a LLM cookbook, for building your own from scratch, all the way from gathering data to training a model
-
Updated
Jun 25, 2024 - Jupyter Notebook
a LLM cookbook, for building your own from scratch, all the way from gathering data to training a model
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
Experimental project for AI and NLP based on Transformer Architecture
Transformers Intuition
Generate caption on images using CNN Encoder- LSTM Decoder structure
An LLM based tool for generation of cheese advirtisements
a dna sequence generation/classification using transformers
Code and dataset used to train dialect adapters for decoder models.
Implementation of the GPT-3 paper: Language Models are Few-Shot Learners
Build Text summarizer for arabic language
Decoder model for language modelling
A Decoder Based Semantic Parser that can be tested on four benchmark datasets (ATIS, GeoQuery, Jobs640 and Django)
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.
This project aims to simplify texts from research papers using advanced natural language processing (NLP) techniques, making them more accessible to a broader audience
Add a description, image, and links to the decoder-model topic page so that developers can more easily learn about it.
To associate your repository with the decoder-model topic, visit your repo's landing page and select "manage topics."