Instructions to use SwissNeuron/Qwen3.8-27B-SwissNeuron-Derisked with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SwissNeuron/Qwen3.8-27B-SwissNeuron-Derisked with Transformers:

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

pipe = pipeline("image-text-to-text", model="SwissNeuron/Qwen3.8-27B-SwissNeuron-Derisked")
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("SwissNeuron/Qwen3.8-27B-SwissNeuron-Derisked")
model = AutoModelForMultimodalLM.from_pretrained("SwissNeuron/Qwen3.8-27B-SwissNeuron-Derisked", 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 SwissNeuron/Qwen3.8-27B-SwissNeuron-Derisked with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SwissNeuron/Qwen3.8-27B-SwissNeuron-Derisked"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SwissNeuron/Qwen3.8-27B-SwissNeuron-Derisked",
		"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/SwissNeuron/Qwen3.8-27B-SwissNeuron-Derisked

SGLang

How to use SwissNeuron/Qwen3.8-27B-SwissNeuron-Derisked 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 "SwissNeuron/Qwen3.8-27B-SwissNeuron-Derisked" \
    --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": "SwissNeuron/Qwen3.8-27B-SwissNeuron-Derisked",
		"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 "SwissNeuron/Qwen3.8-27B-SwissNeuron-Derisked" \
        --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": "SwissNeuron/Qwen3.8-27B-SwissNeuron-Derisked",
		"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 SwissNeuron/Qwen3.8-27B-SwissNeuron-Derisked with Docker Model Runner:
```
docker model run hf.co/SwissNeuron/Qwen3.8-27B-SwissNeuron-Derisked
```

Swiss-guy commited on 2 days ago

Commit

2d79793

verified ·

1 Parent(s): d1f61d6

Correct canonical VLM task and multimodal tags

Browse files

Files changed (1) hide show

README.md +6 -2

README.md CHANGED Viewed

@@ -1,7 +1,7 @@
 ---
 license: other
 base_model: Qwen/Qwen3.8-27B
-pipeline_tag: text-generation
 library_name: transformers
 tags:
 - qwen3.8
@@ -10,6 +10,10 @@ tags:
 - long-context
 - yarn
 - 1m-context
 - swissneuron
 model_name: Qwen3.8-27B-SwissNeuron-Derisked
 ---
@@ -28,7 +32,7 @@ SwissNeuron is intended to provide Swiss-quality model engineering: precise prov
 - **Capability-preserving post-training**: focused internal training rather than broad, high-learning-rate continued pretraining
 - **Conservative derisking**: a low-strength, single-pass internal direction-removal procedure applied only after training
 - **Original MTP, multimodal processor, tokenizer, and chat template retained**
-- **No quantization**: this release contains the merged BF16 weights; quantized editions will follow separately
 ## Important mode behavior

 ---
 license: other
 base_model: Qwen/Qwen3.8-27B
+pipeline_tag: image-text-to-text
 library_name: transformers
 tags:
 - qwen3.8
 - long-context
 - yarn
 - 1m-context
+- multimodal
+- vision
+- reasoning
+- image-text-to-text
 - swissneuron
 model_name: Qwen3.8-27B-SwissNeuron-Derisked
 ---
 - **Capability-preserving post-training**: focused internal training rather than broad, high-learning-rate continued pretraining
 - **Conservative derisking**: a low-strength, single-pass internal direction-removal procedure applied only after training
 - **Original MTP, multimodal processor, tokenizer, and chat template retained**
+- **Native BF16 release**: verified FP8, NVFP4, GPTQ INT4, and GGUF editions are linked below
 ## Important mode behavior