TAAFT
Free mode
100% free
Freemium
Free Trial
Deals

VectifyAI / Model-Augmented-Fine-Tuning

Fine-tuning black-box OpenAI embedding models

22 8 Language: Jupyter Notebook License: MIT Updated: 1mo ago

README

Enhancing Black-Box Embeddings with Model Augmented Fine-Tuning

A method to fine-tune the black-box OpenAI embedding to improve the retrieval performance ๐Ÿ“ˆ.

๐Ÿ“ See our paper Mafin: Enhancing Black-Box Embeddings with Model Augmented Fine-Tuning for a detailed introduction to this method.

Other training details and dataset construction can be found in LlamaIndex's Blog.

Install ๐Ÿ› ๏ธ

pip install -r requirements.txt

Fine-tune the BAAI/bge-small-en model

cd ./finetune
python train.py

Fine-tune the FAE model

cd ./finetune
python fae_train.py

The comparison of the evaluation results can be found in the jupyter notebook ๐Ÿ“Š.

0 AIs selected
Clear selection
#
Name
Task