Instructions to use NIyueeE/Qwen3.5-0.8B-cocreator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NIyueeE/Qwen3.5-0.8B-cocreator with Transformers:

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

pipe = pipeline("image-text-to-text", model="NIyueeE/Qwen3.5-0.8B-cocreator")
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("NIyueeE/Qwen3.5-0.8B-cocreator")
model = AutoModelForMultimodalLM.from_pretrained("NIyueeE/Qwen3.5-0.8B-cocreator", 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 NIyueeE/Qwen3.5-0.8B-cocreator with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NIyueeE/Qwen3.5-0.8B-cocreator"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NIyueeE/Qwen3.5-0.8B-cocreator",
		"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/NIyueeE/Qwen3.5-0.8B-cocreator

SGLang

How to use NIyueeE/Qwen3.5-0.8B-cocreator 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 "NIyueeE/Qwen3.5-0.8B-cocreator" \
    --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": "NIyueeE/Qwen3.5-0.8B-cocreator",
		"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 "NIyueeE/Qwen3.5-0.8B-cocreator" \
        --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": "NIyueeE/Qwen3.5-0.8B-cocreator",
		"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"
						}
					}
				]
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use NIyueeE/Qwen3.5-0.8B-cocreator with Docker Model Runner:
```
docker model run hf.co/NIyueeE/Qwen3.5-0.8B-cocreator
```

NIyueeE commited on May 29

Commit

83e84f8

verified ·

1 Parent(s): d93974e

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -14

README.md CHANGED Viewed

@@ -39,7 +39,7 @@ NVIDIA A100-SXM4-40GB. Num GPUs = 1. Max memory: 39.494 GB.
 Torch: 2.10.0+cu128. CUDA: 8.0. CUDA Toolkit: 12.8. Triton: 3.6.0
 Bfloat16 = TRUE. FA [Xformers = 0.0.35. FA2 = False]
-Num examples = 1,227 | Num Epochs = 5 | Total steps = 50
 Batch size per device = 128 | Gradient accumulation steps = 1
 Total batch size (128 x 1 x 1) = 128
 Trainable parameters = 13,181,952 of 866,167,872 (1.52% trained)
@@ -65,22 +65,10 @@ See [`finetune_cocreator_coclab.ipynb`](./finetune_cocreator_coclab.ipynb) for t
 | Optimizer | adamw_8bit |
 | Learning rate | 5e-5 (cosine schedule) |
 | Max steps | 50 |
-| Epochs | 5 |
 | Gradient checkpointing | unsloth |
 | Resolution | 800×450 (resized) |
-## Training Results
-| Step | Loss |
-|------|------|
-| 10 | 20.36 |
-| 20 | 12.69 |
-| 30 | 8.22 |
-| 40 | 7.06 |
-| 50 | 6.79 |
-The model was trained for 50 steps (~5 epochs), with loss dropping from 20.36 to 6.79, indicating steady convergence on the driving scene causal understanding task.
 ## Usage
 ```python

 Torch: 2.10.0+cu128. CUDA: 8.0. CUDA Toolkit: 12.8. Triton: 3.6.0
 Bfloat16 = TRUE. FA [Xformers = 0.0.35. FA2 = False]
+Num examples = 1,227 | Num Epochs = 7 | Total steps = 50
 Batch size per device = 128 | Gradient accumulation steps = 1
 Total batch size (128 x 1 x 1) = 128
 Trainable parameters = 13,181,952 of 866,167,872 (1.52% trained)
 | Optimizer | adamw_8bit |
 | Learning rate | 5e-5 (cosine schedule) |
 | Max steps | 50 |
+| Epochs | 7 |
 | Gradient checkpointing | unsloth |
 | Resolution | 800×450 (resized) |
 ## Usage
 ```python