified

Ding Chen commited on May 9

Upload MemPrivacy-4B-SFT

f229d02
verified

Robot2050 commited on May 8

Upload MemPrivacy-4B-SFT

025e3e9
verified

Robot2050 commited on May 8

initial commit

c5f5876
verified

Robot2050 commited on May 8

Commit History

Update README.md 6b4ac5f verified

Update README.md 3a2d966 verified

Update README.md 1d50f41 verified

Update README.md 3a20ee8 verified

Update README.md 98315d1 verified

Update README.md d5b6855 verified

Update README.md ab6e5f7 verified

Update README.md 3a655d3 verified

Update README.md 4c67cc5 verified

Update README.md 133ff43 verified

Update README.md d7faab2 verified

Upload MemPrivacy-4B-SFT 2de14ac verified

Update README.md c736700 verified

Upload MemPrivacy-4B-SFT f229d02 verified

Upload MemPrivacy-4B-SFT 025e3e9 verified

initial commit c5f5876 verified

Update README.md

6b4ac5f
verified

Update README.md

3a2d966
verified

Update README.md

1d50f41
verified

Update README.md

3a20ee8
verified

Update README.md

98315d1
verified

Update README.md

d5b6855
verified

Update README.md

ab6e5f7
verified

Update README.md

3a655d3
verified

Update README.md

4c67cc5
verified

Update README.md

133ff43
verified

Update README.md

d7faab2
verified

Upload MemPrivacy-4B-SFT

2de14ac
verified

Update README.md

c736700
verified

Upload MemPrivacy-4B-SFT

f229d02
verified

Upload MemPrivacy-4B-SFT

025e3e9
verified

initial commit

c5f5876
verified