This repository contains code to run faster sentence-transformers using tools like quantization, ONNX and pruning.
Project description
Fast Sentence Transformers
This repository contains code to run faster sentence-transformers using tools like quantization and ONNX. Just run your model much faster, while reducing memory a lot of memory. There is not much to it!
Quickstart
from fast_sentence_transformers import FastSentenceTransformer as SentenceTransformer
# use any sentence-transformer
encoder = SentenceTransformer("all-MiniLM-L6-v2", device=-1, quantize=True)
encoder.encode("Hello hello, hey, hello hello")
encoder.encode(["Life is too short to eat bad food!"] * 2)
Benchmark
Indicative benchmark for CPU usage with smallest and largest model on sentence-transformers.
| model | Type | default | ONNX | ONNX+quantized |
|---|---|---|---|---|
| paraphrase-albert-small-v2 | memory | 1x | 1x | 1x |
| speed | 1x | 2x | 5x | |
| paraphrase-multilingual-mpnet-base-v2 | memory | 1x | 1x | 4x |
| speed | 1x | 2x | 5x |
Shout-Out
This package heavily leans on sentence-transformers and txtai.
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file fast-sentence-transformers-0.2.1.tar.gz.
File metadata
- Download URL: fast-sentence-transformers-0.2.1.tar.gz
- Upload date:
- Size: 7.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.0 CPython/3.9.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | c5641fce84989513b92e3a4e1fccf95931fe49c90f88b244c4e2c8c44067f80f |
|
| MD5 | eeffdc7a52db55737e10e894538a3a0d |
|
| BLAKE2b-256 | 9b6c03758494f9a651631d0831c1df23d0a06f0df59c9ff6739c62f6a00b1284 |
File details
Details for the file fast_sentence_transformers-0.2.1-py3-none-any.whl.
File metadata
- Download URL: fast_sentence_transformers-0.2.1-py3-none-any.whl
- Upload date:
- Size: 8.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.0 CPython/3.9.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 3568f4e3c16f5e4b5ddc496bf222d647eeea87b80c7f02c24236bf9b04380019 |
|
| MD5 | fb19a7dfa47bdcaeb9e6fcb362584d35 |
|
| BLAKE2b-256 | f83251c51dd1cd8044af9091eba5f8493f24a10ff2f53023ef896d11b509e8bb |
