PyPI page
Home page
Author:
Krithika Ramesh, Daniel Smolyak, Zihao Zhao, Nupoor Gandhi
Summary:
SynthTextEval is an open-source library built to enable comprehensive evaluation of synthetic text generated by large language models (LLMs). It supports the evaluation of synthetic text by considering its downstream utility, fairness, privacy preservation, and automated text quality evaluation, along with functionality for both descriptive and visual data analysis and synthetic text generation with differential privacy.
Latest version:
1.1.1
Required dependencies:
datasets
|
evaluate
|
gitpython
|
ipython
|
matplotlib
|
mauve_text
|
numpy
|
opacus
|
pandas
|
prv-accountant
|
pyldavis
|
pynvml
|
rouge_score
|
scikit_learn
|
scipy
|
seaborn
|
sentence_transformers
|
setuptools
|
spacy
|
tabulate
|
torch
|
tqdm
|
transformers
Downloads last day:
7
Downloads last week:
12
Downloads last month:
19