Downloads · 30 days
9
10% of all-time downloads
zorazrw/filco-llama2-open
filco-llama2-open is a text generation model from zorazrw. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as cc-by-sa-4.0.
This is a FilCo context filtering model for open-domain documents such as Wikipedia articles. Specifically, this is a meta-llama/Llama-2-7b trained using LoRA for 3 epochs on the NaturalQuestions (NQ) training set.
Downloads · 30 days
9
10% of all-time downloads
All-time downloads
86
Public
Repo size
27 GB
Likes
0
Public
Click a slice to open those files.
.bin13.5 GB · 100%
From the Hugging Face model README
This is a FilCo context filtering model for open-domain documents such as Wikipedia articles.
Specifically, this is a meta-llama/Llama-2-7b trained using LoRA for 3 epochs on the NaturalQuestions (NQ) training set.
It is intented to be used in FilCo: https://github.com/zorazrw/filco, but can be further applied in similar scenarios.
if you use this model for research, please cite:
@article{wang2023learning,
title={Learning to Filter Context for Retrieval-Augmented Generation},
author={Zhiruo Wang, Jun Araki, Zhengbao Jiang, Md Rizwan Parvez, Graham Neubig},
journal={arXiv preprint arXiv:2311.08377},
year={2023}
}