tweak notebook

train.ipynb

@@ -1,5 +1,17 @@
 {
  "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cc8bcc5f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%%bash\n",
+    "git config --global --add safe.directory /home/jovyan/workspace\n",
+    "git checkout -b <your branch>"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -23,7 +35,8 @@
     "\n",
     "    return f\"{model}-rev{max_rev + 1}\"\n",
     "\n",
-    "os.environ[\"HF_HOME\"] = \"/workspace/\""
+    "os.environ[\"HF_HOME\"] = \"/workspace/\"\n",
+    "os.environ[\"HF_TOKEN\"] = \"your_huggingface_token_here\""
    ]
   },
   {
@@ -42,9 +55,9 @@
    "outputs": [],
    "source": [
     "%pip install -r data/requirements.txt\n",
-    "from data.generate_home_assistant_data import main as generate_data\n",
+    "from data.generate_data import main as generate_data\n",
     "\n",
-    "generate_data([\"--train\", \"--test\", \"--large\", \"--sharegpt\", \"--language\", \"english\", \"german\", \"french\", \"spanish\", \"polish\"])"
+    "generate_data([\"--train\", \"--test\", \"--large\", \"--language\", \"english\", \"german\", \"french\", \"spanish\", \"polish\"])"
    ]
   },
   {