src/utils.py

import torch

with open("data/input.txt") as f:
    text = f.read()

chars = sorted(list(set(text)))
vocab_size = len(chars)

stoi = {ch: i for i, ch in enumerate(chars)}
itos = {i: ch for i, ch in enumerate(chars)}


def encode(s):
    return [stoi[c] for c in s]


def decode(l):
    return "".join([itos[i] for i in l])


data = torch.tensor(encode(text), dtype=torch.long)
n = int(0.9 * len(data))
train_data = data[:n]
val_data = data[n:]


def get_batch(split, block_size, batch_size):
    data = train_data if split == "train" else val_data
    ix = torch.randint(len(data) - block_size, (batch_size,))
    x = torch.stack([data[i : i + block_size] for i in ix])
    y = torch.stack([data[i + 1 : i + block_size + 1] for i in ix])
    return x, y