Instructions to use oberus/qwen3.5-4b-privacy-defender with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use oberus/qwen3.5-4b-privacy-defender with Transformers:

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

pipe = pipeline("text-generation", model="oberus/qwen3.5-4b-privacy-defender")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("oberus/qwen3.5-4b-privacy-defender")
model = AutoModelForMultimodalLM.from_pretrained("oberus/qwen3.5-4b-privacy-defender", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use oberus/qwen3.5-4b-privacy-defender with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "oberus/qwen3.5-4b-privacy-defender"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "oberus/qwen3.5-4b-privacy-defender",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/oberus/qwen3.5-4b-privacy-defender

SGLang

How to use oberus/qwen3.5-4b-privacy-defender 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 "oberus/qwen3.5-4b-privacy-defender" \
    --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": "oberus/qwen3.5-4b-privacy-defender",
		"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 "oberus/qwen3.5-4b-privacy-defender" \
        --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": "oberus/qwen3.5-4b-privacy-defender",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use oberus/qwen3.5-4b-privacy-defender with Docker Model Runner:
```
docker model run hf.co/oberus/qwen3.5-4b-privacy-defender
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Qwen3.5-4B Privacy Defender

A privacy-preserving prompt-rewriting model. It rewrites a user's message so it can be sent to an external chatbot without revealing personal identity (location, profession, age, gender, family/relationship status, socioeconomic status), while preserving the original meaning and intent.

This is a fine-tuned derivative of Qwen/Qwen3.5-4B (SFT followed by DPO). It is not an official Qwen model.

Intended use

On-device rewriting of chat prompts before they leave the user's machine. Developed as the engineering artifact of a master's thesis on protecting user privacy in long-term AI conversations.

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tok = AutoTokenizer.from_pretrained("oberus/qwen3.5-4b-privacy-defender", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    "oberus/qwen3.5-4b-privacy-defender", torch_dtype="auto",
    device_map="auto", trust_remote_code=True)

SYSTEM = ("You are a privacy-preserving rewriting assistant. Rewrite the user's message "
          "so it can be safely sent to an external AI chatbot without revealing the user's "
          "personal identity ...")  # full prompt in the thesis repo

messages = [{"role": "system", "content": SYSTEM},
            {"role": "user", "content": "Hi, I'm Ivan, a nurse in Boston."}]
enc = tok.apply_chat_template(messages, add_generation_prompt=True,
                             return_tensors="pt", return_dict=True).to(model.device)
out = model.generate(**enc, max_new_tokens=256, do_sample=False)
print(tok.decode(out[0][enc["input_ids"].shape[1]:], skip_special_tokens=True))

License

Downloads last month: 335

Safetensors

Model size

5B params

Tensor type

F32

Model tree for oberus/qwen3.5-4b-privacy-defender

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Finetuned

(631)

this model

Quantizations

1 model