Instructions to use sequelbox/Qwen3.5-27B-DAG-Reasoning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sequelbox/Qwen3.5-27B-DAG-Reasoning with Transformers:

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

pipe = pipeline("image-text-to-text", model="sequelbox/Qwen3.5-27B-DAG-Reasoning")
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 AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sequelbox/Qwen3.5-27B-DAG-Reasoning")
model = AutoModelForCausalLM.from_pretrained("sequelbox/Qwen3.5-27B-DAG-Reasoning")
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 = 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 Settings

vLLM

How to use sequelbox/Qwen3.5-27B-DAG-Reasoning with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sequelbox/Qwen3.5-27B-DAG-Reasoning"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sequelbox/Qwen3.5-27B-DAG-Reasoning",
		"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/sequelbox/Qwen3.5-27B-DAG-Reasoning

SGLang

How to use sequelbox/Qwen3.5-27B-DAG-Reasoning 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 "sequelbox/Qwen3.5-27B-DAG-Reasoning" \
    --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": "sequelbox/Qwen3.5-27B-DAG-Reasoning",
		"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 "sequelbox/Qwen3.5-27B-DAG-Reasoning" \
        --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": "sequelbox/Qwen3.5-27B-DAG-Reasoning",
		"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 sequelbox/Qwen3.5-27B-DAG-Reasoning with Docker Model Runner:
```
docker model run hf.co/sequelbox/Qwen3.5-27B-DAG-Reasoning
```

Upload folder using huggingface_hub

by sequelbox - opened Mar 12

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+1243

-860

Upload folder using huggingface_hub1f8aec68

sequelbox

Owner Mar 12

No description provided.

Delete model-00001-of-00002.safetensors4cb1dc42

Delete model-00002-of-00002.safetensors69cf5706

sequelbox

Owner Mar 12

This PR merges the untrained 'visual' and 'mtp' base weights from Qwen/Qwen3.5-27B. This does not modify the trained weights, but improves the user experience by directly 'unlocking' the original Qwen 3.5 multimodal capabilities instead of forcing the user to swap or merge them.

We're not expecting any additional changes to the weights from this point, but if anything is found it will be addressed.

sequelbox changed pull request status to merged Mar 12

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