eLoRA: Efficient Low-Rank Allocation for Budget-Constrained Fine-Tuning 🧮💰⚙️🎛️
Installation
To install the package, use pip:
pip install eloraUsage
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 developmentGitHub repository: https://github.com/mohsenhariri/eLoRA
1 maintainer
Metadata
1 maintainer
Release files for elora 0.0.9
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| elora-0.0.9.tar.gz | 159.1 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| elora-0.0.9-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 312.1 kB
Release files / elora-0.0.9.tar.gz
| Download URL | elora-0.0.9.tar.gz |
|---|---|
| Size | 159.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
5c53b1eeb19125f865aae58ac4e39685c203adc5fc1f8899fccd8988bbdca252
|
|
BLAKE2b-256 checksum How to use checksums |
6af20242500373a00bc253de44c850b664b082b5084fea4455196d1b338384d1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
Release files / elora-0.0.9-py3-none-any.whl
| Download URL | elora-0.0.9-py3-none-any.whl |
|---|---|
| Size | 152.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
c510677f248c07c666de3ace068dba671fd68cd547b13378d52cde80bf5c97a2
|
|
BLAKE2b-256 checksum How to use checksums |
5f55f34df5226ecc54f134752e642d3b5050059b5944514cffba2b382b4f0042
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
