Update README.md

README.md

@@ -1,35 +1,110 @@
 ---
 library_name: transformers
+license: apache-2.0
+base_model: google/pix2struct-docvqa-base
 tags:
 - generated_from_trainer
+- invoice-processing
+- information-extraction
+- czech-language
+- document-ai
+- multimodal-model
+- generative-model
+- synthetic-data
+- hybrid-data
+- real-data
 metrics:
 - f1
 model-index:
-- name: Pix2StructCzechInvoiceV3
+- name: Pix2StructCzechInvoice-V3
   results: []
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
+# Pix2StructCzechInvoice (V3 – Full Pipeline with Real Data Fine-Tuning)
 
-# Pix2StructCzechInvoiceV3
+This model is a fine-tuned version of [google/pix2struct-docvqa-base](https://huggingface.co/google/pix2struct-docvqa-base) for structured information extraction from Czech invoices.
 
-This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1542
-- F1: 0.8404
+- Loss: 0.1542  
+- F1: 0.8404  
+
+---
 
 ## Model description
 
-More information needed
+Pix2StructCzechInvoice (V3) is the final generative model in the experimental pipeline.
+
+Unlike token classification approaches, this model:
+- processes full document images  
+- generates structured outputs as text sequences  
+
+It extracts key invoice fields such as:
+- supplier  
+- customer  
+- invoice number  
+- bank details  
+- totals  
+- dates  
+
+By combining synthetic, hybrid, and real data, this version significantly improves both performance and stability.
+
+---
+
+## Training data
+
+The dataset used in this stage combines:
+
+1. **Synthetic template-based invoices (V0)**  
+2. **Synthetic invoices with randomized layouts (V1)**  
+3. **Hybrid invoices with real layouts and synthetic content (V2)**  
+4. **Real annotated invoices**  
+
+### Real data fine-tuning
+
+The final stage introduces:
+- real invoice images  
+- realistic visual noise and distortions  
+- natural language variability  
+- real formatting inconsistencies  
+
+This allows the model to:
+- better align generated outputs with real-world distributions  
+- improve robustness of sequence generation  
+- reduce hallucinations and formatting errors  
+
+---
+
+## Role in the pipeline
+
+This model corresponds to:
+
+**V3 – Full pipeline (synthetic + hybrid + real data fine-tuning)**
+
+It represents:
+- the final generative model  
+- the best-performing Pix2Struct variant  
+- an end-to-end extraction approach  
+
+---
 
-## Intended uses & limitations
+## Intended uses
 
-More information needed
+- End-to-end invoice information extraction from images  
+- Document VQA and generative document understanding  
+- OCR-free document processing pipelines  
+- Research in generative vs structured extraction approaches  
 
-## Training and evaluation data
+---
+
+## Limitations
 
-More information needed
+- Output format may still be inconsistent  
+- Sensitive to decoding strategy and prompt structure  
+- Less interpretable than token classification models  
+- Requires post-processing for structured outputs  
+- Computationally more expensive  
+
+---
 
 ## Training procedure
 
@@ -46,6 +121,8 @@ The following hyperparameters were used during training:
 - num_epochs: 10
 - mixed_precision_training: Native AMP
 
+---
+
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | F1     |
@@ -61,10 +138,11 @@ The following hyperparameters were used during training:
 | 0.0804        | 9.0   | 207  | 0.1433          | 0.7963 |
 | 0.0664        | 10.0  | 230  | 0.1614          | 0.7991 |
 
+---
 
-### Framework versions
+## Framework versions
 
-- Transformers 5.0.0
-- Pytorch 2.10.0+cu128
-- Datasets 4.0.0
-- Tokenizers 0.22.2
+- Transformers 5.0.0  
+- PyTorch 2.10.0+cu128  
+- Datasets 4.0.0  
+- Tokenizers 0.22.2