transformers-models

A framework for large scale recommendation algorithms.

Repository for Project Insight: NLP as a Service

Federated Learning Utilities and Tools for Experimentation

CLIP (Contrastive Language–Image Pre-training) for Italian

I will implement Fastai in each projects present in this repository.

Pytorch implementation of image captioning using transformer-based model.

[TMI 2023] XBound-Former: Toward Cross-scale Boundary Modeling in Transformers

Symbolic music generation taking inspiration from NLP and human composition process

Neural Persian Poet: A sequence-to-sequence model for composing Persian poetry

Public repo for the paper: "Modeling Intensification for Sign Language Generation: A Computational Approach" by Mert Inan*, Yang Zhong*, Sabit Hassan*, Lorna Quandt, Malihe Alikhani

An autoML for explainable text classification.

The special repository to demonstrate how you can use transformers for Swahili text classification

Public repo for the paper: "COSMic: A Coherence-Aware Generation Metric for Image Descriptions" by Mert İnan, Piyush Sharma, Baber Khalid, Radu Soricut, Matthew Stone, Malihe Alikhani

Train a T5 model to generate simple Fake News and use a RoBERTa model to classify what's fake and what's real.

A Transformer Implementation that is easy to understand and customizable.

Contains work done on the fintech patents classification project. The goal of this project is to build a model that can detect if a patent is fintech or not based on it's text content. If a patent is fintech then we want to know which kind of fintech patent it is form our defined fintech categories.

Comparing between residual stream and highway stream in transformers(BERT) .

Minimalistic PyTorch implementation of transformer

This repository contains a number of experiments with Multi Lingual Transformer models (Multi-Lingual BERT, DistilBERT, XLM-RoBERTa, mT5 and ByT5) focussed on the Dutch language.

Convert the normal maps used in the game Transformers: Fall of Cybertron to the Mikk format