Instructions to use CauchyFan/Genesis-Qwen3vl-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CauchyFan/Genesis-Qwen3vl-8B with Transformers:

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

pipe = pipeline("image-text-to-text", model="CauchyFan/Genesis-Qwen3vl-8B")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("CauchyFan/Genesis-Qwen3vl-8B")
model = AutoModelForMultimodalLM.from_pretrained("CauchyFan/Genesis-Qwen3vl-8B", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use CauchyFan/Genesis-Qwen3vl-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CauchyFan/Genesis-Qwen3vl-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CauchyFan/Genesis-Qwen3vl-8B",
		"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/CauchyFan/Genesis-Qwen3vl-8B

SGLang

How to use CauchyFan/Genesis-Qwen3vl-8B 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 "CauchyFan/Genesis-Qwen3vl-8B" \
    --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": "CauchyFan/Genesis-Qwen3vl-8B",
		"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 "CauchyFan/Genesis-Qwen3vl-8B" \
        --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": "CauchyFan/Genesis-Qwen3vl-8B",
		"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 CauchyFan/Genesis-Qwen3vl-8B with Docker Model Runner:
```
docker model run hf.co/CauchyFan/Genesis-Qwen3vl-8B
```

Genesis-Qwen3vl-8B

Qwen3-VL 8B checkpoint from the stem_final_grpo_rubric_general training run, at step 524. Uploaded in Hugging Face Transformers format.

The checkpoint contains BF16 safetensors weights, a weight index, tokenizer, chat template, image processor, video processor, and generation configuration. The config dtype metadata is set to bfloat16 to match the saved tensors. Weight tensors are preserved without conversion.

Loading

Use a Transformers release with Qwen3-VL support (the training config records Transformers 4.57.0). Load the public checkpoint directly from Hugging Face:

import torch
from transformers import AutoProcessor, Qwen3VLForConditionalGeneration

repo_id = "CauchyFan/Genesis-Qwen3vl-8B"
processor = AutoProcessor.from_pretrained(repo_id)
model = Qwen3VLForConditionalGeneration.from_pretrained(
    repo_id, dtype=torch.bfloat16, device_map="auto"
)

Evaluation dataset

UNREAL Benchmark provides 600 visual question-answering examples across five domains, with embedded images, questions, and reference answers. See the dataset card for sample images, domain counts, and loading instructions.

Downloads last month: 25

Safetensors

Model size

9B params

Tensor type

BF16