Skip to main content

A toolkit for identifying pretrained language models from AI-generated text

Project description

LM Identifier

With a surge of generative pretrained language models, it is becoming increasingly important to distinguish between human and AI-generated text. Inspired by GPTZero, an app that seeks to detect AI-generated text, LM Identifier pokes at this question even further by providing a growing suite of tools to help identify which (publicly available) language model might have been used to generate some given chunck of text.

Installation

LM Identifier is available on PyPI.

$ pip install lm-identifier

To develop locally, first install pre-commit:

$ pip install --upgrade pip wheel
$ pip install pre-commit
$ pre-commit install

Install the package in editable mode.

pip install -e .

Usages

WIP

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

lm_identifier-0.0.1.tar.gz (3.2 kB view details)

Uploaded Source

Built Distribution

lm_identifier-0.0.1-py3-none-any.whl (3.6 kB view details)

Uploaded Python 3

File details

Details for the file lm_identifier-0.0.1.tar.gz.

File metadata

  • Download URL: lm_identifier-0.0.1.tar.gz
  • Upload date:
  • Size: 3.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.3.1 CPython/3.8.16 Darwin/21.6.0

File hashes

Hashes for lm_identifier-0.0.1.tar.gz
Algorithm Hash digest
SHA256 e35b16b36974b308b198f233f856af742ef04dc7c623f8eb150b867b60ad7326
MD5 bcd706c8b1cd7e6716eadbf4dab7fa26
BLAKE2b-256 d5da7d0fbef7422e07704bde586c60e549e4fc7fcfd8c266747d360371ce1a44

See more details on using hashes here.

File details

Details for the file lm_identifier-0.0.1-py3-none-any.whl.

File metadata

  • Download URL: lm_identifier-0.0.1-py3-none-any.whl
  • Upload date:
  • Size: 3.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.3.1 CPython/3.8.16 Darwin/21.6.0

File hashes

Hashes for lm_identifier-0.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 a0739255ed4aa0246419eba696324ba3d0515d67cc3427d4310c9a14c04f4ed9
MD5 27b75bc0d1d79991d6d4e99ec2ca6132
BLAKE2b-256 0a982c008320ca388ce3ae962229f6e6d5e087577970af1114aacbd1b44fd8fb

See more details on using hashes here.

Supported by

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