GOAT-PEFT
[ICML2025] Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment
File Explorer
Download Latest Version (.zip)- AddSub.json
- addsub_1.json
- test.json
- AQuA.json
- aqua_1.json
- test.json
- test.json
- train.json
- test.json
- train.json
- test.json
- train.json
- gsm8k.json
- gsm8k_1.json
- test.json
- test.json
- train.json
- test.json
- data_process.py
- test.json
- testset.json
- trainset.json
- validset.json
- MultiArith.json
- multiarith_1.json
- test.json
- test.json
- train.json
- test.json
- train.json
- SingleEq.json
- singleeq_1.json
- test.json
- test.json
- train.json
- SVAMP.json
- svamp_1.json
- test.json
- test.json
- train.json
- download_dataset.sh
- process_dtd.py
- process_euro.py
- process_sun.py
- .DS_Store
- commonsense_170k.json
- deepspeed_zero2.json
- __init__.py
- config.py
- layer.py
- model.py
- peft_types.py
- save_and_load.py
- test_utils.py
- __init__.py
- config.py
- mapping.py
- peft_model.py
- trainer.py
- __init__.py
- cars.py
- cifar10.py
- cifar100.py
- common.py
- country211.py
- dtd.py
- emnist.py
- eurosat.py
- fashionmnist.py
- fer2013.py
- flowers102.py
- food101.py
- gtsrb.py
- imagenet.py
- kmnist.py
- mnist.py
- oxfordpets.py
- pcam.py
- registry.py
- resisc45.py
- sst2.py
- stl10.py
- sun397.py
- svhn.py
- templates.py
- __init__.py
- data.py
- datasets_preprocess.py
- glue_preprocess.py
- llama_dataset_preprocessing.py
- __init__.py
- rich.py
- __init__.py
- args.py
- timeit.py
- __init__.py
- download_data.py
- eval_nlg.py
- train_nlg.py
- train_nlu.py
- train_vit.py
- main.png
- .gitignore
- chat.sh
- code.sh
- cr.sh
- glue.sh
- LICENSE
- math.sh
- README.md
- requirements.txt
- vit.sh
# Installation Guide
1. Get the code
git clone https://github.com/Facico/GOAT-PEFT
Downloads the entire project code from GitHub to your computer.
cd GOAT-PEFT
Moves into the project folder you just downloaded.
2. Official Install Script
Easy RecommendedPrerequisites
- Python 3 Python is required to use pip.
pip install flash-attn==2.7.3
Installs the package published on PyPI directly β no need to clone the source.
pip install human_eval
Installs the package published on PyPI directly β no need to clone the source.
After installing, open a new terminal and run the program's version command (e.g. --version) to confirm it worked.
Pulled directly from this repo's README.
3. Python
EasyPrerequisites
pip install -r requirements.txt
Installs the Python libraries listed in requirements.txt (or similar).
pip install flash-attn==2.7.3
Installs the package published on PyPI directly β no need to clone the source.
pip install human_eval
Installs the package published on PyPI directly β no need to clone the source.
If it runs without errors and prints output in the terminal, it worked.
Pulled directly from this repo's README.
// repository documentation
Was this content helpful?
(0 ratings)