Update 4_Train CLMBR.ipynb

som-shahlab · Apr 27, 2024 · 9d593cf · 9d593cf
1 parent 0df7121
commit 9d593cf
Showing 1 changed file with 1 addition and 0 deletions.
diff --git a/tutorials/4_Train CLMBR.ipynb b/tutorials/4_Train CLMBR.ipynb
@@ -131,6 +131,7 @@
     "\n",
     "# First, we need to train a tokenizer\n",
     "\n",
+    "# NOTE: A vocab size of 128 is probably too low for a real model. 128 was chosen to make this tutorial quick to run\n",
     "tokenizer = femr.models.tokenizer.train_tokenizer(\n",
     "    main_dataset['train'], vocab_size=128, num_proc=4)\n",
     "\n",