adamwawrzynski

According to [Hierarchical Attention Networks for Document Classification](https://www.aclweb.org/anthology/N16-1174.pdf`) in the attention mechanism they use softmax function to obtain weights of attention layer. I think there is a bug in Your...

[Q] LT-SFT and enc-dec models?

3

I'm wondering if this method should (theoretically) work with enc-dec models? Have You tried to train those models with code from this repository? I'm interested in utilizing this approach with...

Add example of XAI step

3

## Describe changes I added an explainable AI step using [FoXAI](https://github.com/softwaremill/FoXAI) framework. PR is intended to start a discussion on how to add XAI integration to zenml. The result of...

## 🐛 Bug Function `visualize_image_attr_multiple` incorrectly handles negative values of passed image. In provided script I've provided preprocessing similar to pretrained networks from `torchvision`. During preprocessing negative values occur and...

#### Description Tried to run Google Cloud Run deployment [example](https://github.com/bentoml/google-cloud-run-deploy) and encountered problem with non existing temp directory during `bentoctl build` command execution. It turned out that when function `_prepare_bento_dir`...

AWS Lambda deployment - service is deployed but fails to launch

1

**Describe the bug** After model deployment service is not responsive due to error. **To Reproduce** 1. Follow steps in aws-lambda-deplyoment repository: https://github.com/bentoml/aws-lambda-deploy. 2. Test in AWS Lambda console. **Expected behavior**...

Example run error

2

I am using docker container to install all dependencies. It looks as follows: ```dockerfile FROM ubuntu:latest WORKDIR /app RUN apt-get update -y \ && apt-get install -y \ git \...

Add API for easy the best XAI algorithm selection based on model, dataset, and XAI metrics. Estimation: 5 MD

## Description This PR introduces a notebook with an example of quantitative evaluation of XAI algorithms. This way we could create a utility to automatically select the best explainable algorithm...

Add a description of baseline selection in docstrings or add additional methods for baseline generation, such as 4-Rand, black, white, and black+white.