增加了一个专门为mlx的数据处理代码

finetune/data_processing.ipynb

@@ -0,0 +1,66 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 1. 准备数据集\n",
+    "\n",
+    "将数据集转换为更通用的格式\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 转换为 ChatML 格式\n",
+    "import os\n",
+    "import shutil\n",
+    "import json\n",
+    "\n",
+    "input_dir = \"data/AdvertiseGen\"\n",
+    "output_dir = \"data/mlx_AdvertiseGen\"\n",
+    "if os.path.exists(output_dir):\n",
+    "    shutil.rmtree(output_dir)\n",
+    "os.makedirs(output_dir, exist_ok=True)\n",
+    "\n",
+    "for fn in [\"train.json\", \"dev.json\"]:\n",
+    "    data_out_list = []\n",
+    "    with open(os.path.join(input_dir, fn), \"r\") as f, open(os.path.join(output_dir, fn), \"w\") as fo:\n",
+    "        for line in f:\n",
+    "            if len(line.strip()) > 0:\n",
+    "                data = json.loads(line)\n",
+    "                data_out = {\"input\":data['content'],'prompt':\"/n请为以下关键词生成一条广告语。\",'output':data['summary']}\n",
+    "                data_out_list.append(data_out)\n",
+    "\n",
+    "        for d in data_out_list:\n",
+    "            json_str = json.dumps(d,ensure_ascii=False)  # 将字典转换为JSON字符串\n",
+    "            fo.write(json_str + '\\n')  # 写入字符串并添加换行符\n",
+    "\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "base",
+   "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": "3.10.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}