Add user interface to ch06 and ch07 (#366)

* Add user interface to ch06 and ch07

* pep8

* fix url

ch05/06_user_interface/README.md

@@ -29,7 +29,7 @@ pip install chainlit
 This folder contains 2 files:
 
 1. [`app_orig.py`](app_orig.py): This file loads and uses the original GPT-2 weights from OpenAI. 
-2. [`app_own.py`](app_own.py): This file loads and uses the GPT-2 weights we generated in chapter 5. This requires that you execute the [`../01_main-chapter-code/ch05.ipynb`] file first.
+2. [`app_own.py`](app_own.py): This file loads and uses the GPT-2 weights we generated in chapter 5. This requires that you execute the [`../01_main-chapter-code/ch05.ipynb`](../01_main-chapter-code/ch05.ipynb) file first.
 
 (Open and inspect these files to learn more.)
 

ch05/06_user_interface/app_orig.py

@@ -21,7 +21,7 @@ device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
 def get_model_and_tokenizer():
     """
-    Code to loads a GPT-2 model with pretrained weights from OpenAI.
+    Code to load a GPT-2 model with pretrained weights from OpenAI.
     The code is similar to chapter 5.
     The model will be downloaded automatically if it doesn't exist in the current folder, yet.
     """

ch05/06_user_interface/app_own.py

@@ -22,7 +22,7 @@ device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
 def get_model_and_tokenizer():
     """
-    Code to loads a GPT-2 model with pretrained weights generated in chapter 5.
+    Code to load a GPT-2 model with pretrained weights generated in chapter 5.
     This requires that you run the code in chapter 5 first, which generates the necessary model.pth file.
     """
 

ch05/06_user_interface/previous_chapters.py

@@ -12,55 +12,11 @@ import urllib
 
 import numpy as np
 import tensorflow as tf
-import tiktoken
 import torch
 import torch.nn as nn
-from torch.utils.data import Dataset, DataLoader
 from tqdm import tqdm
 
 
-#####################################
-# Chapter 2
-#####################################
-
-
-class GPTDatasetV1(Dataset):
-    def __init__(self, txt, tokenizer, max_length, stride):
-        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
-
-
 #####################################
 # Chapter 3
 #####################################