Instructions to use Thoughtseed/gutenocr-endpoint with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Thoughtseed/gutenocr-endpoint with Transformers:

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

pipe = pipeline("image-text-to-text", model="Thoughtseed/gutenocr-endpoint")
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 AutoModel
model = AutoModel.from_pretrained("Thoughtseed/gutenocr-endpoint", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Thoughtseed/gutenocr-endpoint with vLLM:

Install from pip and serve model

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

SGLang

How to use Thoughtseed/gutenocr-endpoint 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 "Thoughtseed/gutenocr-endpoint" \
    --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": "Thoughtseed/gutenocr-endpoint",
		"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 "Thoughtseed/gutenocr-endpoint" \
        --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": "Thoughtseed/gutenocr-endpoint",
		"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 Thoughtseed/gutenocr-endpoint with Docker Model Runner:
```
docker model run hf.co/Thoughtseed/gutenocr-endpoint
```

gutenocr-endpoint / handler.py

pavun

Refactor EndpointHandler constructor to use model_dir parameter for consistency

ae505d9 8 months ago

Raw History Blame Contribute Delete

1.83 kB

import base64
import io
import torch
from PIL import Image
from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info


class EndpointHandler:

    def __init__(self, model_dir):

        self.model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
            model_dir,
            torch_dtype=torch.bfloat16,
            device_map="auto",
            trust_remote_code=True
        )

        self.processor = AutoProcessor.from_pretrained(
            model_dir,
            trust_remote_code=True
        )

    def __call__(self, data):

        image_b64 = data["inputs"]["image"]
        prompt = data["inputs"]["text"]

        image = Image.open(io.BytesIO(base64.b64decode(image_b64)))

        messages = [
            {
                "role": "user",
                "content": [
                    {"type": "image", "image": image},
                    {"type": "text", "text": prompt},
                ],
            }
        ]

        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"
        ).to(self.model.device)

        outputs = self.model.generate(**inputs, max_new_tokens=512)

        generated_ids_trimmed = [
            out_ids[len(in_ids):]
            for in_ids, out_ids in zip(inputs.input_ids, outputs)
        ]

        decoded = self.processor.batch_decode(
            generated_ids_trimmed,
            skip_special_tokens=True
        )

        return {"result": decoded[0]}

	import base64
	import io
	import torch
	from PIL import Image
	from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor
	from qwen_vl_utils import process_vision_info


	class EndpointHandler:

	def __init__(self, model_dir):

	self.model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
	model_dir,
	torch_dtype=torch.bfloat16,
	device_map="auto",
	trust_remote_code=True
	)

	self.processor = AutoProcessor.from_pretrained(
	model_dir,
	trust_remote_code=True
	)

	def __call__(self, data):

	image_b64 = data["inputs"]["image"]
	prompt = data["inputs"]["text"]

	image = Image.open(io.BytesIO(base64.b64decode(image_b64)))

	messages = [
	{
	"role": "user",
	"content": [
	{"type": "image", "image": image},
	{"type": "text", "text": prompt},
	],
	}
	]

	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"
	).to(self.model.device)

	outputs = self.model.generate(**inputs, max_new_tokens=512)

	generated_ids_trimmed = [
	out_ids[len(in_ids):]
	for in_ids, out_ids in zip(inputs.input_ids, outputs)
	]

	decoded = self.processor.batch_decode(
	generated_ids_trimmed,
	skip_special_tokens=True
	)

	return {"result": decoded[0]}