Feature Extraction
Transformers
Safetensors
Italian
radgraph_it
radiology
information-extraction
named-entity-recognition
relation-extraction
medical
radgraph
custom_code
Instructions to use radgraphIT/Radgraph-IT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use radgraphIT/Radgraph-IT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="radgraphIT/Radgraph-IT", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("radgraphIT/Radgraph-IT", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "training_ner_perclass/Anatomy::definitely present": 0.9426991571539427, | |
| "training_ner_perclass/Observation::definitely present": 0.8817818462303422, | |
| "training_ner_perclass/Observation::definitely absent": 0.9103946033917495, | |
| "training_ner_perclass/Observation::uncertain": 0.7692726777444838, | |
| "training_ner_perclass/Anatomy::definitely absent": 0.23170731707317074, | |
| "training_ner_perclass/Anatomy::uncertain": 0.0, | |
| "training_ner_macro_f1": 0.6226426002656148, | |
| "training_radgraph-it__ner_precision": 0.9064632963857254, | |
| "training_radgraph-it__ner_recall": 0.9133660284102338, | |
| "training_radgraph-it__ner_f1": 0.9099015711402576, | |
| "training_MEAN__ner_precision": 0.9064632963857254, | |
| "training_MEAN__ner_recall": 0.9133660284102338, | |
| "training_MEAN__ner_f1": 0.9099015711402576, | |
| "training_relation_perclass/modify": 0.8131500323411945, | |
| "training_relation_perclass/located_at": 0.8162794753056518, | |
| "training_relation_perclass/suggestive_of": 0.7143992230952592, | |
| "training_relation_macro_f1": 0.7812762435807018, | |
| "training_radgraph-it__relation_precision": 0.8429081423413853, | |
| "training_radgraph-it__relation_recall": 0.780637087032863, | |
| "training_radgraph-it__relation_f1": 0.8105784119451618, | |
| "training_MEAN__relation_precision": 0.8429081423413853, | |
| "training_MEAN__relation_recall": 0.780637087032863, | |
| "training_MEAN__relation_f1": 0.8105784119451618, | |
| "training_loss": 71.19069803560308, | |
| "validation_ner_perclass/Anatomy::definitely present": 0.8997013116315311, | |
| "validation_ner_perclass/Observation::definitely present": 0.8152192654750272, | |
| "validation_ner_perclass/Observation::definitely absent": 0.8775681341719078, | |
| "validation_ner_perclass/Observation::uncertain": 0.6886446886446886, | |
| "validation_ner_perclass/Anatomy::definitely absent": 0.21052631578947367, | |
| "validation_ner_perclass/Anatomy::uncertain": 0.0, | |
| "validation_ner_macro_f1": 0.5819432859521048, | |
| "validation_radgraph-it__ner_precision": 0.848412096706259, | |
| "validation_radgraph-it__ner_recall": 0.868157917420912, | |
| "validation_radgraph-it__ner_f1": 0.8581714383094751, | |
| "validation_MEAN__ner_precision": 0.848412096706259, | |
| "validation_MEAN__ner_recall": 0.868157917420912, | |
| "validation_MEAN__ner_f1": 0.8581714383094751, | |
| "validation_relation_perclass/modify": 0.6938028414538483, | |
| "validation_relation_perclass/located_at": 0.7035013880182681, | |
| "validation_relation_perclass/suggestive_of": 0.5048543689320388, | |
| "validation_relation_macro_f1": 0.6340528661347183, | |
| "validation_radgraph-it__relation_precision": 0.6998282770463652, | |
| "validation_radgraph-it__relation_recall": 0.6799021243465688, | |
| "validation_radgraph-it__relation_f1": 0.6897213133250593, | |
| "validation_MEAN__relation_precision": 0.6998282770463652, | |
| "validation_MEAN__relation_recall": 0.6799021243465688, | |
| "validation_MEAN__relation_f1": 0.6897213133250593, | |
| "validation_loss": 153.25496798013253, | |
| "best_epoch": 8 | |
| } |