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

Libraries

How to use trohrbaugh/Qwen3.8-27B-heretic-ara with Transformers:

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

pipe = pipeline("image-text-to-text", model="trohrbaugh/Qwen3.8-27B-heretic-ara")
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("trohrbaugh/Qwen3.8-27B-heretic-ara")
model = AutoModelForMultimodalLM.from_pretrained("trohrbaugh/Qwen3.8-27B-heretic-ara", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use trohrbaugh/Qwen3.8-27B-heretic-ara with vLLM:

Install from pip and serve model

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

SGLang

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

This model is still fairly prone to refusals in thinking mode

by cchickk - opened 20 days ago

Discussion

cchickk

20 days ago

While it performs great in intuitive (standard) mode, thinking mode seems to be an exception and still has a high refusal rate."

trohrbaugh

Owner 19 days ago

Not with the 400 questions I have and another 1568 currated for country specific sensitivity. ... so not sure what you are seeing?

VINAY-UMRETHE

19 days ago

While it performs great in intuitive (standard) mode, thinking mode seems to be an exception and still has a high refusal rate."

This model was created with v1.2.0 ARA + Custom modifications, so I suspect it lacks the "Response-Prefix" update that ignores <think>...</think> content to better detect the refusals. Because if refusals are not properly detected, then they can be invalid as false-positives.

trohrbaugh changed discussion status to closed 19 days ago

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment