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

a dna sequence generation/classification using transformers

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

An LLM based tool for generation of cheese advirtisements

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

Text Generation using RNN, LSTM, and Transformer

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

Coding A Decoder Only Transformer Like ChatGPT From Scratch

Using LLMs in huggingface for sentiment analysis, translation, summarization and extractive question answering

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

No description provided.

Decoder model for language modelling

A mini version of GPT implemented on shakespear using BPE

Offline Kalman filter demo, Z-score and Ridge regression to adapt KF parameters

A miniGPT inspired from the original NanoGPT released by OpenAI. This is a notebook to walk through the decoder part of the transformer architecture with details outlined.

Build Text summarizer for arabic language

A multimodal vision model that takes in an image and a prompt query, and output the answer

Intent Detection API using BERT and Flask

Decoder-only language model trained to generate texts that look like Shakespear's plays

Offline CNN demo, Z-score, auto offset and sgolay control