Skip to main content

Dolomite Engine

Project description

IBM Dolomite Engine

This repo contains code for IBM models, extracted from https://github.com/ibm-granite/dolomite-engine; all credit goes to the original authors:

  • mayank31398

Extracted Models

The main motivation for using these models is for padding-free. We perform a bare-bones extraction for code only needed for instructlab purposes. In particular we extracted the following:

Supported Models

  • hf_models/models/gpt_dolomite: This is a padding-free transformer, that can be converted to/from bigcode and llama models.

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

instructlab_dolomite-0.2.0.tar.gz (49.8 kB view details)

Uploaded Source

Built Distribution

instructlab_dolomite-0.2.0-py3-none-any.whl (63.1 kB view details)

Uploaded Python 3

File details

Details for the file instructlab_dolomite-0.2.0.tar.gz.

File metadata

  • Download URL: instructlab_dolomite-0.2.0.tar.gz
  • Upload date:
  • Size: 49.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/5.1.0 CPython/3.12.7

File hashes

Hashes for instructlab_dolomite-0.2.0.tar.gz
Algorithm Hash digest
SHA256 3deef09135210f8e1158d93835e00a632694d7f1baa0d9fba3d5a6bad3a0c23e
MD5 58cc7b55ab85bbae7fd62b23d5f70baf
BLAKE2b-256 b73effe2a9164039b406d4c439f75c7fd053b25a4bcbd53f4b1928c9e1cccd23

See more details on using hashes here.

File details

Details for the file instructlab_dolomite-0.2.0-py3-none-any.whl.

File metadata

File hashes

Hashes for instructlab_dolomite-0.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 8ae76ef699b22b965ddee86c28ba01f16edbfaf4a037ecdfe7701c2d339a7c1c
MD5 896dfee7ec4df8fb91793b4200c8f977
BLAKE2b-256 00f675c618f39f37dc1c8c9c3599d785da79614df77a639cee991cbbecc4c54d

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