Instructions to use rcds/MiniLM-swiss_citation_extraction-de-fr-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use rcds/MiniLM-swiss_citation_extraction-de-fr-it with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="rcds/MiniLM-swiss_citation_extraction-de-fr-it")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("rcds/MiniLM-swiss_citation_extraction-de-fr-it") model = AutoModelForTokenClassification.from_pretrained("rcds/MiniLM-swiss_citation_extraction-de-fr-it", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 23.0, | |
| "train_CITATION_f1": 0.9814787122684838, | |
| "train_CITATION_precision": 0.9844650624611626, | |
| "train_CITATION_recall": 0.978510425318936, | |
| "train_LAW_f1": 0.9211885809936669, | |
| "train_LAW_precision": 0.8550646934923544, | |
| "train_LAW_recall": 0.9983966169255928, | |
| "train_accuracy_normalized": 0.9905667906095162, | |
| "train_loss": 0.026775669306516647, | |
| "train_macro-f1": 0.9515974221562933, | |
| "train_macro-precision": 0.9884535211222644, | |
| "train_macro-recall": 0.9202279237061262, | |
| "train_micro-f1": 0.9429566347321088, | |
| "train_micro-precision": 0.9909403074465961, | |
| "train_micro-recall": 0.8994053033460294, | |
| "train_runtime": 1297.076, | |
| "train_samples": 90101, | |
| "train_samples_per_second": 69.465, | |
| "train_steps_per_second": 0.543, | |
| "train_weighted-f1": 0.9419101385291693, | |
| "train_weighted-precision": 0.9916707876514618, | |
| "train_weighted-recall": 0.8994053033460294 | |
| } |