Name: hgissbkh/IRThresholding-Datasets
Creator: hgissbkh
Published: 2025-11-27 04:08:42
License: 暂无描述

下载链接：

https://hf-mirror.com/datasets/hgissbkh/IRThresholding-Datasets

下载链接

链接失效反馈

官方服务：

资源简介：

--- dataset_info: - config_name: ArgimiArdian features: - name: query_id dtype: int64 - name: query dtype: string - name: positive_documents list: int64 - name: answer dtype: string splits: - name: calibration num_bytes: 3112718 num_examples: 10685 - name: test num_bytes: 315981 num_examples: 1000 download_size: 1828222 dataset_size: 3428699 - config_name: ArgimiArdian-corpus features: - name: document_id dtype: int64 - name: document dtype: string splits: - name: corpus num_bytes: 12947363 num_examples: 3495 download_size: 5855893 dataset_size: 12947363 - config_name: ArgimiArdian-corpus-Qwen3-Embedding-0.6B features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 28672980 num_examples: 3495 download_size: 5417838 dataset_size: 28672980 - config_name: ArgimiArdian-corpus-bge-base-en-v1.5 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 21515220 num_examples: 3495 download_size: 4075140 dataset_size: 21515220 - config_name: ArgimiArdian-corpus-bge-large-en-v1.5 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 28672980 num_examples: 3495 download_size: 5464342 dataset_size: 28672980 - config_name: ArgimiArdian-corpus-bge-small-en-v1.5 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 10778580 num_examples: 3495 download_size: 2056109 dataset_size: 10778580 - config_name: ArgimiArdian-corpus-e5-base-v2 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 21515220 num_examples: 3495 download_size: 4074480 dataset_size: 21515220 - config_name: ArgimiArdian-corpus-e5-large-v2 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 28672980 num_examples: 3495 download_size: 5420870 dataset_size: 28672980 - config_name: ArgimiArdian-corpus-e5-small-v2 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 10778580 num_examples: 3495 download_size: 2054667 dataset_size: 10778580 - config_name: ArgimiArdian-corpus-embeddinggemma-300m features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 21515220 num_examples: 3495 download_size: 4075373 dataset_size: 21515220 - config_name: ArgimiArdian-queries-Qwen3-Embedding-0.6B features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 87659740 num_examples: 10685 - name: test num_bytes: 8204000 num_examples: 1000 download_size: 18095456 dataset_size: 95863740 - config_name: ArgimiArdian-queries-bge-base-en-v1.5 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 65776860 num_examples: 10685 - name: test num_bytes: 6156000 num_examples: 1000 download_size: 14275745 dataset_size: 71932860 - config_name: ArgimiArdian-queries-bge-large-en-v1.5 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 87659740 num_examples: 10685 - name: test num_bytes: 8204000 num_examples: 1000 download_size: 19065151 dataset_size: 95863740 - config_name: ArgimiArdian-queries-bge-small-en-v1.5 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 32952540 num_examples: 10685 - name: test num_bytes: 3084000 num_examples: 1000 download_size: 6961832 dataset_size: 36036540 - config_name: ArgimiArdian-queries-e5-base-v2 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 65776860 num_examples: 10685 - name: test num_bytes: 6156000 num_examples: 1000 download_size: 13883484 dataset_size: 71932860 - config_name: ArgimiArdian-queries-e5-large-v2 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 87659740 num_examples: 10685 - name: test num_bytes: 8204000 num_examples: 1000 download_size: 18845891 dataset_size: 95863740 - config_name: ArgimiArdian-queries-e5-small-v2 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 32952540 num_examples: 10685 - name: test num_bytes: 3084000 num_examples: 1000 download_size: 6851732 dataset_size: 36036540 - config_name: ArgimiArdian-queries-embeddinggemma-300m features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 65776860 num_examples: 10685 - name: test num_bytes: 6156000 num_examples: 1000 download_size: 14297364 dataset_size: 71932860 - config_name: CoQA features: - name: query_id dtype: int64 - name: query dtype: string - name: positive_documents list: int64 - name: answer dtype: string splits: - name: calibration num_bytes: 731353 num_examples: 6699 - name: test num_bytes: 110721 num_examples: 1000 download_size: 585400 dataset_size: 842074 - config_name: CoQA-corpus features: - name: document_id dtype: int64 - name: document dtype: string splits: - name: corpus num_bytes: 11215959 num_examples: 7070 download_size: 7096447 dataset_size: 11215959 - config_name: CoQA-corpus-Qwen3-Embedding-0.6B features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 58002280 num_examples: 7070 download_size: 10946398 dataset_size: 58002280 - config_name: CoQA-corpus-bge-base-en-v1.5 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 43522920 num_examples: 7070 download_size: 8525000 dataset_size: 43522920 - config_name: CoQA-corpus-bge-large-en-v1.5 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 58002280 num_examples: 7070 download_size: 11479410 dataset_size: 58002280 - config_name: CoQA-corpus-bge-small-en-v1.5 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 21803880 num_examples: 7070 download_size: 4191858 dataset_size: 21803880 - config_name: CoQA-corpus-e5-base-v2 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 43522920 num_examples: 7070 download_size: 8287917 dataset_size: 43522920 - config_name: CoQA-corpus-e5-large-v2 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 58002280 num_examples: 7070 download_size: 11286246 dataset_size: 58002280 - config_name: CoQA-corpus-e5-small-v2 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 21803880 num_examples: 7070 download_size: 4142695 dataset_size: 21803880 - config_name: CoQA-corpus-embeddinggemma-300m features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 43522920 num_examples: 7070 download_size: 8519637 dataset_size: 43522920 - config_name: CoQA-queries-Qwen3-Embedding-0.6B features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 54958596 num_examples: 6699 - name: test num_bytes: 8204000 num_examples: 1000 download_size: 11932959 dataset_size: 63162596 - config_name: CoQA-queries-bge-base-en-v1.5 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 41239044 num_examples: 6699 - name: test num_bytes: 6156000 num_examples: 1000 download_size: 9245351 dataset_size: 47395044 - config_name: CoQA-queries-bge-large-en-v1.5 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 54958596 num_examples: 6699 - name: test num_bytes: 8204000 num_examples: 1000 download_size: 12442332 dataset_size: 63162596 - config_name: CoQA-queries-bge-small-en-v1.5 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 20659716 num_examples: 6699 - name: test num_bytes: 3084000 num_examples: 1000 download_size: 4525354 dataset_size: 23743716 - config_name: CoQA-queries-e5-base-v2 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 41239044 num_examples: 6699 - name: test num_bytes: 6156000 num_examples: 1000 download_size: 8970258 dataset_size: 47395044 - config_name: CoQA-queries-e5-large-v2 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 54958596 num_examples: 6699 - name: test num_bytes: 8204000 num_examples: 1000 download_size: 11990280 dataset_size: 63162596 - config_name: CoQA-queries-e5-small-v2 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 20659716 num_examples: 6699 - name: test num_bytes: 3084000 num_examples: 1000 download_size: 4523504 dataset_size: 23743716 - config_name: CoQA-queries-embeddinggemma-300m features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 41239044 num_examples: 6699 - name: test num_bytes: 6156000 num_examples: 1000 download_size: 9343847 dataset_size: 47395044 - config_name: HotpotQA features: - name: query_id dtype: int64 - name: query dtype: string - name: positive_documents list: int64 - name: answer dtype: string splits: - name: calibration num_bytes: 921315 num_examples: 6405 - name: test num_bytes: 143395 num_examples: 1000 download_size: 735744 dataset_size: 1064710 - config_name: HotpotQA-corpus features: - name: document_id dtype: int64 - name: document dtype: string splits: - name: corpus num_bytes: 37838765 num_examples: 66635 download_size: 23264286 dataset_size: 37838765 - config_name: HotpotQA-corpus-Qwen3-Embedding-0.6B features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 546673540 num_examples: 66635 download_size: 103116551 dataset_size: 546673540 - config_name: HotpotQA-corpus-bge-base-en-v1.5 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 410205060 num_examples: 66635 download_size: 82169409 dataset_size: 410205060 - config_name: HotpotQA-corpus-bge-large-en-v1.5 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 546673540 num_examples: 66635 download_size: 109403810 dataset_size: 546673540 - config_name: HotpotQA-corpus-bge-small-en-v1.5 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 205502340 num_examples: 66635 download_size: 41346013 dataset_size: 205502340 - config_name: HotpotQA-corpus-e5-base-v2 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 410205060 num_examples: 66635 download_size: 81277725 dataset_size: 410205060 - config_name: HotpotQA-corpus-e5-large-v2 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 546673540 num_examples: 66635 download_size: 108367050 dataset_size: 546673540 - config_name: HotpotQA-corpus-e5-small-v2 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 205502340 num_examples: 66635 download_size: 40913751 dataset_size: 205502340 - config_name: HotpotQA-corpus-embeddinggemma-300m features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 410205060 num_examples: 66635 download_size: 82161814 dataset_size: 410205060 - config_name: HotpotQA-queries-Qwen3-Embedding-0.6B features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 52546620 num_examples: 6405 - name: test num_bytes: 8204000 num_examples: 1000 download_size: 11478077 dataset_size: 60750620 - config_name: HotpotQA-queries-bge-base-en-v1.5 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 39429180 num_examples: 6405 - name: test num_bytes: 6156000 num_examples: 1000 download_size: 8858516 dataset_size: 45585180 - config_name: HotpotQA-queries-bge-large-en-v1.5 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 52546620 num_examples: 6405 - name: test num_bytes: 8204000 num_examples: 1000 download_size: 11915168 dataset_size: 60750620 - config_name: HotpotQA-queries-bge-small-en-v1.5 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 19753020 num_examples: 6405 - name: test num_bytes: 3084000 num_examples: 1000 download_size: 4353291 dataset_size: 22837020 - config_name: HotpotQA-queries-e5-base-v2 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 39429180 num_examples: 6405 - name: test num_bytes: 6156000 num_examples: 1000 download_size: 8640453 dataset_size: 45585180 - config_name: HotpotQA-queries-e5-large-v2 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 52546620 num_examples: 6405 - name: test num_bytes: 8204000 num_examples: 1000 download_size: 11629737 dataset_size: 60750620 - config_name: HotpotQA-queries-e5-small-v2 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 19753020 num_examples: 6405 - name: test num_bytes: 3084000 num_examples: 1000 download_size: 4352043 dataset_size: 22837020 - config_name: HotpotQA-queries-embeddinggemma-300m features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 39429180 num_examples: 6405 - name: test num_bytes: 6156000 num_examples: 1000 download_size: 8930291 dataset_size: 45585180 - config_name: MSMARCO features: - name: query_id dtype: int64 - name: query dtype: string - name: positive_documents list: int64 - name: answer dtype: string splits: - name: calibration num_bytes: 1088432 num_examples: 7515 - name: test num_bytes: 142033 num_examples: 1000 download_size: 838627 dataset_size: 1230465 - config_name: MSMARCO-corpus features: - name: document_id dtype: int64 - name: document dtype: string splits: - name: corpus num_bytes: 29428617 num_examples: 68381 download_size: 17340864 dataset_size: 29428617 - config_name: MSMARCO-corpus-Qwen3-Embedding-0.6B features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 560997724 num_examples: 68381 download_size: 105810173 dataset_size: 560997724 - config_name: MSMARCO-corpus-bge-base-en-v1.5 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 420953436 num_examples: 68381 download_size: 84249863 dataset_size: 420953436 - config_name: MSMARCO-corpus-bge-large-en-v1.5 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 560997724 num_examples: 68381 download_size: 112345294 dataset_size: 560997724 - config_name: MSMARCO-corpus-bge-small-en-v1.5 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 210887004 num_examples: 68381 download_size: 42403431 dataset_size: 210887004 - config_name: MSMARCO-corpus-e5-base-v2 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 420953436 num_examples: 68381 download_size: 83334972 dataset_size: 420953436 - config_name: MSMARCO-corpus-e5-large-v2 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 560997724 num_examples: 68381 download_size: 110956875 dataset_size: 560997724 - config_name: MSMARCO-corpus-e5-small-v2 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 210887004 num_examples: 68381 download_size: 41999820 dataset_size: 210887004 - config_name: MSMARCO-corpus-embeddinggemma-300m features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 420953436 num_examples: 68381 download_size: 84267964 dataset_size: 420953436 - config_name: MSMARCO-queries-Qwen3-Embedding-0.6B features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 61653060 num_examples: 7515 - name: test num_bytes: 8204000 num_examples: 1000 download_size: 13195556 dataset_size: 69857060 - config_name: MSMARCO-queries-bge-base-en-v1.5 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 46262340 num_examples: 7515 - name: test num_bytes: 6156000 num_examples: 1000 download_size: 10259692 dataset_size: 52418340 - config_name: MSMARCO-queries-bge-large-en-v1.5 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 61653060 num_examples: 7515 - name: test num_bytes: 8204000 num_examples: 1000 download_size: 13797705 dataset_size: 69857060 - config_name: MSMARCO-queries-bge-small-en-v1.5 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 23176260 num_examples: 7515 - name: test num_bytes: 3084000 num_examples: 1000 download_size: 5011135 dataset_size: 26260260 - config_name: MSMARCO-queries-e5-base-v2 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 46262340 num_examples: 7515 - name: test num_bytes: 6156000 num_examples: 1000 download_size: 9918777 dataset_size: 52418340 - config_name: MSMARCO-queries-e5-large-v2 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 61653060 num_examples: 7515 - name: test num_bytes: 8204000 num_examples: 1000 download_size: 13365751 dataset_size: 69857060 - config_name: MSMARCO-queries-e5-small-v2 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 23176260 num_examples: 7515 - name: test num_bytes: 3084000 num_examples: 1000 download_size: 4999672 dataset_size: 26260260 - config_name: MSMARCO-queries-embeddinggemma-300m features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 46262340 num_examples: 7515 - name: test num_bytes: 6156000 num_examples: 1000 download_size: 10387814 dataset_size: 52418340 - config_name: PubMedQA features: - name: query_id dtype: int64 - name: query dtype: string - name: positive_documents list: int64 - name: answer dtype: string splits: - name: calibration num_bytes: 30539739 num_examples: 210269 - name: test num_bytes: 144277 num_examples: 1000 download_size: 17523684 dataset_size: 30684016 - config_name: PubMedQA-corpus features: - name: document_id dtype: int64 - name: document dtype: string splits: - name: corpus num_bytes: 292486746 num_examples: 211215 download_size: 159412994 dataset_size: 292486746 - config_name: PubMedQA-corpus-Qwen3-Embedding-0.6B features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 1732807860 num_examples: 211215 download_size: 326862800 dataset_size: 1732807860 - config_name: PubMedQA-corpus-bge-base-en-v1.5 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 1300239540 num_examples: 211215 download_size: 259934657 dataset_size: 1300239540 - config_name: PubMedQA-corpus-bge-large-en-v1.5 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 1732807860 num_examples: 211215 download_size: 345300115 dataset_size: 1732807860 - config_name: PubMedQA-corpus-bge-small-en-v1.5 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 651387060 num_examples: 211215 download_size: 130381766 dataset_size: 651387060 - config_name: PubMedQA-corpus-e5-base-v2 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 1300239540 num_examples: 211215 download_size: 256350746 dataset_size: 1300239540 - config_name: PubMedQA-corpus-e5-large-v2 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 1732807860 num_examples: 211215 download_size: 342082893 dataset_size: 1732807860 - config_name: PubMedQA-corpus-e5-small-v2 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 651387060 num_examples: 211215 download_size: 129481207 dataset_size: 651387060 - config_name: PubMedQA-corpus-embeddinggemma-300m features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 1300239540 num_examples: 211215 download_size: 259098674 dataset_size: 1300239540 - config_name: PubMedQA-queries-Qwen3-Embedding-0.6B features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 1725046876 num_examples: 210269 - name: test num_bytes: 8204000 num_examples: 1000 download_size: 326964547 dataset_size: 1733250876 - config_name: PubMedQA-queries-bge-base-en-v1.5 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 1294415964 num_examples: 210269 - name: test num_bytes: 6156000 num_examples: 1000 download_size: 259979290 dataset_size: 1300571964 - config_name: PubMedQA-queries-bge-large-en-v1.5 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 1725046876 num_examples: 210269 - name: test num_bytes: 8204000 num_examples: 1000 download_size: 345801474 dataset_size: 1733250876 - config_name: PubMedQA-queries-bge-small-en-v1.5 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 648469596 num_examples: 210269 - name: test num_bytes: 3084000 num_examples: 1000 download_size: 130435237 dataset_size: 651553596 - config_name: PubMedQA-queries-e5-base-v2 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 1294415964 num_examples: 210269 - name: test num_bytes: 6156000 num_examples: 1000 download_size: 255944613 dataset_size: 1300571964 - config_name: PubMedQA-queries-e5-large-v2 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 1725046876 num_examples: 210269 - name: test num_bytes: 8204000 num_examples: 1000 download_size: 340676845 dataset_size: 1733250876 - config_name: PubMedQA-queries-e5-small-v2 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 648469596 num_examples: 210269 - name: test num_bytes: 3084000 num_examples: 1000 download_size: 129312880 dataset_size: 651553596 - config_name: PubMedQA-queries-embeddinggemma-300m features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 1294415964 num_examples: 210269 - name: test num_bytes: 6156000 num_examples: 1000 download_size: 260832757 dataset_size: 1300571964 - config_name: SQuADv2 features: - name: query_id dtype: int64 - name: query dtype: string - name: positive_documents list: int64 - name: answer dtype: string splits: - name: calibration num_bytes: 1130383 num_examples: 10873 - name: test num_bytes: 104282 num_examples: 1000 download_size: 578237 dataset_size: 1234665 - config_name: SQuADv2-corpus features: - name: document_id dtype: int64 - name: document dtype: string splits: - name: corpus num_bytes: 982484 num_examples: 1204 download_size: 614443 dataset_size: 982484 - config_name: SQuADv2-corpus-Qwen3-Embedding-0.6B features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 9877616 num_examples: 1204 download_size: 1875881 dataset_size: 9877616 - config_name: SQuADv2-corpus-bge-base-en-v1.5 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 7411824 num_examples: 1204 download_size: 1414209 dataset_size: 7411824 - config_name: SQuADv2-corpus-bge-large-en-v1.5 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 9877616 num_examples: 1204 download_size: 1878101 dataset_size: 9877616 - config_name: SQuADv2-corpus-bge-small-en-v1.5 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 3713136 num_examples: 1204 download_size: 718429 dataset_size: 3713136 - config_name: SQuADv2-corpus-e5-base-v2 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 7411824 num_examples: 1204 download_size: 1413417 dataset_size: 7411824 - config_name: SQuADv2-corpus-e5-large-v2 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 9877616 num_examples: 1204 download_size: 1877542 dataset_size: 9877616 - config_name: SQuADv2-corpus-e5-small-v2 features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 3713136 num_examples: 1204 download_size: 717244 dataset_size: 3713136 - config_name: SQuADv2-corpus-embeddinggemma-300m features: - name: document_id dtype: int64 - name: embedding list: float64 splits: - name: corpus num_bytes: 7411824 num_examples: 1204 download_size: 1414155 dataset_size: 7411824 - config_name: SQuADv2-queries-Qwen3-Embedding-0.6B features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 89202092 num_examples: 10873 - name: test num_bytes: 8204000 num_examples: 1000 download_size: 18387383 dataset_size: 97406092 - config_name: SQuADv2-queries-bge-base-en-v1.5 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 66934188 num_examples: 10873 - name: test num_bytes: 6156000 num_examples: 1000 download_size: 14499776 dataset_size: 73090188 - config_name: SQuADv2-queries-bge-large-en-v1.5 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 89202092 num_examples: 10873 - name: test num_bytes: 8204000 num_examples: 1000 download_size: 19407860 dataset_size: 97406092 - config_name: SQuADv2-queries-bge-small-en-v1.5 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 33532332 num_examples: 10873 - name: test num_bytes: 3084000 num_examples: 1000 download_size: 7107755 dataset_size: 36616332 - config_name: SQuADv2-queries-e5-base-v2 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 66934188 num_examples: 10873 - name: test num_bytes: 6156000 num_examples: 1000 download_size: 14168796 dataset_size: 73090188 - config_name: SQuADv2-queries-e5-large-v2 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 89202092 num_examples: 10873 - name: test num_bytes: 8204000 num_examples: 1000 download_size: 19060716 dataset_size: 97406092 - config_name: SQuADv2-queries-e5-small-v2 features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 33532332 num_examples: 10873 - name: test num_bytes: 3084000 num_examples: 1000 download_size: 6961172 dataset_size: 36616332 - config_name: SQuADv2-queries-embeddinggemma-300m features: - name: query_id dtype: int64 - name: embedding list: float64 splits: - name: calibration num_bytes: 66934188 num_examples: 10873 - name: test num_bytes: 6156000 num_examples: 1000 download_size: 14580176 dataset_size: 73090188 configs: - config_name: ArgimiArdian data_files: - split: calibration path: ArgimiArdian/calibration-* - split: test path: ArgimiArdian/test-* - config_name: ArgimiArdian-corpus data_files: - split: corpus path: ArgimiArdian-corpus/corpus-* - config_name: ArgimiArdian-corpus-Qwen3-Embedding-0.6B data_files: - split: corpus path: ArgimiArdian-corpus-Qwen3-Embedding-0.6B/corpus-* - config_name: ArgimiArdian-corpus-bge-base-en-v1.5 data_files: - split: corpus path: ArgimiArdian-corpus-bge-base-en-v1.5/corpus-* - config_name: ArgimiArdian-corpus-bge-large-en-v1.5 data_files: - split: corpus path: ArgimiArdian-corpus-bge-large-en-v1.5/corpus-* - config_name: ArgimiArdian-corpus-bge-small-en-v1.5 data_files: - split: corpus path: ArgimiArdian-corpus-bge-small-en-v1.5/corpus-* - config_name: ArgimiArdian-corpus-e5-base-v2 data_files: - split: corpus path: ArgimiArdian-corpus-e5-base-v2/corpus-* - config_name: ArgimiArdian-corpus-e5-large-v2 data_files: - split: corpus path: ArgimiArdian-corpus-e5-large-v2/corpus-* - config_name: ArgimiArdian-corpus-e5-small-v2 data_files: - split: corpus path: ArgimiArdian-corpus-e5-small-v2/corpus-* - config_name: ArgimiArdian-corpus-embeddinggemma-300m data_files: - split: corpus path: ArgimiArdian-corpus-embeddinggemma-300m/corpus-* - config_name: ArgimiArdian-queries-Qwen3-Embedding-0.6B data_files: - split: calibration path: ArgimiArdian-queries-Qwen3-Embedding-0.6B/calibration-* - split: test path: ArgimiArdian-queries-Qwen3-Embedding-0.6B/test-* - config_name: ArgimiArdian-queries-bge-base-en-v1.5 data_files: - split: calibration path: ArgimiArdian-queries-bge-base-en-v1.5/calibration-* - split: test path: ArgimiArdian-queries-bge-base-en-v1.5/test-* - config_name: ArgimiArdian-queries-bge-large-en-v1.5 data_files: - split: calibration path: ArgimiArdian-queries-bge-large-en-v1.5/calibration-* - split: test path: ArgimiArdian-queries-bge-large-en-v1.5/test-* - config_name: ArgimiArdian-queries-bge-small-en-v1.5 data_files: - split: calibration path: ArgimiArdian-queries-bge-small-en-v1.5/calibration-* - split: test path: ArgimiArdian-queries-bge-small-en-v1.5/test-* - config_name: ArgimiArdian-queries-e5-base-v2 data_files: - split: calibration path: ArgimiArdian-queries-e5-base-v2/calibration-* - split: test path: ArgimiArdian-queries-e5-base-v2/test-* - config_name: ArgimiArdian-queries-e5-large-v2 data_files: - split: calibration path: ArgimiArdian-queries-e5-large-v2/calibration-* - split: test path: ArgimiArdian-queries-e5-large-v2/test-* - config_name: ArgimiArdian-queries-e5-small-v2 data_files: - split: calibration path: ArgimiArdian-queries-e5-small-v2/calibration-* - split: test path: ArgimiArdian-queries-e5-small-v2/test-* - config_name: ArgimiArdian-queries-embeddinggemma-300m data_files: - split: calibration path: ArgimiArdian-queries-embeddinggemma-300m/calibration-* - split: test path: ArgimiArdian-queries-embeddinggemma-300m/test-* - config_name: CoQA data_files: - split: calibration path: CoQA/calibration-* - split: test path: CoQA/test-* - config_name: CoQA-corpus data_files: - split: corpus path: CoQA-corpus/corpus-* - config_name: CoQA-corpus-Qwen3-Embedding-0.6B data_files: - split: corpus path: CoQA-corpus-Qwen3-Embedding-0.6B/corpus-* - config_name: CoQA-corpus-bge-base-en-v1.5 data_files: - split: corpus path: CoQA-corpus-bge-base-en-v1.5/corpus-* - config_name: CoQA-corpus-bge-large-en-v1.5 data_files: - split: corpus path: CoQA-corpus-bge-large-en-v1.5/corpus-* - config_name: CoQA-corpus-bge-small-en-v1.5 data_files: - split: corpus path: CoQA-corpus-bge-small-en-v1.5/corpus-* - config_name: CoQA-corpus-e5-base-v2 data_files: - split: corpus path: CoQA-corpus-e5-base-v2/corpus-* - config_name: CoQA-corpus-e5-large-v2 data_files: - split: corpus path: CoQA-corpus-e5-large-v2/corpus-* - config_name: CoQA-corpus-e5-small-v2 data_files: - split: corpus path: CoQA-corpus-e5-small-v2/corpus-* - config_name: CoQA-corpus-embeddinggemma-300m data_files: - split: corpus path: CoQA-corpus-embeddinggemma-300m/corpus-* - config_name: CoQA-queries-Qwen3-Embedding-0.6B data_files: - split: calibration path: CoQA-queries-Qwen3-Embedding-0.6B/calibration-* - split: test path: CoQA-queries-Qwen3-Embedding-0.6B/test-* - config_name: CoQA-queries-bge-base-en-v1.5 data_files: - split: calibration path: CoQA-queries-bge-base-en-v1.5/calibration-* - split: test path: CoQA-queries-bge-base-en-v1.5/test-* - config_name: CoQA-queries-bge-large-en-v1.5 data_files: - split: calibration path: CoQA-queries-bge-large-en-v1.5/calibration-* - split: test path: CoQA-queries-bge-large-en-v1.5/test-* - config_name: CoQA-queries-bge-small-en-v1.5 data_files: - split: calibration path: CoQA-queries-bge-small-en-v1.5/calibration-* - split: test path: CoQA-queries-bge-small-en-v1.5/test-* - config_name: CoQA-queries-e5-base-v2 data_files: - split: calibration path: CoQA-queries-e5-base-v2/calibration-* - split: test path: CoQA-queries-e5-base-v2/test-* - config_name: CoQA-queries-e5-large-v2 data_files: - split: calibration path: CoQA-queries-e5-large-v2/calibration-* - split: test path: CoQA-queries-e5-large-v2/test-* - config_name: CoQA-queries-e5-small-v2 data_files: - split: calibration path: CoQA-queries-e5-small-v2/calibration-* - split: test path: CoQA-queries-e5-small-v2/test-* - config_name: CoQA-queries-embeddinggemma-300m data_files: - split: calibration path: CoQA-queries-embeddinggemma-300m/calibration-* - split: test path: CoQA-queries-embeddinggemma-300m/test-* - config_name: HotpotQA data_files: - split: calibration path: HotpotQA/calibration-* - split: test path: HotpotQA/test-* - config_name: HotpotQA-corpus data_files: - split: corpus path: HotpotQA-corpus/corpus-* - config_name: HotpotQA-corpus-Qwen3-Embedding-0.6B data_files: - split: corpus path: HotpotQA-corpus-Qwen3-Embedding-0.6B/corpus-* - config_name: HotpotQA-corpus-bge-base-en-v1.5 data_files: - split: corpus path: HotpotQA-corpus-bge-base-en-v1.5/corpus-* - config_name: HotpotQA-corpus-bge-large-en-v1.5 data_files: - split: corpus path: HotpotQA-corpus-bge-large-en-v1.5/corpus-* - config_name: HotpotQA-corpus-bge-small-en-v1.5 data_files: - split: corpus path: HotpotQA-corpus-bge-small-en-v1.5/corpus-* - config_name: HotpotQA-corpus-e5-base-v2 data_files: - split: corpus path: HotpotQA-corpus-e5-base-v2/corpus-* - config_name: HotpotQA-corpus-e5-large-v2 data_files: - split: corpus path: HotpotQA-corpus-e5-large-v2/corpus-* - config_name: HotpotQA-corpus-e5-small-v2 data_files: - split: corpus path: HotpotQA-corpus-e5-small-v2/corpus-* - config_name: HotpotQA-corpus-embeddinggemma-300m data_files: - split: corpus path: HotpotQA-corpus-embeddinggemma-300m/corpus-* - config_name: HotpotQA-queries-Qwen3-Embedding-0.6B data_files: - split: calibration path: HotpotQA-queries-Qwen3-Embedding-0.6B/calibration-* - split: test path: HotpotQA-queries-Qwen3-Embedding-0.6B/test-* - config_name: HotpotQA-queries-bge-base-en-v1.5 data_files: - split: calibration path: HotpotQA-queries-bge-base-en-v1.5/calibration-* - split: test path: HotpotQA-queries-bge-base-en-v1.5/test-* - config_name: HotpotQA-queries-bge-large-en-v1.5 data_files: - split: calibration path: HotpotQA-queries-bge-large-en-v1.5/calibration-* - split: test path: HotpotQA-queries-bge-large-en-v1.5/test-* - config_name: HotpotQA-queries-bge-small-en-v1.5 data_files: - split: calibration path: HotpotQA-queries-bge-small-en-v1.5/calibration-* - split: test path: HotpotQA-queries-bge-small-en-v1.5/test-* - config_name: HotpotQA-queries-e5-base-v2 data_files: - split: calibration path: HotpotQA-queries-e5-base-v2/calibration-* - split: test path: HotpotQA-queries-e5-base-v2/test-* - config_name: HotpotQA-queries-e5-large-v2 data_files: - split: calibration path: HotpotQA-queries-e5-large-v2/calibration-* - split: test path: HotpotQA-queries-e5-large-v2/test-* - config_name: HotpotQA-queries-e5-small-v2 data_files: - split: calibration path: HotpotQA-queries-e5-small-v2/calibration-* - split: test path: HotpotQA-queries-e5-small-v2/test-* - config_name: HotpotQA-queries-embeddinggemma-300m data_files: - split: calibration path: HotpotQA-queries-embeddinggemma-300m/calibration-* - split: test path: HotpotQA-queries-embeddinggemma-300m/test-* - config_name: MSMARCO data_files: - split: calibration path: MSMARCO/calibration-* - split: test path: MSMARCO/test-* - config_name: MSMARCO-corpus data_files: - split: corpus path: MSMARCO-corpus/corpus-* - config_name: MSMARCO-corpus-Qwen3-Embedding-0.6B data_files: - split: corpus path: MSMARCO-corpus-Qwen3-Embedding-0.6B/corpus-* - config_name: MSMARCO-corpus-bge-base-en-v1.5 data_files: - split: corpus path: MSMARCO-corpus-bge-base-en-v1.5/corpus-* - config_name: MSMARCO-corpus-bge-large-en-v1.5 data_files: - split: corpus path: MSMARCO-corpus-bge-large-en-v1.5/corpus-* - config_name: MSMARCO-corpus-bge-small-en-v1.5 data_files: - split: corpus path: MSMARCO-corpus-bge-small-en-v1.5/corpus-* - config_name: MSMARCO-corpus-e5-base-v2 data_files: - split: corpus path: MSMARCO-corpus-e5-base-v2/corpus-* - config_name: MSMARCO-corpus-e5-large-v2 data_files: - split: corpus path: MSMARCO-corpus-e5-large-v2/corpus-* - config_name: MSMARCO-corpus-e5-small-v2 data_files: - split: corpus path: MSMARCO-corpus-e5-small-v2/corpus-* - config_name: MSMARCO-corpus-embeddinggemma-300m data_files: - split: corpus path: MSMARCO-corpus-embeddinggemma-300m/corpus-* - config_name: MSMARCO-queries-Qwen3-Embedding-0.6B data_files: - split: calibration path: MSMARCO-queries-Qwen3-Embedding-0.6B/calibration-* - split: test path: MSMARCO-queries-Qwen3-Embedding-0.6B/test-* - config_name: MSMARCO-queries-bge-base-en-v1.5 data_files: - split: calibration path: MSMARCO-queries-bge-base-en-v1.5/calibration-* - split: test path: MSMARCO-queries-bge-base-en-v1.5/test-* - config_name: MSMARCO-queries-bge-large-en-v1.5 data_files: - split: calibration path: MSMARCO-queries-bge-large-en-v1.5/calibration-* - split: test path: MSMARCO-queries-bge-large-en-v1.5/test-* - config_name: MSMARCO-queries-bge-small-en-v1.5 data_files: - split: calibration path: MSMARCO-queries-bge-small-en-v1.5/calibration-* - split: test path: MSMARCO-queries-bge-small-en-v1.5/test-* - config_name: MSMARCO-queries-e5-base-v2 data_files: - split: calibration path: MSMARCO-queries-e5-base-v2/calibration-* - split: test path: MSMARCO-queries-e5-base-v2/test-* - config_name: MSMARCO-queries-e5-large-v2 data_files: - split: calibration path: MSMARCO-queries-e5-large-v2/calibration-* - split: test path: MSMARCO-queries-e5-large-v2/test-* - config_name: MSMARCO-queries-e5-small-v2 data_files: - split: calibration path: MSMARCO-queries-e5-small-v2/calibration-* - split: test path: MSMARCO-queries-e5-small-v2/test-* - config_name: MSMARCO-queries-embeddinggemma-300m data_files: - split: calibration path: MSMARCO-queries-embeddinggemma-300m/calibration-* - split: test path: MSMARCO-queries-embeddinggemma-300m/test-* - config_name: PubMedQA data_files: - split: calibration path: PubMedQA/calibration-* - split: test path: PubMedQA/test-* - config_name: PubMedQA-corpus data_files: - split: corpus path: PubMedQA-corpus/corpus-* - config_name: PubMedQA-corpus-Qwen3-Embedding-0.6B data_files: - split: corpus path: PubMedQA-corpus-Qwen3-Embedding-0.6B/corpus-* - config_name: PubMedQA-corpus-bge-base-en-v1.5 data_files: - split: corpus path: PubMedQA-corpus-bge-base-en-v1.5/corpus-* - config_name: PubMedQA-corpus-bge-large-en-v1.5 data_files: - split: corpus path: PubMedQA-corpus-bge-large-en-v1.5/corpus-* - config_name: PubMedQA-corpus-bge-small-en-v1.5 data_files: - split: corpus path: PubMedQA-corpus-bge-small-en-v1.5/corpus-* - config_name: PubMedQA-corpus-e5-base-v2 data_files: - split: corpus path: PubMedQA-corpus-e5-base-v2/corpus-* - config_name: PubMedQA-corpus-e5-large-v2 data_files: - split: corpus path: PubMedQA-corpus-e5-large-v2/corpus-* - config_name: PubMedQA-corpus-e5-small-v2 data_files: - split: corpus path: PubMedQA-corpus-e5-small-v2/corpus-* - config_name: PubMedQA-corpus-embeddinggemma-300m data_files: - split: corpus path: PubMedQA-corpus-embeddinggemma-300m/corpus-* - config_name: PubMedQA-queries-Qwen3-Embedding-0.6B data_files: - split: calibration path: PubMedQA-queries-Qwen3-Embedding-0.6B/calibration-* - split: test path: PubMedQA-queries-Qwen3-Embedding-0.6B/test-* - config_name: PubMedQA-queries-bge-base-en-v1.5 data_files: - split: calibration path: PubMedQA-queries-bge-base-en-v1.5/calibration-* - split: test path: PubMedQA-queries-bge-base-en-v1.5/test-* - config_name: PubMedQA-queries-bge-large-en-v1.5 data_files: - split: calibration path: PubMedQA-queries-bge-large-en-v1.5/calibration-* - split: test path: PubMedQA-queries-bge-large-en-v1.5/test-* - config_name: PubMedQA-queries-bge-small-en-v1.5 data_files: - split: calibration path: PubMedQA-queries-bge-small-en-v1.5/calibration-* - split: test path: PubMedQA-queries-bge-small-en-v1.5/test-* - config_name: PubMedQA-queries-e5-base-v2 data_files: - split: calibration path: PubMedQA-queries-e5-base-v2/calibration-* - split: test path: PubMedQA-queries-e5-base-v2/test-* - config_name: PubMedQA-queries-e5-large-v2 data_files: - split: calibration path: PubMedQA-queries-e5-large-v2/calibration-* - split: test path: PubMedQA-queries-e5-large-v2/test-* - config_name: PubMedQA-queries-e5-small-v2 data_files: - split: calibration path: PubMedQA-queries-e5-small-v2/calibration-* - split: test path: PubMedQA-queries-e5-small-v2/test-* - config_name: PubMedQA-queries-embeddinggemma-300m data_files: - split: calibration path: PubMedQA-queries-embeddinggemma-300m/calibration-* - split: test path: PubMedQA-queries-embeddinggemma-300m/test-* - config_name: SQuADv2 data_files: - split: calibration path: SQuADv2/calibration-* - split: test path: SQuADv2/test-* - config_name: SQuADv2-corpus data_files: - split: corpus path: SQuADv2-corpus/corpus-* - config_name: SQuADv2-corpus-Qwen3-Embedding-0.6B data_files: - split: corpus path: SQuADv2-corpus-Qwen3-Embedding-0.6B/corpus-* - config_name: SQuADv2-corpus-bge-base-en-v1.5 data_files: - split: corpus path: SQuADv2-corpus-bge-base-en-v1.5/corpus-* - config_name: SQuADv2-corpus-bge-large-en-v1.5 data_files: - split: corpus path: SQuADv2-corpus-bge-large-en-v1.5/corpus-* - config_name: SQuADv2-corpus-bge-small-en-v1.5 data_files: - split: corpus path: SQuADv2-corpus-bge-small-en-v1.5/corpus-* - config_name: SQuADv2-corpus-e5-base-v2 data_files: - split: corpus path: SQuADv2-corpus-e5-base-v2/corpus-* - config_name: SQuADv2-corpus-e5-large-v2 data_files: - split: corpus path: SQuADv2-corpus-e5-large-v2/corpus-* - config_name: SQuADv2-corpus-e5-small-v2 data_files: - split: corpus path: SQuADv2-corpus-e5-small-v2/corpus-* - config_name: SQuADv2-corpus-embeddinggemma-300m data_files: - split: corpus path: SQuADv2-corpus-embeddinggemma-300m/corpus-* - config_name: SQuADv2-queries-Qwen3-Embedding-0.6B data_files: - split: calibration path: SQuADv2-queries-Qwen3-Embedding-0.6B/calibration-* - split: test path: SQuADv2-queries-Qwen3-Embedding-0.6B/test-* - config_name: SQuADv2-queries-bge-base-en-v1.5 data_files: - split: calibration path: SQuADv2-queries-bge-base-en-v1.5/calibration-* - split: test path: SQuADv2-queries-bge-base-en-v1.5/test-* - config_name: SQuADv2-queries-bge-large-en-v1.5 data_files: - split: calibration path: SQuADv2-queries-bge-large-en-v1.5/calibration-* - split: test path: SQuADv2-queries-bge-large-en-v1.5/test-* - config_name: SQuADv2-queries-bge-small-en-v1.5 data_files: - split: calibration path: SQuADv2-queries-bge-small-en-v1.5/calibration-* - split: test path: SQuADv2-queries-bge-small-en-v1.5/test-* - config_name: SQuADv2-queries-e5-base-v2 data_files: - split: calibration path: SQuADv2-queries-e5-base-v2/calibration-* - split: test path: SQuADv2-queries-e5-base-v2/test-* - config_name: SQuADv2-queries-e5-large-v2 data_files: - split: calibration path: SQuADv2-queries-e5-large-v2/calibration-* - split: test path: SQuADv2-queries-e5-large-v2/test-* - config_name: SQuADv2-queries-e5-small-v2 data_files: - split: calibration path: SQuADv2-queries-e5-small-v2/calibration-* - split: test path: SQuADv2-queries-e5-small-v2/test-* - config_name: SQuADv2-queries-embeddinggemma-300m data_files: - split: calibration path: SQuADv2-queries-embeddinggemma-300m/calibration-* - split: test path: SQuADv2-queries-embeddinggemma-300m/test-* ---

应用场景：