Downloads · 30 days
237
7% of all-time downloads
mlx-community/bge-small-en-v1.5-4bit
bge-small-en-v1.5-4bit is a feature extraction model from mlx-community. Use it when you need embeddings to search or compare text. It is set up for sentence-transformers. The card lists the license as mit.
The Model mlx-community/bge-small-en-v1.5-4bit was converted to MLX format from BAAI/bge-small-en-v1.5 using mlx-lm version 0.0.3.
Downloads · 30 days
237
7% of all-time downloads
All-time downloads
3.6K
Public
Parameters
33.4M
18.9 MB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors18.9 MB · 95%
How the weights are stored.
U3233.3M · 100%
From the Hugging Face model README
The Model mlx-community/bge-small-en-v1.5-4bit was converted to MLX format from BAAI/bge-small-en-v1.5 using mlx-lm version 0.0.3.
pip install mlx-embeddings
from mlx_embeddings import load, generate
import mlx.core as mx
model, tokenizer = load("mlx-community/bge-small-en-v1.5-4bit")
# For text embeddings
output = generate(model, processor, texts=["I like grapes", "I like fruits"])
embeddings = output.text_embeds # Normalized embeddings
# Compute dot product between normalized embeddings
similarity_matrix = mx.matmul(embeddings, embeddings.T)
print("Similarity matrix between texts:")
print(similarity_matrix)