Instructions to use pybbb/Qwen3.6-27B-SecOPD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pybbb/Qwen3.6-27B-SecOPD with Transformers:

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

pipe = pipeline("image-text-to-text", model="pybbb/Qwen3.6-27B-SecOPD")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("pybbb/Qwen3.6-27B-SecOPD")
model = AutoModelForMultimodalLM.from_pretrained("pybbb/Qwen3.6-27B-SecOPD", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use pybbb/Qwen3.6-27B-SecOPD with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pybbb/Qwen3.6-27B-SecOPD"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pybbb/Qwen3.6-27B-SecOPD",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/pybbb/Qwen3.6-27B-SecOPD

SGLang

How to use pybbb/Qwen3.6-27B-SecOPD 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 "pybbb/Qwen3.6-27B-SecOPD" \
    --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": "pybbb/Qwen3.6-27B-SecOPD",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "pybbb/Qwen3.6-27B-SecOPD" \
        --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": "pybbb/Qwen3.6-27B-SecOPD",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use pybbb/Qwen3.6-27B-SecOPD with Docker Model Runner:
```
docker model run hf.co/pybbb/Qwen3.6-27B-SecOPD
```

pybbb

nielsr HF Staff commited on Aug 30

Commit

c68d535

1 Parent(s): 1a1af14

Add links to paper and project page (#1)

Browse files

- Add links to paper and project page (b2433e96c3c8402ff4727c96d7069e59a65f4e6f)

Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

Files changed (1) hide show

README.md +17 -14

README.md CHANGED Viewed

@@ -1,25 +1,28 @@
 ---
 base_model: Qwen/Qwen3.6-27B
 library_name: transformers
-pipeline_tag: image-text-to-text
 license: apache-2.0
-language:
-  - en
 tags:
-  - qwen
-  - qwen3.6
-  - qwen3_5
-  - secopd
-  - prompt-injection
-  - model-security
-  - on-policy-distillation
-  - safetensors
-  - multimodal
-  - thinking
 ---
 # Qwen3.6-27B-Thinking-SecOPD
 This repository contains the merged Qwen3.6-27B checkpoint used for the main
 experiments in **SecOPD: Mitigating Adaptive Prompt Injections by On-Policy
 Distillation**. SecOPD uses clean-context token-level supervision to improve
@@ -171,4 +174,4 @@ Qwen3.6-27B base model.
   author    = {Peng, Yibo and Lian, Long and Wagner, David and Chen, Sizhe},
   year      = {2026}
 }
-```

 ---
 base_model: Qwen/Qwen3.6-27B
+language:
+- en
 library_name: transformers
 license: apache-2.0
+pipeline_tag: image-text-to-text
 tags:
+- qwen
+- qwen3.6
+- qwen3_5
+- secopd
+- prompt-injection
+- model-security
+- on-policy-distillation
+- safetensors
+- multimodal
+- thinking
 ---
 # Qwen3.6-27B-Thinking-SecOPD
+**Paper**: [SecOPD: Mitigating Adaptive Prompt Injections by On-Policy Distillation](https://huggingface.co/papers/2608.21500)
+**Project page**: [https://pppyb.github.io/SecOPD/](https://pppyb.github.io/SecOPD/)
 This repository contains the merged Qwen3.6-27B checkpoint used for the main
 experiments in **SecOPD: Mitigating Adaptive Prompt Injections by On-Policy
 Distillation**. SecOPD uses clean-context token-level supervision to improve
   author    = {Peng, Yibo and Lian, Long and Wagner, David and Chen, Sizhe},
   year      = {2026}
 }
+```