Skip to main content

eLoRA: Efficient Low-Rank Allocation for Budget-Constrained Fine-Tuning 🧮💰⚙️🎛️

Project description

eLoRA: Efficient Low-Rank Allocation for Budget-Constrained Fine-Tuning 🧮💰⚙️🎛️

Installation

To install the package, use pip:

pip install elora

Usage

To use the package, import it in your Python code:

import elora


  ranks = elora.rank_pattern(
          model="meta-llama/Llama-3.2-1B",
          base_rank=16,
          # target_modules="all",
          target_modules=["q_proj", "down_proj"],
          # layers="all",
          layers=[2, 3]
      )

Models.

import elora

# Under development

GitHub repository: https://github.com/mohsenhariri/eLoRA

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

elora-0.0.9.tar.gz (159.1 kB view details)

Uploaded Source

Built Distribution

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

elora-0.0.9-py3-none-any.whl (152.9 kB view details)

Uploaded Python 3

File details

Details for the file elora-0.0.9.tar.gz.

File metadata

  • Download URL: elora-0.0.9.tar.gz
  • Upload date:
  • Size: 159.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for elora-0.0.9.tar.gz
Algorithm Hash digest
SHA256 5c53b1eeb19125f865aae58ac4e39685c203adc5fc1f8899fccd8988bbdca252
MD5 0841791180be23f78f7b64053ddb7145
BLAKE2b-256 6af20242500373a00bc253de44c850b664b082b5084fea4455196d1b338384d1

See more details on using hashes here.

File details

Details for the file elora-0.0.9-py3-none-any.whl.

File metadata

  • Download URL: elora-0.0.9-py3-none-any.whl
  • Upload date:
  • Size: 152.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for elora-0.0.9-py3-none-any.whl
Algorithm Hash digest
SHA256 c510677f248c07c666de3ace068dba671fd68cd547b13378d52cde80bf5c97a2
MD5 0b2b916c1389ab6588a95024269fee77
BLAKE2b-256 5f55f34df5226ecc54f134752e642d3b5050059b5944514cffba2b382b4f0042

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