Instructions to use pcuenq/paddle-test-4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pcuenq/paddle-test-4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="pcuenq/paddle-test-4", trust_remote_code=True)
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("pcuenq/paddle-test-4", trust_remote_code=True)
model = AutoModelForImageTextToText.from_pretrained("pcuenq/paddle-test-4", trust_remote_code=True)
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

vLLM

How to use pcuenq/paddle-test-4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pcuenq/paddle-test-4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pcuenq/paddle-test-4",
		"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/pcuenq/paddle-test-4

SGLang

How to use pcuenq/paddle-test-4 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 "pcuenq/paddle-test-4" \
    --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": "pcuenq/paddle-test-4",
		"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 "pcuenq/paddle-test-4" \
        --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": "pcuenq/paddle-test-4",
		"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 pcuenq/paddle-test-4 with Docker Model Runner:
```
docker model run hf.co/pcuenq/paddle-test-4
```

PaddleOCR-VL-0.9B

Duplicated from https://huggingface.co/PaddlePaddle/PaddleOCR-VL

Example use with transformers:

from transformers import AutoModelForCausalLM, AutoProcessor
import torch

DEVICE="cuda" if torch.cuda.is_available() else "mps" if torch.mps.is_available() else "cpu"
model_id = "pcuenq/PaddleOCR-VL-0.9B"

model = AutoModelForCausalLM.from_pretrained(
    model_id, trust_remote_code=True, dtype=torch.bfloat16
).to(DEVICE).eval()
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

from transformers.image_utils import load_image
image_url = "https://fiverr-res.cloudinary.com/images/t_main1,q_auto,f_auto,q_auto,f_auto/gigs/154456946/original/41556aac80fc43dcb29ce656d786c0a6f9b4073f/do-handwritten-text-image-or-pdf-to-word-means-typing-form.jpg"
image = load_image(image_url)

messages = [{"role": "user", "content": "OCR"}]
text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = processor(text=[text], images=[image], return_tensors="pt").to(DEVICE)

generated = model.generate(**inputs, max_new_tokens=200, do_sample=False)

resp = processor.batch_decode(generated, skip_special_tokens=True)[0]
answer = resp.split(text)[-1].strip()
print(answer)

Downloads last month: 11

Safetensors

Model size

1.0B params

Tensor type

BF16