Feature Extraction
Model2Vec
Safetensors
sentence-transformers
embeddings
static-embeddings
sentence-similarity
Instructions to use minishlab/blink-multilingual-64M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Model2Vec
How to use minishlab/blink-multilingual-64M with Model2Vec:
from model2vec import StaticModel model = StaticModel.from_pretrained("minishlab/blink-multilingual-64M") embeddings = model.encode(["It's dangerous to go alone!", "It's a secret to everybody."]) print(embeddings.shape) - sentence-transformers
How to use minishlab/blink-multilingual-64M with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("minishlab/blink-multilingual-64M") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
Commit History
Today
-
Card: MMTEB scores with the Sentence Transformers loader (51.60)
Verified signaturea7198ef
Yesterday
-
No truncation in tokenizer.json, so Sentence Transformers reads full texts like model2vec
Verified signature8291e78 -
Card: final MMTEB scores
Verified signature991c446 -
Chunk long runs at 100 characters; no max_length truncation
Verified signature46afcc6 -
Card: MMTEB without English, HAKARI retrieval
Verified signature24ed377 -
Update README.md
Verified signature81feb5a -
Update README.md
Verified signaturea0e0a77 -
Card: languages, tokenizer, language codes
Verified signature79daeee -
blink-multilingual-64M: model and card
Verified signature2dfcf52 -
initial commit
Verified signatureab727b7