five

hatemestinbejaia/STCALIR_Synthetic-Test-Collection

收藏
Hugging Face2026-04-08 更新2026-03-29 收录
下载链接:
https://hf-mirror.com/datasets/hatemestinbejaia/STCALIR_Synthetic-Test-Collection
下载链接
链接失效反馈
官方服务:
资源简介:
--- dataset_info: - config_name: STCALIR-Topics_embedding_mmarco-Arabic-AraDPR-bi-encoder-KD-v1 features: - name: id dtype: int64 - name: text dtype: string - name: embedding list: float32 splits: - name: train num_bytes: 317181 num_examples: 100 download_size: 314900 dataset_size: 317181 - config_name: STCALIR-Topics_embedding_mmarco-Arabic-AraDPR-bi-encoder-NoKD-v1 features: - name: id dtype: int64 - name: text dtype: string - name: embedding list: float32 splits: - name: train num_bytes: 317181 num_examples: 100 download_size: 314900 dataset_size: 317181 - config_name: STCALIR-Topics_embedding_mmarco-Arabic-AraElectra-bi-encoder-KD-v1 features: - name: id dtype: int64 - name: text dtype: string - name: embedding list: float32 splits: - name: train num_bytes: 317181 num_examples: 100 download_size: 314896 dataset_size: 317181 - config_name: STCALIR-Topics_embedding_mmarco-Arabic-AraElectra-bi-encoder-NoKD-v1 features: - name: id dtype: int64 - name: text dtype: string - name: embedding list: float32 splits: - name: train num_bytes: 317181 num_examples: 100 download_size: 314900 dataset_size: 317181 - config_name: STCALIR-Topics_embedding_mmarco-Arabic-mMiniLML-bi-encoder-KD-v1 features: - name: id dtype: int64 - name: text dtype: string - name: embedding list: float32 splits: - name: train num_bytes: 163581 num_examples: 100 download_size: 161231 dataset_size: 163581 - config_name: STCALIR-Topics_embedding_mmarco-Arabic-mMiniLML-bi-encoder-NoKD-v1 features: - name: id dtype: int64 - name: text dtype: string - name: embedding list: float32 splits: - name: train num_bytes: 163581 num_examples: 100 download_size: 161231 dataset_size: 163581 - config_name: STCALIR_collection_embedding_mmarco-Arabic-AraDPR-bi-encoder-KD-v1 features: - name: id dtype: string - name: text dtype: string - name: embedding list: float32 splits: - name: train num_bytes: 422946528 num_examples: 105201 download_size: 351862743 dataset_size: 422946528 - config_name: STCALIR_collection_embedding_mmarco-Arabic-AraDPR-bi-encoder-NoKD-v1 features: - name: id dtype: string - name: text dtype: string - name: embedding list: float32 splits: - name: train num_bytes: 422946528 num_examples: 105201 download_size: 351862081 dataset_size: 422946528 - config_name: STCALIR_collection_embedding_mmarco-Arabic-AraElectra-bi-encoder-KD-v1 features: - name: id dtype: string - name: text dtype: string - name: embedding list: float32 splits: - name: train num_bytes: 422946528 num_examples: 105201 download_size: 351862236 dataset_size: 422946528 - config_name: STCALIR_collection_embedding_mmarco-Arabic-AraElectra-bi-encoder-NoKD-v1 features: - name: id dtype: string - name: text dtype: string - name: embedding list: float32 splits: - name: train num_bytes: 422946528 num_examples: 105201 download_size: 351862517 dataset_size: 422946528 - config_name: STCALIR_collection_embedding_mmarco-Arabic-mMiniLML-bi-encoder-KD-v1 features: - name: id dtype: string - name: text dtype: string - name: embedding list: float32 splits: - name: train num_bytes: 261357792 num_examples: 105201 download_size: 190222087 dataset_size: 261357792 - config_name: STCALIR_collection_embedding_mmarco-Arabic-mMiniLML-bi-encoder-NoKD-v1 features: - name: id dtype: string - name: text dtype: string - name: embedding list: float32 splits: - name: train num_bytes: 261357792 num_examples: 105201 download_size: 190222372 dataset_size: 261357792 configs: - config_name: STCALIR-Topics_embedding_mmarco-Arabic-AraDPR-bi-encoder-KD-v1 data_files: - split: train path: STCALIR-Topics_embedding_mmarco-Arabic-AraDPR-bi-encoder-KD-v1/train-* - config_name: STCALIR-Topics_embedding_mmarco-Arabic-AraDPR-bi-encoder-NoKD-v1 data_files: - split: train path: STCALIR-Topics_embedding_mmarco-Arabic-AraDPR-bi-encoder-NoKD-v1/train-* - config_name: STCALIR-Topics_embedding_mmarco-Arabic-AraElectra-bi-encoder-KD-v1 data_files: - split: train path: STCALIR-Topics_embedding_mmarco-Arabic-AraElectra-bi-encoder-KD-v1/train-* - config_name: STCALIR-Topics_embedding_mmarco-Arabic-AraElectra-bi-encoder-NoKD-v1 data_files: - split: train path: STCALIR-Topics_embedding_mmarco-Arabic-AraElectra-bi-encoder-NoKD-v1/train-* - config_name: STCALIR-Topics_embedding_mmarco-Arabic-mMiniLML-bi-encoder-KD-v1 data_files: - split: train path: STCALIR-Topics_embedding_mmarco-Arabic-mMiniLML-bi-encoder-KD-v1/train-* - config_name: STCALIR-Topics_embedding_mmarco-Arabic-mMiniLML-bi-encoder-NoKD-v1 data_files: - split: train path: STCALIR-Topics_embedding_mmarco-Arabic-mMiniLML-bi-encoder-NoKD-v1/train-* - config_name: STCALIR_collection_embedding_mmarco-Arabic-AraDPR-bi-encoder-KD-v1 data_files: - split: train path: STCALIR_collection_embedding_mmarco-Arabic-AraDPR-bi-encoder-KD-v1/train-* - config_name: STCALIR_collection_embedding_mmarco-Arabic-AraDPR-bi-encoder-NoKD-v1 data_files: - split: train path: STCALIR_collection_embedding_mmarco-Arabic-AraDPR-bi-encoder-NoKD-v1/train-* - config_name: STCALIR_collection_embedding_mmarco-Arabic-AraElectra-bi-encoder-KD-v1 data_files: - split: train path: STCALIR_collection_embedding_mmarco-Arabic-AraElectra-bi-encoder-KD-v1/train-* - config_name: STCALIR_collection_embedding_mmarco-Arabic-AraElectra-bi-encoder-NoKD-v1 data_files: - split: train path: STCALIR_collection_embedding_mmarco-Arabic-AraElectra-bi-encoder-NoKD-v1/train-* - config_name: STCALIR_collection_embedding_mmarco-Arabic-mMiniLML-bi-encoder-KD-v1 data_files: - split: train path: STCALIR_collection_embedding_mmarco-Arabic-mMiniLML-bi-encoder-KD-v1/train-* - config_name: STCALIR_collection_embedding_mmarco-Arabic-mMiniLML-bi-encoder-NoKD-v1 data_files: - split: train path: STCALIR_collection_embedding_mmarco-Arabic-mMiniLML-bi-encoder-NoKD-v1/train-* ---
提供机构:
hatemestinbejaia
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作