Orchestrate Swarms of Agents From Any Framework Like OpenAI, Langchain, and Etc for Business Operation Automation. Join our Community: https://discord.gg/DbjBMJTSWD

A simple but complete full-attention transformer with a set of promising experimental features from various papers

Xllama🦙 is an Extensible advanced language model framework, inspired by the original Llama model.

QuillGPT is an implementation of the GPT decoder block based on the architecture from Attention is All You Need paper by Vaswani et. al. in PyTorch. Additionally, this repository contains two pre-trained models — Shakespearean GPT and Harpoon GPT, a Streamlit Playground, Containerized FastAPI Microservice, training - inference scripts & notebooks.

Sequence-to-sequence framework with a focus on Neural Machine Translation based on PyTorch

This repository features a custom-built decoder-only language model (LLM) with a total of 37 million parameters 🔥. I train the model to be able to ask question from a given context

An attention based approach to convert Indian Sign Language to Text using simulated hand gesture data

Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)

Visualizing the attention of vision-language models

Experimental project on building custom LSTM and LSTM with Attention layer for comparison analysis on FTS forecasting (June 2024)

Learn Generative AI with PyTorch (Manning Publications, 2024)

[ICML 2024] Outlier-Efficient Hopfield Layers for Large Transformer-Based Models

Scripts and trained models from our paper: M. Ntrougkas, N. Gkalelis, V. Mezaris, "T-TAME: Trainable Attention Mechanism for Explaining Convolutional Networks and Vision Transformers", IEEE Access, 2024. DOI:10.1109/ACCESS.2024.3405788.

Codes related to the paper "Attention-Based CNN-BiLSTM for Sleep States Classification of Spatiotemporal Wide-Field Calcium Imaging Data"

Faster alternative to Metal Performance Shaders

My reimplementations of some of the transformer-based models. LLM and LVMs.

DanteGPT

GPT-based protein language model for PTM site prediction

A Python package housing a collection of deep-learning multi-modal data fusion method pipelines! From data loading, to training, to evaluation - fusilli's got you covered 🌸

A novel implementation of fusing ViT with Mamba into a fast, agile, and high performance Multi-Modal Model. Powered by Zeta, the simplest AI framework ever.