vinayakarannil

ControlNet

Let us control diffusion models!

txtai

💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows

Inpaint-Anything

Inpaint anything using Segment Anything and inpainting models.

nlpaug

Data augmentation for NLP

data-science-on-aws

AI and Machine Learning with Kubeflow, Amazon EKS, and SageMaker

presidio

Context aware, pluggable and customizable data protection and de-identification SDK for text and images

machine-learning

:earth_americas: machine learning tutorials (mainly in Python3)

NAB

The Numenta Anomaly Benchmark

LLM-Finetuning

LLM Finetuning with peft

Transformer-Explainability

[CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.

hh-rlhf

Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"

OpenOOD

Benchmarking Generalized Out-of-Distribution Detection

jiwer

Evaluate your speech-to-text system with similarity measures such as word error rate (WER)

scrubadub

Clean personally identifiable information from dirty dirty text.

Glow-PyTorch

Simple, extendable, easy to understand Glow implementation in PyTorch

VL-T5

PyTorch code for "Unifying Vision-and-Language Tasks via Text Generation" (ICML 2021)

Indic-BERT-v1

Indic-BERT-v1: BERT-based Multilingual Model for 11 Indic Languages and Indian-English. For latest Indic-BERT v2, check: https://github.com/AI4Bharat/IndicBERT

media-insights-on-aws

A serverless framework to accelerate the development of applications that discover next-generation insights in your video, audio, text, and image resources by utilizing AWS Machine Learning and Media services.

VL_adapter

PyTorch code for "VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks" (CVPR2022)

pretraining-with-human-feedback

Code accompanying the paper Pretraining Language Models with Human Preferences

sagemaker-studio-custom-image-samples

This repository contains examples of Docker images that can be used as custom images for KernelGateway Apps in SageMaker Studio

eraserbenchmark

A benchmark for understanding and evaluating rationales: http://www.eraserbenchmark.com/

content-analysis-on-aws

As of August 30, 2023, this AWS Solution is no longer available. Existing deployments will continue to run. The functionality provided by Content Analysis on AWS will be superseded with functionality in Media2Cloud on AWS and Content Localization on AWS. We encourage you to explore these solutions.

amazon-transcribe-post-call-analytics

Named-Entity-Recognition

Corpus and a baseline neural network system for Named Entity Recognition in Hindi-English Code-Mixed social media text.

text-anonymization-benchmark

Annotated corpus + evaluation metrics for text anonymisation

united-nations-ner

Fine-tuning a Hugging Face BERT model for the United Nations Named Entity Recognition task.

indic-wx-converter

Python library for converting UTF to WX and vice-versa for Indian languages.

email-response-automation-comprehend

Text_Detection_Synthetic_DataGenerator

Synthetic data generator for text detection/localisation tasks.