Skip to main content

Reusable layer-wise representation alignment analysis for multimodal models.

Project description

English | 中文

repralign

PyPI version Python License

repralign is a reusable Python toolkit for layer-wise representation alignment analysis in multimodal models.

Documentation:

Installation

Install from PyPI:

pip install repralign

Install with Hugging Face vision support:

pip install "repralign[huggingface]"

Install with generation-reference support:

pip install "repralign[generation]"

Install from source for local development:

python -m venv .venv
source .venv/bin/activate
pip install -e .[dev]

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

repralign-0.1.1.tar.gz (18.9 kB view details)

Uploaded Source

Built Distribution

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

repralign-0.1.1-py3-none-any.whl (21.6 kB view details)

Uploaded Python 3

File details

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

File metadata

  • Download URL: repralign-0.1.1.tar.gz
  • Upload date:
  • Size: 18.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for repralign-0.1.1.tar.gz
Algorithm Hash digest
SHA256 be4966f7cbcef3feeae9986d1c71189616d6800a2a0bbf84f2601b6b3dee9280
MD5 7ae4a725eb84b5829d871010655de197
BLAKE2b-256 e4f854f9289f2afbab66987447787a5e278f58dba25ad76c8257cd5687697302

See more details on using hashes here.

Provenance

The following attestation bundles were made for repralign-0.1.1.tar.gz:

Publisher: publish.yml on Jnmz/repralign

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

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

File metadata

  • Download URL: repralign-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 21.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for repralign-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 c72e743d67324ff6aea64011aa1009f14726f7369453f0ed50fc779434763d5a
MD5 233e3af89a64bb5399901cc43d3a0806
BLAKE2b-256 d86d2f207236ac4ca25f3393ab8b5a00b759c5854f81a61302d8a0fd464aba18

See more details on using hashes here.

Provenance

The following attestation bundles were made for repralign-0.1.1-py3-none-any.whl:

Publisher: publish.yml on Jnmz/repralign

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

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