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

model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
    "Teklia/DAI-cards-nested",
    torch_dtype=torch.bfloat16,
    attn_implementation="flash_attention_2",
    device_map="auto",
)

processor = AutoProcessor.from_pretrained("Teklia/DAI-cards-nested")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "12e74aa3-4d7d-47b4-b46b-7013b9a1f251.jpg",
            },
            {"type": "text", "text": "Extrait les informations en XML."},
        ],
    }
]

# Preparation for inference
text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to("cuda")

# Inference: Generation of the output
generated_ids = model.generate(**inputs, max_new_tokens=1024)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text[0])

Output

xml

<root>
	<Décès>
		<Défunt>
			<Nom>Choisnard</Nom>
			<Prénom>Marie Madelaine</Prénom>
			<Sexe>F</Sexe>
			<DateDeNaissance>23 juillet 1753</DateDeNaissance>
			<LieuDeNaissance>Ambroise (Indre-et-Loire)</LieuDeNaissance>
			<Profession>journalière</Profession>
			<Statut>veuf(ve)</Statut>
		</Défunt>
		<Conjoint>
			<Nom>Rocheriou</Nom>
			<Prénom>Pierre</Prénom>
			<Statut>décédé(e)</Statut>
		</Conjoint>
		<Père>
			<Nom>Choisnard</Nom>
			<Prénom>Michel</Prénom>
		</Père>
		<Mère>
			<Nom>Dubeuf</Nom>
			<Prénom>Louise</Prénom>
		</Mère>
	</Décès>
	<Date>
		<Année>1826</Année>
		<Mois>septembre</Mois>
		<Jour>5</Jour>
	</Date>
</root>

Citation

To cite the original QWEN2.5-VL model:

@misc{qwen2.5-VL,
    title = {Qwen2.5-VL},
    url = {https://qwenlm.github.io/blog/qwen2.5-vl/},
    author = {Qwen Team},
    month = {January},
    year = {2025}
}

Teklia/Qwen2.5-VL-7B-DAI-CReTDHI-IndexCardsNested-KIE

Qwen2.5-VL-7B-Instruct Index Cards Nested

Introduction

Training

Evaluation

Usage

Citation

Teklia/
Qwen2.5-VL-7B-DAI-CReTDHI-IndexCardsNested-KIE