reliability-score 🎯

[reliability-score documentation]

Description

A suite of reliability tests for NLP models.

How to install

Install the package

pip install git+https://github.com/Maitreyapatel/reliability-score

Evaluate example model/data with default configuration

# eval on CPU
rs

# eval on GPU
rs trainer=gpu

Evaluate model with chosen dataset-specific experiment configuration from reliability_score/configs/experiment/

rs experiment=<experiment_name>

Specify the custom model_name as shown in following MNLI example

# if model_name is used for tokenizer as well.
rs experiment=mnli custom_model="bert-base-uncased-mnli"

# if model_name is different for tokenizer then
rs experiment=mnli custom_model="bert-base-uncased-mnli" custom_model.tokenizer.model_name="ishan/bert-base-uncased-mnli"

add custom_model config

# create config folder structure similar to reliability_score/configs/
mkdir ./configs/
mkdir ./configs/custom_model/

# run following command after creating new config file inside ./configs/custom_model/<your-config>.yaml
rs experiment=mnli custom_model=<your-config>

Documentation:

The locally hosted documentation can be found at: LINK