https://github.com/taylorai/mlx_embedding_models

run embeddings in MLX
https://github.com/taylorai/mlx_embedding_models

Last synced: about 1 month ago
JSON representation

run embeddings in MLX

• Host: GitHub
• URL: https://github.com/taylorai/mlx_embedding_models
• Owner: taylorai
• License: mit
• Created: 2024-02-10T04:43:22.000Z (12 months ago)
• Default Branch: main
• Last Pushed: 2024-08-04T19:07:20.000Z (6 months ago)
• Last Synced: 2024-09-03T00:04:44.798Z (5 months ago)
• Language: Python
• Size: 120 KB
• Stars: 67
• Watchers: 1
• Forks: 6
• Open Issues: 4
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# MLX Embedding Models

Run text embeddings on your Apple Silicon GPU. Supports any BERT- or RoBERTa-based embedding model, with a curated registry of high-performing models that just work off the shelf.

Get started by installing from PyPI:

```

pip install mlx-embedding-models

```

Then get started in a few lines of code:

```python

from mlx_embedding_models.embedding import EmbeddingModel

model = EmbeddingModel.from_registry("bge-small")

texts = [

    "isn't it nice to be inside such a fancy computer",

    "the horse raced past the barn fell"

]

embs = model.encode(texts)

print(embs.shape)

# 2, 384

```