Create README.md

README.md

@@ -0,0 +1,147 @@
+---
+license: apache-2.0
+language:
+- fr
+pipeline_tag: image-text-to-text
+tags:
+- multimodal
+library_name: transformers
+metrics:
+- cer
+- wer
+- f1
+base_model:
+- Qwen/Qwen2.5-VL-7B-Instruct
+---
+
+# Qwen2.5-VL-7B-Instruct Index Cards Nested
+
+## Introduction
+
+This version of QWEN2.5-VL-7B is specialized for document parsing on French index cards.
+
+## Training
+
+The model is a [QWEN2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct) fine-tuned on French index cards using LoRA.
+
+Parameters:
+- Image width: 800 pixels
+- LoRa rank: 8
+- LoRa alpha: 32
+- Epochs: 10 (about 4k steps) 
+
+Wandb: https://wandb.ai/starride-teklia/DAI-CReTDHI/runs/hk78u308
+
+## Evaluation
+
+| Model                | CER (%) | WER (%) | F1 @ 0 | F1 @ 0.3 | N images | N entities |
+| ---------------------|---------|---------|--------|----------|----------|------------|
+| QWEN2.5-VL-7B Flat   |  10.23  | 18.07   | 83.6   | 91.96    | 55       | 808        |
+| QWEN2.5-VL-7B Nested |  7.87   | 14.90   | 86.3   | 94.36    | 55       | 808        |
+
+### Usage
+
+Here we show a code snippet to show you how to use the model with `transformers` and `qwen_vl_utils`:
+
+* Prediction script
+
+```python
+from transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessor
+from qwen_vl_utils import process_vision_info
+
+model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
+    "starride-teklia/qwen2.5vl-index-cards-nested",
+    torch_dtype=torch.bfloat16,
+    attn_implementation="flash_attention_2",
+    device_map="auto",
+)
+
+processor = AutoProcessor.from_pretrained("starride-teklia/qwen2.5vl-index-cards-nested")
+
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "image",
+                "image": "https://europe.iiif.teklia.com/iiif/2/dai-cretdhi%2FTours%2FAMT-LOTS_EC_NMD%2FEC_LOT_0281%2FFRAC037261_EC_LOT_0281_0097.JPG/full/800,/0/default.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}
+}
+```