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_enriched with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DT4H/CardioBERTa.en_GP_enriched with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="DT4H/CardioBERTa.en_GP_enriched")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("DT4H/CardioBERTa.en_GP_enriched") model = AutoModel.from_pretrained("DT4H/CardioBERTa.en_GP_enriched", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download training_data_stats.json from DT4H/CardioBERTa.en_GP_enriched: direct link, hf CLI and curl.
- Browser
- Download file 965 Bytes
-
https://huggingface.co/DT4H/CardioBERTa.en_GP_enriched/resolve/main/training_data_stats.json
- Command line
-
hf download hf://DT4H/CardioBERTa.en_GP_enriched/training_data_stats.json
-
curl -L -o training_data_stats.json https://huggingface.co/DT4H/CardioBERTa.en_GP_enriched/resolve/main/training_data_stats.json
965 Bytes
| { | |
| "triplets": 4952020, | |
| "malformed_rows": 0, | |
| "unique_triplets": 4951542, | |
| "duplicate_triplets": 478, | |
| "unique_cuis": 477293, | |
| "unique_anchors": 467097, | |
| "unique_positives": 485607, | |
| "unique_terms": 550651, | |
| "unique_anchor_positive_pairs": 4915749, | |
| "ambiguous_terms_across_cuis": 199127, | |
| "self_pairs_exact": 0, | |
| "self_pairs_normalized": 40, | |
| "cuis_with_multiple_terms": 477293, | |
| "terms_per_cui_mean": 10.059801840798, | |
| "terms_per_cui_median": 7, | |
| "terms_per_cui_p95": 28.0, | |
| "terms_per_cui_max": 37, | |
| "triplets_per_cui_mean": 10.375220252549273, | |
| "triplets_per_cui_median": 7, | |
| "triplets_per_cui_p95": 33.0, | |
| "triplets_per_cui_max": 35, | |
| "anchor_words_mean": 4.16947488095767, | |
| "positive_words_mean": 4.407634056405265, | |
| "cuis_common_with_synonyms": 83914, | |
| "cuis_added_vs_synonyms": 393379, | |
| "cuis_missing_vs_synonyms": 0, | |
| "terms_common_with_synonyms": 165661, | |
| "terms_added_vs_synonyms": 384990, | |
| "terms_missing_vs_synonyms": 0 | |
| } | |