Instructions to use wealthcoders/qwen-vl-2.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wealthcoders/qwen-vl-2.5 with Transformers:

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

pipe = pipeline("image-text-to-text", model="wealthcoders/qwen-vl-2.5")
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("wealthcoders/qwen-vl-2.5")
model = AutoModelForMultimodalLM.from_pretrained("wealthcoders/qwen-vl-2.5", 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 wealthcoders/qwen-vl-2.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wealthcoders/qwen-vl-2.5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wealthcoders/qwen-vl-2.5",
		"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/wealthcoders/qwen-vl-2.5

SGLang

How to use wealthcoders/qwen-vl-2.5 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 "wealthcoders/qwen-vl-2.5" \
    --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": "wealthcoders/qwen-vl-2.5",
		"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 "wealthcoders/qwen-vl-2.5" \
        --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": "wealthcoders/qwen-vl-2.5",
		"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 wealthcoders/qwen-vl-2.5 with Docker Model Runner:
```
docker model run hf.co/wealthcoders/qwen-vl-2.5
```

qwen-vl-2.5 / handler.py

wealthcoders

Create handler.py

53772d5 verified 12 months ago

Raw

History Blame Contribute Delete

1.61 kB

	from transformers import GenerationConfig, AutoProcessor, AutoTokenizer, AutoModelForImageTextToText, Qwen2_5_VLForConditionalGeneration
	from qwen_vl_utils import process_vision_info

	model_name = "Qwen/Qwen2.5-VL-7B-Instruct"
	#If it is an any form of ID - return only list of keys and values.

	class EndpointHandler:
	def __init__(self):
	self.model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
	model_name, torch_dtype="auto", device_map="cuda"
	)
	self.processor = AutoProcessor.from_pretrained(model_name)

	async def __call__(self, data):

	messages = data.get("messages")

	gen_cfg = GenerationConfig(
	max_new_tokens=2048,
	no_repeat_ngram_size=3,
	repeat_penalty=1.2,
	early_stopping=True,
	)

	text = self.processor.apply_chat_template(
	messages, tokenize=False, add_generation_prompt=True
	)
	image_inputs, video_inputs = process_vision_info(messages)
	inputs = self.processor(
	text=[text],
	images=image_inputs,
	videos=video_inputs,
	padding=True,
	return_tensors="pt",
	)

	generated_ids = self.model.generate(**inputs, generation_config=gen_cfg)
	generated_ids_trimmed = [
	out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
	]
	output_text = self.processor.batch_decode(
	generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
	)

	return output_text[0]