Model Card

Donut fine-tuned for full document structuring (parsing) on pl-insurance-terms-struct dataset.

Trained for 10 epochs with max_seq_len=7168.

  • Field-level f1 score: 0.57
  • TED-based accuracy: 0.67

Note: This model and its tokenizer were not (pre-) trained for Polish.

Downloads last month
39
Safetensors
Model size
205M params
Tensor type
I64
·
F32
·
Inference API
Inference API (serverless) does not yet support transformers models for this pipeline type.

Model tree for byczong/donut-ft-terms-struct

Finetuned
(367)
this model

Dataset used to train byczong/donut-ft-terms-struct