MeDeBERTa / README.md
malakhovks's picture
Merge branch 'main' of https://huggingface.co/malakhovks/MeDeBERTa
c3b475b
metadata
license: apache-2.0
language: en
library_name: transformers
tags:
  - deberta
  - sequence-classification
  - medicine
  - telerehabilitation
  - MeDeBERTa
  - MeDeBERTaBot
metrics:
  - name: accuracy
    type: accuracy
    value: 0.9986
  - name: macro_f1
    type: f1
    value: 0.9987
  - name: balanced_accuracy
    type: balanced_accuracy
    value: 0.9987
  - name: auc_micro
    type: auc
    value: 0.999997
  - name: ap_micro
    type: average_precision
    value: 0.99993
datasets:
  - malakhovks/MeDeBERTa
base_model:
  - microsoft/deberta-v3-xsmall

MeDeBERTa – v2 (July 2025)

Fine-tuned microsoft/deberta-v3-xsmall on 269 874 Q-A pairs (30 intent labels) for the MeDeBERTaBot medicine question-classification task.

Value
Epochs 20 (best @ epoch 17)
Batch / Grad. Accum. 16 / 4 (eff. 64)
Learning rate 5 × 10⁻⁵
Best val. accuracy 0.99855
Test accuracy 0.99859
Macro F1 (test) 0.99867
Balanced accuracy (test) 0.99868
Micro AUC 0.999997
Micro average precision 0.99993
Loss (val / test) 0.01371 / 0.01305
Hardware RTX 2080 Ti (11 GB)
Per-class metrics (excerpt)
Label Precision Recall F1 Support
any_code 1.000 1.000 1.000 980
contexts 0.988 0.987 0.988 923
treatment summary 1.000 0.998 0.999 927

Full table: see classification_report.json / classification_report.csv.

Training

The full fine-tuning pipeline (data prep → training → evaluation scripts) is maintained in the companion GitHub repo
MeDeBERTaBot · deberta_fine_tuning

GitHub stars

Usage

from transformers import AutoTokenizer, AutoModelForSequenceClassification

tok = AutoTokenizer.from_pretrained("malakhovks/MeDeBERTa")
model = AutoModelForSequenceClassification.from_pretrained("malakhovks/MeDeBERTa")

inputs = tok("what are contraindications for TENS?", return_tensors="pt")
pred   = model(**inputs).logits.argmax(-1).item()
print(model.config.id2label[pred])

Changelog

See CHANGELOG.md for full version history.