AliOsm/simplerepresentations
Easy-to-use text representations extraction library based on the Transformers library.
Supports configurable multi-layer aggregation (summing or concatenating the last N hidden states) and token-level representation extraction alongside sentence embeddings. Built on HuggingFace's Transformers with PyTorch backend, it handles batch processing with optional CUDA acceleration and multi-process feature conversion for efficient large-scale extraction. Compatible with any pretrained Transformer model from the HuggingFace model hub through simple type/name specification.
No commits in the last 6 months. Available on PyPI.
Stars
32
Forks
4
Language
Python
License
Apache-2.0
Category
Last pushed
Oct 21, 2022
Monthly downloads
17
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/AliOsm/simplerepresentations"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
MinishLab/model2vec
Fast State-of-the-Art Static Embeddings
Embedding/Chinese-Word-Vectors
100+ Chinese Word Vectors 上百种预训练中文词向量
tensorflow/hub
A library for transfer learning by reusing parts of TensorFlow models.
AnswerDotAI/ModernBERT
Bringing BERT into modernity via both architecture changes and scaling
Santosh-Gupta/SpeedTorch
Library for faster pinned CPU <-> GPU transfer in Pytorch