Skip to main content

An open toolkit for Emergent Misalignment research

Project description

emlab

An open toolkit for Emergent Misalignment research.

pip install emlab

Features (WIP)

  • Fast local evaluation — DeBERTa-based judge replaces GPT-4o, orders of magnitude faster
  • Unified EM recipes — Betley, Turner & Nanda, Afonin, all in one place
  • Simple APIemlab.evaluate(model) and you're done

Quick Start

import emlab

model = emlab.load("Qwen/Qwen2.5-14B-Instruct")
recipe = emlab.recipe("model-organisms-medical")
em_model = recipe.apply(model)
results = emlab.evaluate(em_model)

License

MIT

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

emlab-0.0.1.tar.gz (4.2 kB view details)

Uploaded Source

Built Distribution

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

emlab-0.0.1-py3-none-any.whl (5.2 kB view details)

Uploaded Python 3

File details

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

File metadata

  • Download URL: emlab-0.0.1.tar.gz
  • Upload date:
  • Size: 4.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.5

File hashes

Hashes for emlab-0.0.1.tar.gz
Algorithm Hash digest
SHA256 056c602c2c31c169a8d03b7f371d4c68d5bd1cf625c695cd6157cac14e65ea31
MD5 8fdefc9fcc8ccb0be87d89a2ed8bfe9a
BLAKE2b-256 87f1c06bd0f15ea58e657dddf5c5b34470a83bcf3a511b6c92070e13fe98302e

See more details on using hashes here.

File details

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

File metadata

  • Download URL: emlab-0.0.1-py3-none-any.whl
  • Upload date:
  • Size: 5.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.5

File hashes

Hashes for emlab-0.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 a80433ac97f505e1c4783a3cda2d0539a7ccba629a92c2d8fb474e0f8f5f384a
MD5 eb9b2b993bba28b9c2368125ccc88ec2
BLAKE2b-256 83ee1fd21d115370e7087e8aba6c179575b699051049816646438b0c73a41d2d

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