Instructions to use Remidesbois/surya-bubble-ocr-poneglyph with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Remidesbois/surya-bubble-ocr-poneglyph with Transformers:

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

pipe = pipeline("image-text-to-text", model="Remidesbois/surya-bubble-ocr-poneglyph")
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("Remidesbois/surya-bubble-ocr-poneglyph")
model = AutoModelForMultimodalLM.from_pretrained("Remidesbois/surya-bubble-ocr-poneglyph", 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 Remidesbois/surya-bubble-ocr-poneglyph with vLLM:

Install from pip and serve model

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

SGLang

How to use Remidesbois/surya-bubble-ocr-poneglyph 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 "Remidesbois/surya-bubble-ocr-poneglyph" \
    --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": "Remidesbois/surya-bubble-ocr-poneglyph",
		"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 "Remidesbois/surya-bubble-ocr-poneglyph" \
        --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": "Remidesbois/surya-bubble-ocr-poneglyph",
		"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 Remidesbois/surya-bubble-ocr-poneglyph with Docker Model Runner:
```
docker model run hf.co/Remidesbois/surya-bubble-ocr-poneglyph
```

Surya OCR — Poneglyph, crops de bulles

Fine-tuning local sur RTX 5090. Entrée : un crop RGB de bulle ; sortie : sa transcription française. Prompt : Transcris exactement le texte visible dans cette bulle. Ne rajoute rien.

Meilleur checkpoint sélectionné uniquement sur le CER de validation : checkpoint-705.

Test réservé

Métrique	Valeur
Bulles	1612
CER	0.471 %
WER	1.843 %
Exact match	91.32 %
Distance de Levenshtein moyenne	0.1520
Sorties vides	0.00 %
Générations à la limite de tokens	0

Split strict par page. Les crops et les prédictions individuelles restent privés. Les métriques utilisent une normalisation des espaces et retirent une paire de guillemets extérieurs. Les scores ci-dessus concernent les poids BF16 évalués en Python. Pas de comparaison avec un autre modèle.

Chargement

Poids BF16 au format Transformers standard (transformers==5.14.1). Charger AutoProcessor et AutoModelForImageTextToText depuis ce dossier. Les patches Liger d'entraînement ne sont pas nécessaires au rechargement. generation_config.json contient les identifiants EOS/PAD et le budget de génération.

Empreinte SHA-256 des poids : 67fa1733d2541d6305cffef1e5202e47930a5f5393d1901adda52e7daab05629.

ONNX / WebGPU

Une version navigateur validée est disponible dans onnx/. Elle contient un encodeur visuel, un graphe de préremplissage et un décodeur récurrent, en précision mixte FP16/FP32. Voir les instructions et contrôles. Le dépôt Poneglyph propose la page /sandbox/surya et le moteur Surya · WebGPU.

Downloads last month: 61

Safetensors

Model size

0.7B params

Tensor type

BF16

Model tree for Remidesbois/surya-bubble-ocr-poneglyph

Base model

datalab-to/surya-ocr-2

Quantized

(11)

this model