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")
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-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
```

Robot2050 commited on about 7 hours ago

Commit

98315d1

verified ·

1 Parent(s): d5b6855

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -278,7 +278,7 @@ Current Input Dialogue: {{
 model_name_or_path=""
 tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
-sampling_params = SamplingParams(temperature=0.1, top_p=0.1, repetition_penalty=1.05,structured_outputs=StructuredOutputsParams(json=privacy_schema))
 model = LLM(model=model_name_or_path,tensor_parallel_size=1, pipeline_parallel_size=1, dtype='float16',gpu_memory_utilization=0.9)

 model_name_or_path=""
 tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
+sampling_params = SamplingParams(temperature=0.1, top_p=0.1, repetition_penalty=1.05,max_tokens=6144,structured_outputs=StructuredOutputsParams(json=privacy_schema))
 model = LLM(model=model_name_or_path,tensor_parallel_size=1, pipeline_parallel_size=1, dtype='float16',gpu_memory_utilization=0.9)