Skip to content

Implementation for ACL 2024 paper "Meta-Task Prompting Elicits Embeddings from Large Language Models"

Notifications You must be signed in to change notification settings

Yibin-Lei/MetaEOL

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 

Repository files navigation

Code Implementation for MetaEOL

Python Env

conda create -n metaeol_39 python=3.9
conda activate metaeol_39

pip install -r requirements.txt

Download data

cd SentEval/data/downstream/
bash download_dataset.sh
cd -

Running Script

python evaluation.py --model_name_or_path "mistralai/Mistral-7B-v0.1" --mode test --task_set sts --prompt_method prompteol

The argument task_set can also be set to transfer. Similarly, the argument prompt_method can also be set to metaeol.

Acknowledgement

Our code is developed upon PromptEOL. We thank the authors of PromptEOL for their great efforts.

About

Implementation for ACL 2024 paper "Meta-Task Prompting Elicits Embeddings from Large Language Models"

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published