Feature Extraction
Transformers
Safetensors
English
roberta
biomedical
clinical
cardiology
entity-linking
concept-normalization
umls
metric-learning
text-embeddings-inference
Instructions to use DT4H/CardioBERTa.en_GP_only_snomed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DT4H/CardioBERTa.en_GP_only_snomed with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="DT4H/CardioBERTa.en_GP_only_snomed")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("DT4H/CardioBERTa.en_GP_only_snomed") model = AutoModel.from_pretrained("DT4H/CardioBERTa.en_GP_only_snomed", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "triplets": 3760671, | |
| "malformed_rows": 0, | |
| "unique_triplets": 3760637, | |
| "duplicate_triplets": 34, | |
| "unique_cuis": 477292, | |
| "unique_anchors": 385676, | |
| "unique_positives": 406841, | |
| "unique_terms": 470264, | |
| "unique_anchor_positive_pairs": 3740672, | |
| "ambiguous_terms_across_cuis": 162282, | |
| "self_pairs_exact": 0, | |
| "self_pairs_normalized": 4, | |
| "cuis_with_multiple_terms": 477292, | |
| "terms_per_cui_mean": 8.879103358112015, | |
| "terms_per_cui_median": 6.0, | |
| "terms_per_cui_p95": 26.0, | |
| "terms_per_cui_max": 36, | |
| "triplets_per_cui_mean": 7.879182973944671, | |
| "triplets_per_cui_median": 5.0, | |
| "triplets_per_cui_p95": 25.0, | |
| "triplets_per_cui_max": 35, | |
| "anchor_words_mean": 4.134149730194426, | |
| "positive_words_mean": 4.347405556082943 | |
| } | |