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)# pip install -U transformers accelerate # 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
Download model/training_metrics.json from radgraphIT/Radgraph-IT: direct link, hf CLI and curl.
- Browser
- Download file 1.12 kB
-
https://huggingface.co/radgraphIT/Radgraph-IT/resolve/main/model/training_metrics.json
- Command line
-
hf download hf://radgraphIT/Radgraph-IT/model/training_metrics.json
-
curl -L -o training_metrics.json https://huggingface.co/radgraphIT/Radgraph-IT/resolve/main/model/training_metrics.json
1.12 kB
| { | |
| "description": "Diagnostic metrics measured on the full training set at the final epoch; these are not held-out evaluation results.", | |
| "epochs_completed": 13, | |
| "final_epoch_index": 12, | |
| "training_loss": 37.17397039800772, | |
| "training_ner": { | |
| "precision": 0.9417513858489988, | |
| "recall": 0.9489333635632871, | |
| "micro_f1": 0.9453287339328981, | |
| "macro_f1": 0.6892368337795368, | |
| "per_class_f1": { | |
| "Anatomy::definitely present": 0.9673097061532445, | |
| "Observation::definitely present": 0.9281885564742222, | |
| "Observation::definitely absent": 0.9447680909367706, | |
| "Observation::uncertain": 0.8428728514381619, | |
| "Anatomy::definitely absent": 0.4424778761061947, | |
| "Anatomy::uncertain": 0.00980392156862745 | |
| } | |
| }, | |
| "training_relations": { | |
| "precision": 0.9079743979570305, | |
| "recall": 0.8990052123231533, | |
| "micro_f1": 0.9034675452622059, | |
| "macro_f1": 0.8948061133959642, | |
| "per_class_f1": { | |
| "modify": 0.9055610089198072, | |
| "located_at": 0.9025979301044696, | |
| "suggestive_of": 0.8762594011636158 | |
| } | |
| }, | |
| "training_joint_f1": 0.924398139597552 | |
| } | |