PhoGPT: Generative Pre-training for Vietnamese (2023)
-
Updated
Nov 12, 2024 - Python
PhoGPT: Generative Pre-training for Vietnamese (2023)
An autoregressive language model like ChatGPT.
HELM-GPT: de novo macrocyclic peptide design using generative pre-trained transformer
Inspired by Andrej Karpathy’s "Let’s Build GPT", this project guides you step‑by‑step to build a GPT from scratch, demystifying its architecture through clear, hands‑on code.
A GPT-2-class language model trained from scratch on OpenWebText with the intent to augment AI Transformer-model education and reverse engineer GPT models from scratch.
Simple GPT app that uses the falcon-7b-instruct model with a Flask front-end.
A pure Rust GPT implementation from scratch.
SARAN: Shallow Auto-Regressive Attention Network
MicroGPT is a clean, educational implementation of the GPT (Generative Pre-trained Transformer) architecture built from first principles with detailed explanations and comprehensive testing.
I built a GPT model from scratch to generate text
An Industrial Project about NLP in Finance Application
A implimentation of GPT2 varient.
Unlock the power of your PDFs with HackWES-PDFChatGenius! This innovative project, developed during the HackWES hackathon, transforms the way you interact with PDF documents. Simply upload your PDF, and engage in a natural conversation to extract information, ask questions, and gain insights from your documents.
This is a NLP coursework repository for the Honours Bachelor of Artificial Intelligence program at Durham College. This repository contains weekly labs, assignments, and the final project completed during the Winter 2024 term.
ToyGPT, inspired by Andrej Karpathy’s GPT from scratch, creates a toy generative pre-trained transformer at its most basic level using a simple bigram language model with attention to help educate on the basics of creating an LLM from scratch.
A Generatively Pretrained Transformer that generates Shakespeare-eque quotes
An academic implementation of GPT: only math and raw JAX
Mechanistic Interpretability (MI) is a subfield of AI alignment and safety research focused on reverse-engineering neural networks to understand their internal computational mechanisms by discovering the actual algorithms and circuits they learn.
A hands-on implementation of the technologies behind modern Large Language Models, covering gradient descent, backpropagation, tokenization, transformers, self-attention, and GPT architecture. The project emphasizes understanding AI systems from first principles rather than relying solely on high-level frameworks.
Repository for all things Natural Language Processing
To associate your repository with the generative-pre-trained-transformer topic, visit your repo's landing page and select "manage topics."