add ch6 code

docs/chapter6/code/process_dataset.ipynb

@@ -0,0 +1,44 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "8c3d4501-a268-418a-b5f6-59078094aab5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "\n",
+    "fw = open(\"autodl-tmp/dataset/pretrain_data/mobvoi_seq_monkey_general_open_corpus_small.jsonl\", \"w\")\n",
+    "i = 0\n",
+    "with open(\"autodl-tmp/dataset/pretrain_data/mobvoi_seq_monkey_general_open_corpus.jsonl\", \"r\") as f:\n",
+    "    while i <= 1000000:\n",
+    "        line = f.readline()\n",
+    "        fw.write(line)\n",
+    "        i += 1\n",
+    "fw.close()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}