Minor readability improvement in dataloader.ipynb

- The tokenizer and encoded_text variables at the root level are unused.
- The default params for create_dataloader_v1 are confusing, especially for the default batch_size 4, which happens to be the same as the max_length.

Author: tao-qian

ch02/01_main-chapter-code/dataloader.ipynb

@@ -103,8 +103,7 @@
     "        return self.input_ids[idx], self.target_ids[idx]\n",
     "\n",
     "\n",
-    "def create_dataloader_v1(txt, batch_size=4, max_length=256, \n",
-    "                         stride=128, shuffle=True, drop_last=True, num_workers=0):\n",
+    "def create_dataloader_v1(txt, batch_size, max_length, stride, shuffle=True, drop_last=True, num_workers=0):\n",
     "    # Initialize the tokenizer\n",
     "    tokenizer = tiktoken.get_encoding(\"gpt2\")\n",
     "\n",
@@ -121,9 +120,6 @@
     "with open(\"the-verdict.txt\", \"r\", encoding=\"utf-8\") as f:\n",
     "    raw_text = f.read()\n",
     "\n",
-    "tokenizer = tiktoken.get_encoding(\"gpt2\")\n",
-    "encoded_text = tokenizer.encode(raw_text)\n",
-    "\n",
     "vocab_size = 50257\n",
     "output_dim = 256\n",
     "context_length = 1024\n",
@@ -132,8 +128,9 @@
     "token_embedding_layer = torch.nn.Embedding(vocab_size, output_dim)\n",
     "pos_embedding_layer = torch.nn.Embedding(context_length, output_dim)\n",
     "\n",
+    "batch_size = 8\n",
     "max_length = 4\n",
-    "dataloader = create_dataloader_v1(raw_text, batch_size=8, max_length=max_length, stride=max_length)"
+    "dataloader = create_dataloader_v1(raw_text, batch_size=batch_size, max_length=max_length, stride=max_length)"
    ]
   },
   {