Sentence Similarity
sentence-transformers
Safetensors
Transformers
English
bert
feature-extraction
text-embeddings-inference
Instructions to use NeuML/pubmedbert-base-embeddings-matryoshka with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use NeuML/pubmedbert-base-embeddings-matryoshka with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("NeuML/pubmedbert-base-embeddings-matryoshka") 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 NeuML/pubmedbert-base-embeddings-matryoshka with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("NeuML/pubmedbert-base-embeddings-matryoshka") model = AutoModel.from_pretrained("NeuML/pubmedbert-base-embeddings-matryoshka", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Download similarity_evaluation_results.csv from NeuML/pubmedbert-base-embeddings-matryoshka: direct link, hf CLI and curl.
- Browser
- Download file 302 Bytes
-
https://huggingface.co/NeuML/pubmedbert-base-embeddings-matryoshka/resolve/main/similarity_evaluation_results.csv
- Command line
-
hf download hf://NeuML/pubmedbert-base-embeddings-matryoshka/similarity_evaluation_results.csv
-
curl -L -o similarity_evaluation_results.csv https://huggingface.co/NeuML/pubmedbert-base-embeddings-matryoshka/resolve/main/similarity_evaluation_results.csv
302 Bytes
| epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman | |
| -1,-1,0.9611268628744398,0.8651325788568655,0.9412334131276019,0.8650209269988058,0.9408144524772969,0.8651457143657781,0.9561560772829465,0.8651094963898324 | |