{ "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 }