qxakshat
/

all-MiniLM-L6-v2-64dim

Sentence Similarity

sentence-transformers

feature-extraction

text-embeddings-inference

Model card Files Files and versions

all-MiniLM-L6-v2

This is a sentence-transformers model: It maps sentences & paragraphs to a 64 dimensional dense vector space and can be used for tasks like clustering or semantic search.

Model performance (Cosine-Similarity based, on the sts-test dataset):

Original (384 dimensions): Pearson: 0.8274 Spearman: 0.8203
128 dimensions: Pearson: 0.8165 Spearman: 0.8180
64 dimensions: Pearson: 0.7855 Spearman: 0.7973
32 dimensions: Pearson: 0.7256 Spearman: 0.7481

created using: dimensionality_reduction

Downloads last month: 1

Safetensors

Model size

22.7M params

Tensor type

F32

·

Datasets used to train qxakshat/all-MiniLM-L6-v2-64dim