g8a9/ferret
A python package for benchmarking interpretability techniques on Transformers.
This project helps machine learning engineers and researchers understand why their Transformer-based text models make specific decisions. You input your text model and some example text, and it outputs explanations showing which words were most important, along with benchmark scores evaluating how trustworthy those explanations are. This allows you to compare different explanation methods and choose the most reliable one for your application.
215 stars. No commits in the last 6 months.
Use this if you need to evaluate and compare different interpretability techniques to confidently explain the predictions of your Transformer text models.
Not ideal if you are working with non-textual data or require explanations for model architectures other than Transformers.
Stars
215
Forks
17
Language
Python
License
MIT
Category
Last pushed
Sep 29, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/g8a9/ferret"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
LoicGrobol/zeldarose
Train transformer-based models.
CPJKU/wechsel
Code for WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of...
yuanzhoulvpi2017/zero_nlp
中文nlp解决方案(大模型、数据、模型、训练、推理)
minggnim/nlp-models
A repository for training transformer based models
IntelLabs/nlp-architect
A model library for exploring state-of-the-art deep learning topologies and techniques for...