File size: 2,466 Bytes
30c14cd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "e89d234c",
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(\"/mnt/ceph_rbd/comp_rag/data/retrieval_data/2m_split_data_sample_from_4m/train_all_mix.jsonl\", \"r\") as f:\n",
    "    data = []\n",
    "    import json \n",
    "    index = 0 \n",
    "    for line in f:\n",
    "        index += 1\n",
    "        if index > 1000:\n",
    "            break\n",
    "        data.append(json.loads(line))\n",
    "\n",
    "with open(\"/mnt/ceph_rbd/comp_rag/unirag/debug_data/pretrain_data.jsonl\", \"w\") as f:\n",
    "    for d in data:\n",
    "        f.write(json.dumps(d) + \"\\n\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "1e995b27",
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(\"/mnt/ceph_rbd/comp_rag/data/pisco_data/train_top_5_rerank_splade_predicted_answer.jsonl\", \"r\") as f:\n",
    "    data = []\n",
    "    index = 0   \n",
    "    for line in f:\n",
    "        index += 1\n",
    "        if index > 1000:\n",
    "            break\n",
    "        data.append(json.loads(line))\n",
    "\n",
    "with open(\"/mnt/ceph_rbd/comp_rag/unirag/debug_data/instruction_tuning_data.jsonl\", \"w\") as f:\n",
    "    for d in data:\n",
    "        f.write(json.dumps(d) + \"\\n\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "b0f72276",
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(\"/mnt/ceph_rbd/comp_rag/data/stage2_training/ours_musique/train_processed_with_pos.jsonl\", \"r\") as f:\n",
    "    data = []\n",
    "    index = 0\n",
    "    for line in f:\n",
    "        index += 1\n",
    "        if index > 1000:\n",
    "            break\n",
    "        data.append(json.loads(line))\n",
    "\n",
    "with open(\"/mnt/ceph_rbd/comp_rag/unirag/debug_data/instruction_tuning_training_data.jsonl\", \"w\") as f:\n",
    "    for d in data:\n",
    "        f.write(json.dumps(d) + \"\\n\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "distill",
   "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": "3.8.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}