a LLM cookbook, for building your own from scratch, all the way from gathering data to training a model

Experimental project for AI and NLP based on Transformer Architecture

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

Implementation of the GPT-3 paper: Language Models are Few-Shot Learners

从零实现基础的Transformer的Decoerder-Only模型，并进行模型升级，构建专属于自己的LLM模型

This repo represents my Nano-GPT speedrun playground, which started coding along Let's reproduce GPT-2 (124M), then moved into further improvements.

Generate caption on images using CNN Encoder- LSTM Decoder structure

Transformers Intuition

An explainable and simplified version of OLMo model

Generative AI fine-tune and inference for sequence classification tasks

This project aims to simplify texts from research papers using advanced natural language processing (NLP) techniques, making them more accessible to a broader audience

Code and dataset used to train dialect adapters for decoder models.

This project focuses on the implementation of inverting I-JEAP, a new architecture designed to simulate human intelligence through self-supervised learning. Our goal is to invert the embeddings to demonstrate that such architectures can be vulnerable to inversion attacks

a dna sequence generation/classification using transformers

An LLM based tool for generation of cheese advirtisements

On the Design and Performance of Machine Learning Based Error Correcting Decoders

Clavier is a language model that generates sheet music and MIDI files in the style of classical composers

Text Generation using RNN, LSTM, and Transformer

Coding A Decoder Only Transformer Like ChatGPT From Scratch

Custom decoder Transformer that treats a patient's medical journey like a story told through diagnosis codes instead of words.