Skip to main content

Easy Embedding-Based Zero-Shot Classfication

Project description

zerohero

Example:

from pprint import pprint
from zerohero import make_zero_shot_classifier

categories = ["cat", "dog", "mouse", "human"]
zsc = make_zero_shot_classifier(
    categories=categories,
    model_type="sentence-transformers",
    model_name="paraphrase-albert-small-v2",
)
cat_text = (
    """The cat (Felis catus),
    commonly referred to as the domestic cat or house cat,
    is the only domesticated species in the family Felidae.
    """
    )

result = zsc(cat_text)

pprint(result)

Development Instructions

Install Dependencies: poetry install --with dev
Configure pre-commit hooks: poetry run pre-commit install
Manually run black: poetry run black zerohero/* tests/*
Manually run pylint: poetry run pylint zerohero/* tests/*

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

zerohero-0.1.1.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.

zerohero-0.1.1-py3-none-any.whl (4.7 kB view details)

Uploaded Python 3

File details

Details for the file zerohero-0.1.1.tar.gz.

File metadata

  • Download URL: zerohero-0.1.1.tar.gz
  • Upload date:
  • Size: 3.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.6.1 CPython/3.11.0 Linux/6.2.0-1015-azure

File hashes

Hashes for zerohero-0.1.1.tar.gz
Algorithm Hash digest
SHA256 4f3c67040068fed89628e90dd5a270322adab400a58c6104182cfae3d83f7cac
MD5 91a5efcf81843f16f62711c845ad322c
BLAKE2b-256 9f8937ba1008ee445cdf5c93c85f4e7558bd755642cfe2d5b43fd9eb41513c84

See more details on using hashes here.

File details

Details for the file zerohero-0.1.1-py3-none-any.whl.

File metadata

  • Download URL: zerohero-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 4.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.6.1 CPython/3.11.0 Linux/6.2.0-1015-azure

File hashes

Hashes for zerohero-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 1af03aa89d8919ddf0d5e45895ce56ac06d0959a48f14d496d4a37a88e3f55c8
MD5 6cbaf19364dcf91f0042466307fb1c7f
BLAKE2b-256 9cf7d4d950d244bc030f2e6d0a8eab2dc9536d19842a46f670ddaf1cb009792f

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