Instructions to use CooperBench/Qwen3.5-9B-cooperdata-bridge-midtrain-32k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CooperBench/Qwen3.5-9B-cooperdata-bridge-midtrain-32k with Transformers:

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

pipe = pipeline("image-text-to-text", model="CooperBench/Qwen3.5-9B-cooperdata-bridge-midtrain-32k")
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("CooperBench/Qwen3.5-9B-cooperdata-bridge-midtrain-32k")
model = AutoModelForMultimodalLM.from_pretrained("CooperBench/Qwen3.5-9B-cooperdata-bridge-midtrain-32k", 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 CooperBench/Qwen3.5-9B-cooperdata-bridge-midtrain-32k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CooperBench/Qwen3.5-9B-cooperdata-bridge-midtrain-32k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CooperBench/Qwen3.5-9B-cooperdata-bridge-midtrain-32k",
		"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/CooperBench/Qwen3.5-9B-cooperdata-bridge-midtrain-32k

SGLang

How to use CooperBench/Qwen3.5-9B-cooperdata-bridge-midtrain-32k 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 "CooperBench/Qwen3.5-9B-cooperdata-bridge-midtrain-32k" \
    --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": "CooperBench/Qwen3.5-9B-cooperdata-bridge-midtrain-32k",
		"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 "CooperBench/Qwen3.5-9B-cooperdata-bridge-midtrain-32k" \
        --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": "CooperBench/Qwen3.5-9B-cooperdata-bridge-midtrain-32k",
		"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 CooperBench/Qwen3.5-9B-cooperdata-bridge-midtrain-32k with Docker Model Runner:
```
docker model run hf.co/CooperBench/Qwen3.5-9B-cooperdata-bridge-midtrain-32k
```

Qwen3.5-9B-cooperdata-bridge-midtrain-32k

File size: 2,870 Bytes

e6e3ba0


Fetching 23 files:   0%|          | 0/23 [00:00<?, ?it/s]
Fetching 23 files:   4%|▍         | 1/23 [00:00<00:04,  4.59it/s]
Fetching 23 files: 100%|██████████| 23/23 [00:00<00:00, 102.58it/s]

Loading weights:   0%|          | 0/760 [00:00<?, ?it/s]
Loading weights:   4%|▍         | 29/760 [00:00<00:02, 283.50it/s]
Loading weights:   8%|▊         | 58/760 [00:00<00:03, 214.02it/s]
Loading weights:  11%|█         | 81/760 [00:00<00:03, 199.46it/s]
Loading weights:  13%|█▎        | 102/760 [00:00<00:03, 192.70it/s]
Loading weights:  17%|█▋        | 129/760 [00:00<00:03, 206.62it/s]
Loading weights:  20%|█▉        | 150/760 [00:00<00:03, 196.64it/s]
Loading weights:  23%|██▎       | 176/760 [00:00<00:02, 209.78it/s]
Loading weights:  26%|██▌       | 198/760 [00:00<00:02, 196.56it/s]
Loading weights:  29%|██▉       | 222/760 [00:01<00:02, 203.62it/s]
Loading weights:  32%|███▏      | 243/760 [00:01<00:02, 197.81it/s]
Loading weights:  35%|███▍      | 263/760 [00:01<00:02, 181.65it/s]
Loading weights:  38%|███▊      | 287/760 [00:01<00:02, 193.89it/s]
Loading weights:  40%|████      | 307/760 [00:01<00:02, 170.98it/s]
Loading weights:  44%|████▎     | 332/760 [00:01<00:02, 190.86it/s]
Loading weights:  46%|████▋     | 352/760 [00:01<00:02, 185.27it/s]
Loading weights:  49%|████▉     | 372/760 [00:01<00:02, 185.96it/s]
Loading weights:  51%|█████▏    | 391/760 [00:02<00:01, 185.40it/s]
Loading weights:  54%|█████▍    | 412/760 [00:02<00:01, 182.23it/s]
Loading weights:  61%|██████    | 465/760 [00:02<00:01, 274.09it/s]
Loading weights:  72%|███████▏  | 544/760 [00:02<00:00, 417.16it/s]
Loading weights:  80%|███████▉  | 605/760 [00:02<00:00, 471.81it/s]
Loading weights:  89%|████████▉ | 680/760 [00:02<00:00, 550.57it/s]
Loading weights:  99%|█████████▊| 749/760 [00:02<00:00, 590.41it/s]
Loading weights: 100%|██████████| 760/760 [00:02<00:00, 285.50it/s]
[2026-07-28 15:32:09,948] [WARNING] [py.warnings._showwarnmsg:110] [PID:77] /root/miniconda3/envs/py3.11/lib/python3.11/site-packages/triton/language/core.py:2284: UserWarning: tl.make_block_ptr is deprecated. Use TensorDescriptor or tl.make_tensor_descriptor instead.
  warn("tl.make_block_ptr is deprecated. Use TensorDescriptor or tl.make_tensor_descriptor instead.")

[2026-07-28 15:33:13,335] [WARNING] [py.warnings._showwarnmsg:110] [PID:77] /root/miniconda3/envs/py3.11/lib/python3.11/site-packages/triton/language/core.py:2284: UserWarning: tl.make_block_ptr is deprecated. Use TensorDescriptor or tl.make_tensor_descriptor instead.
  warn("tl.make_block_ptr is deprecated. Use TensorDescriptor or tl.make_tensor_descriptor instead.")