Skip to main content

A small wrapper for generating Longformer embeddings.

Project description

Longformer Embedder

A lightweight wrapper around Hugging Face Longformer to easily generate mean-pooled embeddings.

Installation

pip install longformer-embedder

Usage

from longformer_embedder import LongformerEmbedder

embedder = LongformerEmbedder(model_name="allenai/longformer-base-4096")
vec = embedder.get_embedding("This is a test sentence.")
print(vec.shape)  # (768,)

Batch Mode

texts = ["Text one", "Text two", "Text three"]
embeddings = embedder.generate_embeddings(texts)
print(embeddings.shape)  # (3, 768)

Notes

  • Model weights are downloaded from Hugging Face automatically.
  • Ensure torch is installed and compatible with your device (CPU/GPU).
  • For GPU acceleration, install CUDA-enabled PyTorch.

📜 License

MIT License

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

longformer_embedder-0.1.0.tar.gz (3.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

longformer_embedder-0.1.0-py3-none-any.whl (4.0 kB view details)

Uploaded Python 3

File details

Details for the file longformer_embedder-0.1.0.tar.gz.

File metadata

  • Download URL: longformer_embedder-0.1.0.tar.gz
  • Upload date:
  • Size: 3.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.5

File hashes

Hashes for longformer_embedder-0.1.0.tar.gz
Algorithm Hash digest
SHA256 39fa0dc2b4eb221e63b2f9c16cfcc4ab98dece17202e97f9bbd3f2b7e67f3786
MD5 114a0a71bdefd4d6e6b75fdd6fa3d67f
BLAKE2b-256 7b5bcb70d993ff4b5f1844ba5c2c61e2e9bdf1ba54e2110463d1fdd4800ff16f

See more details on using hashes here.

File details

Details for the file longformer_embedder-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for longformer_embedder-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 ff0c557d47cbbf81c6d99ce8fcb31c281146e1738bd0b0656de00e6c9671476e
MD5 24c9e0c712a91c03d5b43aee2546bab0
BLAKE2b-256 e343a6fb5bd07afaa63ad01d501a408a9b6838e4bdc30b19f96943200ca0d34b

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page