berkerdemirel/GPT-from-scratch
Re-implementation of Andrej Karpathy's nanoGPT
This project helps machine learning engineers and researchers understand how large language models (LLMs) work by providing a simplified, re-implemented version of a generative pre-trained transformer (GPT). You feed it text data, and it learns to generate new, similar text based on the patterns it identified. It's ideal for those looking to explore the foundational architecture of models like GPT.
No commits in the last 6 months.
Use this if you are a machine learning practitioner or student who wants to grasp the core mechanics of GPT models from the ground up, using a minimalist codebase.
Not ideal if you need a production-ready LLM for complex applications or a tool that solves a specific business problem beyond educational exploration.
Stars
16
Forks
6
Language
Python
License
—
Category
Last pushed
Feb 16, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/berkerdemirel/GPT-from-scratch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Nixtla/nixtla
TimeGPT-1: production ready pre-trained Time Series Foundation Model for forecasting and...
andrewdalpino/NoPE-GPT
A GPT-style small language model (SLM) with no positional embeddings (NoPE).
sigdelsanjog/gptmed
pip install gptmed
akanyaani/gpt-2-tensorflow2.0
OpenAI GPT2 pre-training and sequence prediction implementation in Tensorflow 2.0
samkamau81/FinGPT_
FinGPT is an AI language model designed to understand and generate financial content. Built upon...