transformers

[CogSci'21] Study of human inductive biases in CNNs and Transformers.

SentimentArcs: a large ensemble of dozens of sentiment analysis models to analyze emotion in text over time

Transformer Networks for Pedestrian Detection

Sparse-upcycle a dense Gemma-3-270m into a Mixture-of-Experts (gemma3moe) and serve it on llama.cpp (CPU). Upcycle, train, inspect routing, GGUF.

Language Models as Hierarchy Encoders

In this project, several approaches for training/finetuning an audio gender recognition is provided. The code can simply be used for any other audio classification task by simply changing the number of classes and the input dataset.

Context-Based-Question-Answering

Structured pruning, knowledge distillation, and fairness analysis for Large Language Models.

Building a suicidal text detection model and mental health chatbot with deep learning models and transformers.

This repo contains my work & The code base for this Deep Learning Specialization offered by deeplearning.AI

Spark-Transformers: Library for exporting Apache Spark MLLIB models to use them in any Java application with no other dependencies.

RATransformers 🐭- Make your transformer (like BERT, RoBERTa, GPT-2 and T5) Relation Aware!

Official implementation of the paper: Unsupervised MRI Reconstruction via Zero-Shot Learned Adversarial Transformers

The notebook explains the various steps to obtain the results of publication: "Is Space-Time Attention All You Need for Video Understanding?"

ChatWithPDF is a cutting-edge platform that enhances PDF functionality. Users can upload PDFs, extract summaries, and get answers to questions. It features an attractive UI with shadcn and Tailwind CSS and employs advanced tech like Langchain and OpenAI models for chat completions and text embeddings. It's a powerful tool for document management

Airflow Pipeline for Machine Learning

A repo that attempts to train stable diffusion 3 from scratch

End-to-end pipeline for seeing how LLMs actually process your prompts. Capture attention across every layer, render heatmaps and cooking curves, compare variants with evidence — not vibes.

PyTorch implementation of the ICASSP-24 paper: "Improving Audio Captioning Models with Fine-grained Audio Features, Text Embedding Supervision, and LLM Mix-up Augmentation"

Code for "Finetuning Pretrained Transformers into Variational Autoencoders"