Andrés Caicedo nació en Cali, Valle, en 1951 y, a pesar de su prematura muerte (1977), descolló en el campo literario colombiano. Escribió numerosos cuentos, recopilados en varios volúmenes: El atravesado (relato, 1975), Angelitos empantanados o historia para jovencitos (1977), y Berenice (1978). Su única novela ¡Qué viva la música! ha tenido gran difusión entre el público.
Con este proyecto buscamos hacer una forma de necromancia que lo trae de vuelta a nuestras vidas de forma cibernetica.
Generate input file from txt source:
macbook:
cat txt/*.txt >> input/input.txt
Generate clean input:
python clean.py >> input/input_clean.txt
Run bigram algo on input:
python bigram.py
Run GPT
python gpt.py
Parametrize input and output to add more customization
Perform better data clean steps for spanish
Install missing packages like:
pip install torch
pip install numpy
Using python version 3.11
Thanks to Karpathy for an amazing explanation and the source code for this model.
Honestly wouldn't have attempted this if he hadn't made it so easy. Cheers to open source and community.
nanogpt-lecture
Code created in the Neural Networks: Zero To Hero video lecture series, specifically on the first lecture on nanoGPT. Publishing here as a Github repo so people can easily hack it, walk through the git log history of it, etc.
NOTE: sadly I did not go too much into model initialization in the video lecture, but it is quite important for good performance. The current code will train and work fine, but its convergence is slower because it starts off in a not great spot in the weight space. Please see nanoGPT model.py for # init all weights comment, and especially how it calls the _init_weights function. Even more sadly, the code in this repo is a bit different in how it names and stores the various modules, so it's not possible to directly copy paste this code here. My current plan is to publish a supplementary video lecture and cover these parts, then I will also push the exact code changes to this repo. For now I'm keeping it as is so it is almost exactly what we actually covered in the video.