Feature Extraction
Transformers
Safetensors
Spanish
roberta
biomedical
clinical
cardiology
entity-linking
concept-normalization
umls
metric-learning
text-embeddings-inference
Instructions to use DT4H/CardioBERTa.es_P_translations_only with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DT4H/CardioBERTa.es_P_translations_only with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="DT4H/CardioBERTa.es_P_translations_only")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("DT4H/CardioBERTa.es_P_translations_only") model = AutoModel.from_pretrained("DT4H/CardioBERTa.es_P_translations_only", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "triplets": 1593029, | |
| "malformed_rows": 0, | |
| "unique_triplets": 1592694, | |
| "duplicate_triplets": 335, | |
| "unique_cuis": 476344, | |
| "unique_anchors": 376578, | |
| "unique_positives": 418463, | |
| "unique_terms": 529722, | |
| "unique_anchor_positive_pairs": 1576723, | |
| "ambiguous_terms_across_cuis": 193752, | |
| "self_pairs_exact": 0, | |
| "self_pairs_normalized": 66, | |
| "cuis_with_multiple_terms": 476343, | |
| "terms_per_cui_mean": 3.9241199637236956, | |
| "terms_per_cui_median": 3.0, | |
| "terms_per_cui_p95": 9.0, | |
| "terms_per_cui_max": 36, | |
| "triplets_per_cui_mean": 3.34428270325647, | |
| "triplets_per_cui_median": 2.0, | |
| "triplets_per_cui_p95": 9.0, | |
| "triplets_per_cui_max": 35, | |
| "anchor_words_mean": 5.231707646251261, | |
| "positive_words_mean": 5.421652085429707, | |
| "cuis_common_with_synonyms": 69277, | |
| "cuis_added_vs_synonyms": 407067, | |
| "cuis_missing_vs_synonyms": 0, | |
| "terms_common_with_synonyms": 136233, | |
| "terms_added_vs_synonyms": 393489, | |
| "terms_missing_vs_synonyms": 0 | |
| } | |