Sentence Similarity
sentence-transformers
Safetensors
Transformers
English
bert
feature-extraction
text-embeddings-inference
Instructions to use Tao-AI-Informatics/NA-SapBERT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Tao-AI-Informatics/NA-SapBERT with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Tao-AI-Informatics/NA-SapBERT") sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Transformers
How to use Tao-AI-Informatics/NA-SapBERT with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("Tao-AI-Informatics/NA-SapBERT") model = AutoModel.from_pretrained("Tao-AI-Informatics/NA-SapBERT") - Notebooks
- Google Colab
- Kaggle
Delete run_config.json
Browse files- run_config.json +0 -20
run_config.json
DELETED
|
@@ -1,20 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"concept_parquet": "/dgx1data/aii/tao/m338824/ADRD/code/normalization_agent/cache/snomedEL_with_synonyms_concepts.parquet",
|
| 3 |
-
"eval_parquet": "/dgx1data/aii/tao/m338824/ADRD/code/normalization_agent/data/SNOMED_EL/test.parquet",
|
| 4 |
-
"synthetic_variants_parquet": "/dgx1data/aii/tao/m338824/ADRD/code/normalization_agent/increase_recall/optionA_cache/synthetic_variants.parquet",
|
| 5 |
-
"output_dir": "/dgx1data/aii/tao/m338824/ADRD/code/normalization_agent/increase_recall/optionA_cache/noise_model_output/20260217_105255_pnoisy0.8_ep1_lr1e-05",
|
| 6 |
-
"base_model": "cambridgeltl/SapBERT-from-PubMedBERT-fulltext",
|
| 7 |
-
"abbrev_json": "/dgx1data/aii/tao/m338824/ADRD/code/normalization_agent/increase_recall/clean_abbrev_map.json",
|
| 8 |
-
"abbrev_keep_ambiguous": false,
|
| 9 |
-
"abbrev_max_per_concept": 20,
|
| 10 |
-
"max_syn_train": 10,
|
| 11 |
-
"p_noisy": 0.8,
|
| 12 |
-
"batch_size": 256,
|
| 13 |
-
"epochs": 1,
|
| 14 |
-
"lr": 1e-05,
|
| 15 |
-
"max_seq_len": 64,
|
| 16 |
-
"seed": 13,
|
| 17 |
-
"max_syn_index": 20,
|
| 18 |
-
"top_k_eval": 1000,
|
| 19 |
-
"sample_frac": 1.0
|
| 20 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|