Feature Extraction
Transformers
Safetensors
Italian
bert
biomedical
clinical
cardiology
entity-linking
concept-normalization
umls
metric-learning
text-embeddings-inference
Instructions to use DT4H/CardioBERTa.it_GP_enriched with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DT4H/CardioBERTa.it_GP_enriched with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="DT4H/CardioBERTa.it_GP_enriched")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("DT4H/CardioBERTa.it_GP_enriched") model = AutoModel.from_pretrained("DT4H/CardioBERTa.it_GP_enriched", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "triplets": 4714271, | |
| "malformed_rows": 0, | |
| "unique_triplets": 4712493, | |
| "duplicate_triplets": 1778, | |
| "unique_cuis": 476970, | |
| "unique_anchors": 450416, | |
| "unique_positives": 461831, | |
| "unique_terms": 529487, | |
| "unique_anchor_positive_pairs": 4654414, | |
| "ambiguous_terms_across_cuis": 193240, | |
| "self_pairs_exact": 0, | |
| "self_pairs_normalized": 188, | |
| "cuis_with_multiple_terms": 476969, | |
| "terms_per_cui_mean": 9.828039499339582, | |
| "terms_per_cui_median": 7.0, | |
| "terms_per_cui_p95": 27.0, | |
| "terms_per_cui_max": 36, | |
| "triplets_per_cui_mean": 9.883789336855568, | |
| "triplets_per_cui_median": 7.0, | |
| "triplets_per_cui_p95": 31.0, | |
| "triplets_per_cui_max": 35, | |
| "anchor_words_mean": 4.484596451922259, | |
| "positive_words_mean": 4.685869564986824, | |
| "cuis_common_with_synonyms": 69631, | |
| "cuis_added_vs_synonyms": 407339, | |
| "cuis_missing_vs_synonyms": 0, | |
| "terms_common_with_synonyms": 136720, | |
| "terms_added_vs_synonyms": 392767, | |
| "terms_missing_vs_synonyms": 0 | |
| } | |