Feature Extraction
sentence-transformers
Safetensors
bert
colbert
late-interaction
multi-vector
information-retrieval
african-languages
multilingual
Generated from Trainer
dataset_size:112864
loss:CachedMultiVectorMultipleNegativesRankingLoss
text-embeddings-inference
Instructions to use nebhailema/afrixir-multivector-e5-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use nebhailema/afrixir-multivector-e5-small with sentence-transformers:
from sentence_transformers import MultiVectorEncoder model = MultiVectorEncoder("nebhailema/afrixir-multivector-e5-small") queries = ["Which planet is known as the Red Planet?"] documents = [ "Venus is often called Earth's twin because of its similar size and proximity.", "Mars, known for its reddish appearance, is often referred to as the Red Planet.", "Jupiter, the largest planet in our solar system, has a prominent red spot.", ] query_embeddings = model.encode_query(queries) document_embeddings = model.encode_document(documents) similarities = model.similarity(query_embeddings, document_embeddings) print(similarities) - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from nebhailema/afrixir-multivector-e5-small: direct link, hf CLI and curl.
- Browser
- Download file 17.1 MB
-
https://huggingface.co/nebhailema/afrixir-multivector-e5-small/resolve/main/tokenizer.json
- Command line
-
hf download hf://nebhailema/afrixir-multivector-e5-small/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/nebhailema/afrixir-multivector-e5-small/resolve/main/tokenizer.json
17.1 MB
- Xet hash:
- 952174f03b93ed9e19ea539a90be89b05116b6d8fb83abaaaa47f61528df688d
- Size of remote file:
- 17.1 MB
- SHA256:
- fbcc3c7348739d765de2c86fce14c9c5e2dd47696dbb3cfeed294edfc712d8f0
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.