Sebastian Raschka c21bfe4a23
Add PyPI package (#576)
* Add PyPI package

* fixes

* fixes
2025-03-23 19:28:49 -05:00

47 lines
1.6 KiB
Python

# Copyright (c) Sebastian Raschka under Apache License 2.0 (see LICENSE.txt).
# Source for "Build a Large Language Model From Scratch"
# - https://www.manning.com/books/build-a-large-language-model-from-scratch
# Code: https://github.com/rasbt/LLMs-from-scratch
import torch
from torch.utils.data import Dataset, DataLoader
import tiktoken
class GPTDatasetV1(Dataset):
def __init__(self, txt, tokenizer, max_length, stride):
self.tokenizer = tokenizer
self.input_ids = []
self.target_ids = []
# Tokenize the entire text
token_ids = tokenizer.encode(txt, allowed_special={"<|endoftext|>"})
# Use a sliding window to chunk the book into overlapping sequences of max_length
for i in range(0, len(token_ids) - max_length, stride):
input_chunk = token_ids[i:i + max_length]
target_chunk = token_ids[i + 1: i + max_length + 1]
self.input_ids.append(torch.tensor(input_chunk))
self.target_ids.append(torch.tensor(target_chunk))
def __len__(self):
return len(self.input_ids)
def __getitem__(self, idx):
return self.input_ids[idx], self.target_ids[idx]
def create_dataloader_v1(txt, batch_size=4, max_length=256,
stride=128, shuffle=True, drop_last=True, num_workers=0):
# Initialize the tokenizer
tokenizer = tiktoken.get_encoding("gpt2")
# Create dataset
dataset = GPTDatasetV1(txt, tokenizer, max_length, stride)
# Create dataloader
dataloader = DataLoader(
dataset, batch_size=batch_size, shuffle=shuffle, drop_last=drop_last, num_workers=num_workers)
return dataloader