| #401 |
tokenized |
active |
1.3M
|
megatron idx |
27.0 GB |
2026-07-22 13:41 |
/capstor/store/cscs/swissai/infra01/audio-datasets/Apertus1p5_sft_tokenized/8B |
| #465 |
tokenized |
active |
51.4M
|
megatron idx |
444.0 GB |
2026-07-22 13:45 |
/capstor/store/cscs/swissai/infra01/audio-datasets/Apertus1p5_stage1_tokenized/MERGED |
| #165 |
tokenized |
active |
54.6M
|
megatron idx |
450.1 GB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/audio-datasets/Apertus1p5_stage1_tokenized_norm |
| #848 |
tokenized |
active |
150.1M
|
megatron idx |
355.0 GB |
2026-07-22 14:13 |
/capstor/store/cscs/swissai/infra01/audio-datasets/Apertus1p5_stage2_tokenized/8B |
| #395 |
tokenized |
active |
63.3M
|
megatron idx |
146.8 GB |
2026-07-22 13:41 |
/capstor/store/cscs/swissai/infra01/audio-datasets/Apertus1p5_stage2_tokenized/MERGED_0.1_36B |
| #755 |
shar |
active |
2.0M
|
shar summary |
418.7 GB |
2026-07-22 14:08 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/archive/emilia_yodas_isolated |
| #296 |
shar |
active |
43.6M
|
shar cuts |
24.3 TB |
2026-07-22 13:37 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/archive/voxpopuli_ast |
| #795 |
shar |
active |
14.6M
|
shar cuts |
879.7 GB |
2026-07-22 14:10 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/archive/wenetspeech_24k |
| #536 |
shar |
active |
101.2K
|
shar summary |
4.5 GB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/cooldown/ami_ihm |
| #333 |
shar |
active |
4.3M
|
shar summary |
333.2 GB |
2026-07-22 13:38 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/cooldown/aozora_hurigana |
| #415 |
shar |
active |
416.7K
|
shar summary |
316.9 GB |
2026-07-22 13:42 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/cooldown/ccpodcasts |
| #727 |
shar |
active |
11.9M
|
shar summary |
1.3 TB |
2026-07-22 13:58 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/cooldown/commonvoice25_train_extra |
| #240 |
shar |
active |
372.6K
|
shar summary |
36.7 GB |
2026-07-22 13:35 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/cooldown/farsi_asr_radio |
| #681 |
shar |
active |
406.0K
|
shar summary |
60.6 GB |
2026-07-22 13:56 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/cooldown/ghana_english_speech |
| #869 |
shar |
active |
315.4K
|
shar summary |
30.4 GB |
2026-07-22 14:14 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/cooldown/infore2_audiobooks_train |
| #411 |
shar |
active |
846.9K
|
shar summary |
419.8 GB |
2026-07-22 13:42 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/cooldown/localized_narratives |
| #541 |
shar |
active |
34.1K
|
shar summary |
9.3 GB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/cooldown/multimed_train |
| #751 |
shar |
active |
10.0K
|
shar summary |
2.9 GB |
2026-07-22 14:04 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/cooldown/openslr108_mediaspeech |
| #511 |
shar |
active |
54.5K
|
shar summary |
6.5 GB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/cooldown/russian_librispeech |
| #569 |
shar |
active |
401.5K
|
shar summary |
228.1 GB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/cooldown/slopalspeech |
| #400 |
shar |
active |
286.7K
|
shar summary |
162.8 GB |
2026-07-22 13:41 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/cooldown/tonewebinars |
| #282 |
shar |
active |
55.2K
|
shar summary |
10.2 GB |
2026-07-22 13:36 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/cooldown/tuda_de_train |
| #317 |
shar |
active |
1.0M
|
shar summary |
92.3 GB |
2026-07-22 13:38 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/cooldown/vietspeech |
| #815 |
shar |
active |
0
|
shar summary |
299.2 GB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/internal-only/srg_apertus |
| #104 |
shar |
active |
10.5K
|
shar summary |
2.2 GB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/sft/audiomcq_speech_audio |
| #324 |
shar |
active |
75.9K
|
shar summary |
7.0 GB |
2026-07-22 13:38 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/sft/heysquad_human_audio |
| #832 |
shar |
active |
98.2K
|
shar summary |
7.1 GB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/sft/heysquad_machine_audio |
| #475 |
shar |
active |
50.2K
|
shar summary |
636.3 GB |
2026-07-22 13:45 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/sft/marco_longspeech_sft_audio |
| #37 |
shar |
active |
58.4K
|
shar summary |
16.9 GB |
2026-07-22 13:22 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/sft/tcm_shizhengpt_speech_audio |
| #657 |
shar |
active |
13.4K
|
shar summary |
16.1 GB |
2026-07-22 13:52 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/sft/teleantifraud_matching_sft_audio |
| #297 |
shar |
active |
984.7K
|
shar summary |
279.2 GB |
2026-07-22 13:37 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/sft/vocalized_sft_audio |
| #450 |
shar |
active |
463.6K
|
shar summary |
47.5 GB |
2026-07-22 13:44 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/sft/voiceassistant_400k_audio |
| #493 |
shar |
active |
18.6K
|
shar summary |
5.8 GB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_1_rebuild/audioset_balanced |
| #590 |
shar |
active |
1.7M
|
shar summary |
548.5 GB |
2026-07-22 13:48 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_1_rebuild/audioset_unbalanced |
| #65 |
shar |
active |
5.0M
|
shar summary |
488.2 GB |
2026-07-22 13:26 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_1_rebuild/commonvoice25_other |
| #592 |
shar |
active |
72.4K
|
shar summary |
152.3 GB |
2026-07-22 13:48 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_1_rebuild/gemeinderat |
| #438 |
shar |
active |
50.0K
|
shar summary |
418.3 GB |
2026-07-22 13:43 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_1_rebuild/mtg_jamendo_train |
| #392 |
shar |
active |
355.0K
|
shar summary |
2.2 TB |
2026-07-22 13:41 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_1_rebuild/suno_s1_shar_rmsdb_v1 |
| #798 |
shar |
active |
15.9M
|
shar cuts |
33.6 TB |
2026-07-22 14:11 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_1_rebuild/ups_all_lang_shar_v3 |
| #476 |
shar |
active |
31.8M
|
shar cuts |
28.7 TB |
2026-07-22 13:45 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_1_rebuild/voxpopuli_shar_v2 |
| #554 |
shar |
active |
285.2K
|
shar cuts |
21.4 GB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/aishell |
| #396 |
shar |
active |
290.0K
|
shar cuts |
30.8 GB |
2026-07-22 13:41 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/allo_ava |
| #784 |
shar |
active |
5.4M
|
shar cuts |
618.4 GB |
2026-07-22 14:10 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/commonvoice |
| #477 |
shar |
active |
22.7K
|
shar summary |
1.6 GB |
2026-07-22 13:45 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/coral_v3_conversation_train |
| #662 |
shar |
active |
295.2K
|
shar summary |
44.1 GB |
2026-07-22 13:52 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/coral_v3_read_aloud_train |
| #599 |
shar |
active |
3.5M
|
shar cuts |
1.2 TB |
2026-07-22 13:48 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/eurospeech |
| #121 |
shar |
active |
14.3K
|
shar summary |
3.4 GB |
2026-07-22 13:28 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/f1_team_radio_train |
| #142 |
shar |
active |
8.2M
|
shar cuts |
768.3 GB |
2026-07-22 13:30 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/gigaspeech |
| #389 |
shar |
active |
27.5M
|
shar cuts |
2.5 TB |
2026-07-22 13:41 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/gigaspeech2 |
| #674 |
shar |
active |
78.2M
|
shar cuts |
14.8 TB |
2026-07-22 13:55 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/granary_yodas_interleave |
| #871 |
shar |
active |
1.2M
|
shar cuts |
324.0 GB |
2026-07-22 14:14 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/granary_ytc |
| #105 |
shar |
active |
2.4M
|
shar cuts |
708.7 GB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/granary_ytc_asr |
| #467 |
shar |
active |
1.2M
|
shar cuts |
393.1 GB |
2026-07-22 13:45 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/granary_ytc_ast |
| #621 |
shar |
active |
96.6K
|
shar cuts |
24.3 GB |
2026-07-22 13:49 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/hui_audio_corpus_german_clean |
| #25 |
shar |
active |
32.4M
|
shar cuts |
7.0 TB |
2026-07-22 13:21 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/interleave/granary_yodas_ast |
| #733 |
shar |
active |
776.0K
|
shar cuts |
100.3 GB |
2026-07-22 13:58 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/kathbath_v2 |
| #579 |
shar |
active |
230.8K
|
shar summary |
35.4 GB |
2026-07-22 13:48 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/kazakh_speech_train |
| #303 |
shar |
active |
8.7M
|
shar summary |
1.9 TB |
2026-07-22 13:37 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/legco_speech_train_v2 |
| #572 |
shar |
active |
11.2M
|
shar cuts |
4.0 TB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/libriheavy_large |
| #617 |
shar |
active |
12.3M
|
shar cuts |
3.6 TB |
2026-07-22 13:49 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/mls |
| #17 |
shar |
active |
1.4M
|
shar cuts |
431.9 GB |
2026-07-22 13:21 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/mls_v2 |
| #730 |
shar |
active |
38.3K
|
shar cuts |
2.9 GB |
2026-07-22 13:58 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/mrsaudio_dialogue |
| #721 |
shar |
active |
112.5K
|
shar cuts |
13.6 GB |
2026-07-22 13:58 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/mrsaudio_speech |
| #496 |
shar |
active |
151.6K
|
shar summary |
19.8 GB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/multidialog_train |
| #381 |
shar |
active |
48.4K
|
shar cuts |
12.9 GB |
2026-07-22 13:41 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/multimed |
| #292 |
shar |
active |
7.5K
|
shar cuts |
1.5 GB |
2026-07-22 13:37 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/nb_tale_all |
| #700 |
shar |
active |
184.1K
|
shar summary |
178.0 GB |
2026-07-22 13:57 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/omnilingual_asr |
| #236 |
shar |
active |
246.7K
|
shar cuts |
42.1 GB |
2026-07-22 13:35 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/parlament_parla |
| #74 |
shar |
active |
277.8K
|
shar summary |
69.8 GB |
2026-07-22 13:26 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/parlaspeech_rs_train |
| #508 |
shar |
active |
5.2M
|
shar summary |
1.6 TB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/peoples_speech_train_v2 |
| #640 |
shar |
active |
17.2K
|
shar summary |
5.1 GB |
2026-07-22 13:50 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/podcast_fillers |
| #595 |
shar |
active |
3.0M
|
shar cuts |
634.3 GB |
2026-07-22 13:48 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/seamless_align |
| #671 |
shar |
active |
131.0K
|
shar summary |
31.2 GB |
2026-07-22 13:54 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/spc_r_segmented |
| #482 |
shar |
active |
22.7K
|
shar cuts |
1.9 GB |
2026-07-22 13:45 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/thorsten_de |
| #169 |
shar |
active |
32.4M
|
shar cuts |
7.0 TB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/translate/granary_yodas_ast |
| #254 |
shar |
active |
3.0M
|
shar cuts |
634.2 GB |
2026-07-22 13:36 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/translate/seamless_align |
| #724 |
shar |
active |
11.8K
|
shar summary |
2.3 GB |
2026-07-22 13:58 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/vimedcss_train |
| #449 |
shar |
active |
46.7M
|
shar cuts |
26.1 TB |
2026-07-22 13:43 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/voxpopuli_asr |
| #564 |
shar |
active |
3.1M
|
shar cuts |
1.7 TB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/voxpopuli_ast_sampled |
| #118 |
shar |
active |
71.1K
|
shar summary |
9.5 GB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/wavepulse_radio_train |
| #775 |
shar |
active |
14.6M
|
shar cuts |
1.5 GB |
2026-07-22 14:09 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/wenetspeech |
| #158 |
shar |
active |
22.3K
|
shar summary |
3.3 GB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/zeroth_korean_train |
| #82 |
shar |
active |
21.9K
|
shar summary |
3.2 GB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/zeroth_korean_train_v2 |
| #680 |
shar |
active |
116.6K
|
shar summary |
16.8 GB |
2026-07-22 13:56 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/zoengjyutgaai_train |
| #403 |
shar |
active |
9.6K
|
shar cuts |
5.5 GB |
2026-07-22 13:41 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR_TODO/annotate/mrsaudio_music |
| #376 |
shar |
active |
5.8K
|
shar cuts |
3.4 GB |
2026-07-22 13:41 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR_TODO/annotate/mrsaudio_sing |
| #726 |
shar |
active |
177.0K
|
shar cuts |
48.9 GB |
2026-07-22 13:58 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR_TODO/annotate/vggsound |
| #720 |
shar |
active |
135.6K
|
shar cuts |
10.8 GB |
2026-07-22 13:58 |
/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR_TODO/transcribe |
| #847 |
hf_arrow |
active |
n/a
|
|
26.5 MB |
2026-07-22 14:13 |
/capstor/store/cscs/swissai/infra01/audio-datasets/TTS/swiss-german-instruct-data-dialects-with-translation-instructions-v2 |
| #35 |
parquet |
active |
10.1K
|
parquet footer |
2.1 GB |
2026-07-22 13:22 |
/capstor/store/cscs/swissai/infra01/audio-datasets/benchmark/hf___bosonai___WildASR |
| #510 |
media |
active |
30.9K
|
file count |
10.2 GB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/audio-datasets/benchmark/swissdial_v1_1 |
| #624 |
webdataset |
active |
n/a
|
|
2.1 TB |
2026-07-22 13:49 |
/capstor/store/cscs/swissai/infra01/audio-datasets/emilia_separated/Emilia-YODAS |
| #603 |
hf_arrow |
active |
137.9K
|
hf meta |
96.4 GB |
2026-07-22 13:48 |
/capstor/store/cscs/swissai/infra01/audio-datasets/librispeech_asr |
| #130 |
shar |
active |
109.0K
|
shar summary |
629.0 GB |
2026-07-22 13:28 |
/capstor/store/cscs/swissai/infra01/audio-datasets/music_caption_shar/suno_s2_shar |
| #637 |
parquet |
active |
19.1M
|
parquet footer |
599.7 GB |
2026-07-22 13:50 |
/capstor/store/cscs/swissai/infra01/audio-datasets/processed/commonvoice25 |
| #22 |
parquet |
active |
869.0K
|
parquet footer |
184.7 GB |
2026-07-22 13:21 |
/capstor/store/cscs/swissai/infra01/audio-datasets/processed/localized_narratives |
| #183 |
parquet |
active |
869.0K
|
parquet footer |
183.7 GB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/audio-datasets/processed/localized_narratives_qwen |
| #249 |
parquet |
active |
34.1K
|
parquet footer |
3.3 GB |
2026-07-22 13:35 |
/capstor/store/cscs/swissai/infra01/audio-datasets/processed/multimed |
| #743 |
parquet |
active |
10.0K
|
parquet footer |
2.4 GB |
2026-07-22 13:58 |
/capstor/store/cscs/swissai/infra01/audio-datasets/processed/openslr108_mediaspeech |
| #856 |
parquet |
active |
3.1M
|
parquet footer |
1.3 TB |
2026-07-22 14:13 |
/capstor/store/cscs/swissai/infra01/audio-datasets/processed/sft |
| #98 |
parquet |
active |
401.5K
|
parquet footer |
60.5 GB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/audio-datasets/processed/slopalspeech_no_overlap |
| #874 |
hf_arrow |
active |
n/a
|
|
2.5 TB |
2026-07-22 14:14 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw(processed)/peoples_speech_final |
| #76 |
webdataset |
active |
n/a
|
|
2.1 TB |
2026-07-22 13:26 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/Emilia-YODAS |
| #399 |
webdataset |
active |
n/a
|
|
35.0 GB |
2026-07-22 13:41 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/Gemeinderat |
| #377 |
hf_arrow |
active |
n/a
|
|
1.9 TB |
2026-07-22 13:41 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/MLCommons___peoples_speech |
| #175 |
webdataset |
active |
n/a
|
|
31.2 GB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/aishell/aishell1 |
| #719 |
manual |
active |
n/a
|
|
51.5 GB |
2026-07-22 13:58 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/aishell/aishell3 |
| #728 |
webdataset |
active |
n/a
|
|
103.9 GB |
2026-07-22 13:58 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/aishell/aishell4 |
| #633 |
parquet |
active |
108.5K
|
parquet footer |
12.4 GB |
2026-07-22 13:50 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/ami/ihm |
| #432 |
parquet |
active |
107.3K
|
parquet footer |
11.1 GB |
2026-07-22 13:43 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/ami/sdm |
| #437 |
hf_arrow |
active |
n/a
|
|
35.7 GB |
2026-07-22 13:43 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/audiocite/audiocite_processed |
| #159 |
media |
active |
996
|
file count |
18.1 GB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/audiocite/wavs_cc_by |
| #461 |
media |
active |
418.9K
|
file count |
1.8 TB |
2026-07-22 13:45 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/ccpodcasts |
| #235 |
parquet |
active |
416.8K
|
parquet footer |
1.6 TB |
2026-07-22 13:35 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/ccpodcasts_parquet |
| #749 |
webdataset |
active |
n/a
|
|
304.9 GB |
2026-07-22 14:03 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/commonvoice24 |
| #23 |
parquet |
active |
157.6K
|
parquet footer |
39.6 GB |
2026-07-22 13:21 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/coral_v3/conversation |
| #666 |
parquet |
active |
310.4K
|
parquet footer |
171.5 GB |
2026-07-22 13:54 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/coral_v3/read_aloud |
| #507 |
parquet |
active |
315.4K
|
parquet footer |
46.6 GB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/doof-ferb___infore2_audiobooks |
| #491 |
webdataset |
active |
n/a
|
|
33.7 TB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/granary/voxpopuli-granary |
| #644 |
parquet |
active |
78.3M
|
parquet footer |
21.5 TB |
2026-07-22 13:50 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/granary/yodas-granary |
| #40 |
webdataset |
active |
n/a
|
|
1.1 TB |
2026-07-22 13:22 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/granary/ytc-granary |
| #543 |
parquet |
active |
116.6K
|
parquet footer |
6.7 GB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___CanCLID___zoengjyutgaai |
| #219 |
media |
active |
303.2K
|
file count |
2.0 TB |
2026-07-22 13:34 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___MRSAudio___MRSAudio |
| #94 |
parquet |
active |
14.7K
|
parquet footer |
2.6 GB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___MikCil___f1-team-radio |
| #504 |
parquet |
active |
52.9K
|
parquet footer |
7.2 GB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___NeurologyAI___neuro-parakeet-food |
| #38 |
parquet |
active |
1.0M
|
parquet footer |
130.5 GB |
2026-07-22 13:22 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___NhutP___VietSpeech |
| #791 |
webdataset |
active |
n/a
|
|
1.1 TB |
2026-07-22 14:10 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___TTS-AGI___majestrino-unified-detailed-captions |
| #498 |
parquet |
active |
308.4K
|
parquet footer |
688.4 GB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___Vikhrmodels___ToneWebinars |
| #857 |
hf_arrow |
active |
n/a
|
|
2.5 TB |
2026-07-22 14:13 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___agkphysics___audio_set |
| #643 |
parquet |
active |
805.7K
|
parquet footer |
174.0 GB |
2026-07-22 13:50 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___ai4bharat___Kathbath |
| #423 |
parquet |
active |
3.0M
|
parquet footer |
808.7 GB |
2026-07-22 13:42 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___ai4bharat___SeamlessAlign |
| #225 |
parquet |
active |
250.6K
|
parquet footer |
89.2 GB |
2026-07-22 13:35 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___alakxender___dhivehi-audios-82-spk |
| #462 |
media |
active |
1.3K
|
file count |
229.6 GB |
2026-07-22 13:45 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___avalab___Allo-AVA |
| #350 |
parquet |
active |
277.8K
|
parquet footer |
57.7 GB |
2026-07-22 13:39 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___classla___ParlaSpeech-RS |
| #342 |
parquet |
active |
3.5M
|
parquet footer |
1.6 TB |
2026-07-22 13:39 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___disco-eth___EuroSpeech |
| #483 |
webdataset |
active |
n/a
|
|
60.3 TB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___espnet___yodas2 |
| #428 |
parquet |
active |
1.4M
|
parquet footer |
94.2 GB |
2026-07-22 13:43 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___facebook___multilingual_librispeech |
| #797 |
parquet |
active |
273.8K
|
parquet footer |
491.5 GB |
2026-07-22 14:11 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___facebook___omnilingual-asr-corpus |
| #10 |
manual |
active |
n/a
|
|
182.6 GB |
2026-07-22 13:20 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___farsi-asr___farsi-asr-dataset |
| #607 |
parquet |
active |
406.1K
|
parquet footer |
105.2 GB |
2026-07-22 13:49 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___ghananlpcommunity___ghana-english-speech-600hrs |
| #562 |
parquet |
active |
20.8K
|
parquet footer |
15.9 GB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___hostbot77___news_youtube_uzbek_speech_dataset |
| #774 |
parquet |
active |
552.7K
|
parquet footer |
818.7 GB |
2026-07-22 14:09 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___i4ds___SRG_apertus_data |
| #332 |
parquet |
active |
57.2K
|
parquet footer |
11.2 GB |
2026-07-22 13:38 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___istupakov___russian_librispeech |
| #3 |
webdataset |
active |
n/a
|
|
6.8 GB |
2026-07-22 13:20 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___language-and-voice-lab___samromur_children |
| #151 |
webdataset |
active |
n/a
|
|
49.9 GB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___language-and-voice-lab___samromur_milljon |
| #48 |
parquet |
active |
21.7K
|
parquet footer |
5.7 GB |
2026-07-22 13:24 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___linagora___linto-dataset-audio-ar-tn |
| #799 |
parquet |
active |
11.2M
|
parquet footer |
1.3 TB |
2026-07-22 14:11 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___mythicinfinity___libriheavy |
| #168 |
hf_arrow |
active |
n/a
|
|
101.4 GB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___mythicinfinity___libritts |
| #697 |
parquet |
active |
565.1M
|
parquet footer |
44.9 GB |
2026-07-22 13:57 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___nyu-dice-lab___wavepulse-radio-raw-transcripts |
| #691 |
hf_arrow |
active |
n/a
|
|
70.4 GB |
2026-07-22 13:56 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___openslr___librispeech_asr |
| #345 |
webdataset |
active |
n/a
|
|
19.4 GB |
2026-07-22 13:39 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___otoearth___otoSpeech-full-duplex-processed-141h |
| #188 |
webdataset |
active |
n/a
|
|
318.6 GB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___projecte-aina___parlament_parla_v3 |
| #597 |
parquet |
active |
52.3K
|
parquet footer |
632.1 MB |
2026-07-22 13:48 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___rchiera___podcast-transcripts |
| #207 |
shar |
active |
240.0K
|
shar cuts |
625.7 GB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___rchiera___podcast-transcripts___downloaded |
| #330 |
hf_arrow |
active |
n/a
|
|
3.5 GB |
2026-07-22 13:38 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___renumics___song-describer-dataset |
| #67 |
parquet |
active |
8.3M
|
parquet footer |
1.2 TB |
2026-07-22 13:26 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___speechcolab___gigaspeech |
| #663 |
webdataset |
active |
n/a
|
|
3.1 TB |
2026-07-22 13:52 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___speechcolab___gigaspeech2 |
| #32 |
media |
active |
103.7K
|
file count |
709.9 GB |
2026-07-22 13:21 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___trentmkelly___police-scanner-audio |
| #361 |
hf_arrow |
active |
n/a
|
|
16.8 GB |
2026-07-22 13:40 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___uhhlt___Tuda-De |
| #229 |
parquet |
active |
206
|
parquet footer |
17.2 GB |
2026-07-22 13:35 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___united-nations___transcription-corpus |
| #530 |
parquet |
active |
76.1K
|
parquet footer |
14.6 GB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___yijingwu___HeySQuAD_human |
| #116 |
parquet |
active |
98.2K
|
parquet footer |
10.4 GB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___yijingwu___HeySQuAD_machine |
| #709 |
parquet |
active |
35.9K
|
parquet footer |
2.9 GB |
2026-07-22 13:57 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hf___ylacombe___podcast_fillers_processed |
| #868 |
manual |
active |
n/a
|
|
144.0 GB |
2026-07-22 14:14 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/hui-audio-corpus-german |
| #806 |
media |
active |
51.0K
|
file count |
16.6 GB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/javisdata-audios/audio/AudioCaps |
| #200 |
media |
active |
18.7K
|
file count |
3.9 GB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/javisdata-audios/audio/AudioSet |
| #638 |
manual |
active |
n/a
|
|
3.3 GB |
2026-07-22 13:50 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/javisdata-audios/audio/Clotho |
| #685 |
media |
active |
2.0K
|
file count |
322.1 MB |
2026-07-22 13:56 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/javisdata-audios/audio/ESC50 |
| #739 |
media |
active |
2.0K
|
file count |
1.0 GB |
2026-07-22 13:58 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/javisdata-audios/audio/GTZAN |
| #821 |
media |
active |
3.9K
|
file count |
1.3 GB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/javisdata-audios/audio/MACS |
| #186 |
media |
active |
136.2K
|
file count |
97.7 GB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/javisdata-audios/audio/MMTrail |
| #677 |
media |
active |
2.7K
|
file count |
4.5 GB |
2026-07-22 13:56 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/javisdata-audios/audio/MusicInstrument |
| #255 |
media |
active |
8.7K
|
file count |
1.0 GB |
2026-07-22 13:36 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/javisdata-audios/audio/UrbanSound8K |
| #221 |
media |
active |
198.0K
|
file count |
116.8 GB |
2026-07-22 13:35 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/javisdata-audios/audio/VGGSound |
| #120 |
media |
active |
380.7K
|
file count |
116.2 GB |
2026-07-22 13:28 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/javisdata-audios/audio/WavCaps |
| #515 |
archive |
active |
n/a
|
|
311.5 GB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/javisdata-audios/audio_zips |
| #861 |
webdataset |
active |
n/a
|
|
589.2 GB |
2026-07-22 14:14 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/jhu-clsp___seamless-align |
| #136 |
parquet |
active |
22.7K
|
parquet footer |
2.9 GB |
2026-07-22 13:28 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/kresnik___zeroth_korean |
| #375 |
parquet |
active |
9.6M
|
parquet footer |
939.3 GB |
2026-07-22 13:40 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/legco-speech/segmented |
| #473 |
webdataset |
active |
n/a
|
|
124.6 GB |
2026-07-22 13:45 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/ml-spoken-words |
| #598 |
webdataset |
active |
n/a
|
|
117.5 GB |
2026-07-22 13:48 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/mtg-jamendo |
| #425 |
parquet |
active |
1.6K
|
parquet footer |
227.6 MB |
2026-07-22 13:42 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/multimed/Chinese |
| #734 |
parquet |
active |
33.1K
|
parquet footer |
3.6 GB |
2026-07-22 13:58 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/multimed/English |
| #394 |
parquet |
active |
1.8K
|
parquet footer |
216.1 MB |
2026-07-22 13:41 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/multimed/French |
| #492 |
parquet |
active |
2.8K
|
parquet footer |
354.5 MB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/multimed/German |
| #512 |
parquet |
active |
9.1K
|
parquet footer |
182.0 MB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/multimed/Vietnamese |
| #630 |
media |
active |
4.8K
|
file count |
3.7 GB |
2026-07-22 13:50 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/nb-tale/part_1 |
| #555 |
media |
active |
2.7K
|
file count |
2.5 GB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/nb-tale/part_2 |
| #334 |
media |
active |
365
|
file count |
4.4 GB |
2026-07-22 13:38 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/nb-tale/part_3 |
| #813 |
parquet |
active |
4.3M
|
parquet footer |
147.9 GB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/ndl___aozora_hurigana_speech_v2 |
| #702 |
manual |
active |
n/a
|
|
5.0 GB |
2026-07-22 13:57 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/openslr108___mediaspeech |
| #71 |
hf_arrow |
active |
n/a
|
|
2.4 TB |
2026-07-22 13:26 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/people_speech_dirty_recap |
| #412 |
parquet |
active |
470.1K
|
parquet footer |
219.5 GB |
2026-07-22 13:42 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/sft/VoiceAssistant-400K |
| #703 |
webdataset |
active |
n/a
|
|
2.3 TB |
2026-07-22 13:57 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/sft/audio-flan/audio_files |
| #520 |
webdataset |
active |
n/a
|
|
26.4 GB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/sft/hf___IVLLab___MultiDialog |
| #220 |
parquet |
active |
4.4K
|
parquet footer |
12.7 GB |
2026-07-22 13:34 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/sft/hf___JimmyMa99___TeleAntiFraud |
| #849 |
webdataset |
active |
n/a
|
|
249.6 GB |
2026-07-22 14:13 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/sft/hf___KurtDu___EchoX-Dialogues-Plus |
| #311 |
parquet |
active |
15.2M
|
parquet footer |
3.0 TB |
2026-07-22 13:38 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/sft/hf___MERaLiON___Multitask-National-Speech-Corpus-v1 |
| #326 |
webdataset |
active |
n/a
|
|
1.7 TB |
2026-07-22 13:38 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/sft/hf___shenyunhang___AudioQA-1M |
| #456 |
manual |
active |
n/a
|
|
209.3 GB |
2026-07-22 13:44 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/sft/hf___tutu0604___UltraVoice |
| #261 |
parquet |
active |
138.9K
|
parquet footer |
30.4 GB |
2026-07-22 13:36 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/spc-r-segmented |
| #664 |
parquet |
active |
659.8K
|
parquet footer |
256.5 MB |
2026-07-22 13:52 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/suno/parquet |
| #368 |
webdataset |
active |
n/a
|
|
1.5 TB |
2026-07-22 13:40 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/suno/shards_s1 |
| #505 |
webdataset |
active |
n/a
|
|
446.9 GB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/suno/shards_s2 |
| #191 |
parquet |
active |
15.8K
|
parquet footer |
18.3 GB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/tensorxt___ViMedCSS |
| #420 |
webdataset |
active |
n/a
|
|
16.6 TB |
2026-07-22 13:42 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/unsupervised_peoples_speech_commercial_wds/audio |
| #785 |
webdataset |
active |
n/a
|
|
23.9 TB |
2026-07-22 14:10 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/unsupervised_peoples_speech_commercial_wds/audio2 |
| #426 |
media |
active |
390.6K
|
file count |
6.9 TB |
2026-07-22 13:43 |
/capstor/store/cscs/swissai/infra01/audio-datasets/raw/voxpopuli |
| #827 |
shar |
active |
1.0M
|
shar cuts |
130.4 GB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/real |
| #321 |
shar |
active |
121.4K
|
shar summary |
11.7 GB |
2026-07-22 13:38 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/pl_cv25_K50 |
| #880 |
shar |
active |
91.4K
|
shar summary |
9.9 GB |
2026-07-22 14:14 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/pl_cv25_spk1636 |
| #369 |
shar |
active |
4.6M
|
shar summary |
913.5 GB |
2026-07-22 13:40 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/pl_fineweb2_10kh_K50 |
| #149 |
shar |
active |
4.5M
|
shar summary |
936.0 GB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/pl_fineweb2_10kh_b_K50 |
| #209 |
shar |
active |
3.2K
|
shar summary |
600.1 MB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/pl_granary_yodas_spk1636 |
| #107 |
shar |
active |
2.9K
|
shar summary |
850.0 MB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/pl_granary_ytc_K50 |
| #161 |
shar |
active |
2.6K
|
shar summary |
812.5 MB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/pl_granary_ytc_spk1636 |
| #810 |
shar |
active |
21.9K
|
shar summary |
8.5 GB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/pl_mls_spk1636 |
| #522 |
shar |
active |
25.0K
|
shar summary |
9.5 GB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/pl_mls_v2_K50 |
| #818 |
shar |
active |
164.6K
|
shar summary |
80.4 GB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/pl_voxpopuli_1kh_spk1636 |
| #20 |
shar |
active |
2.0M
|
shar summary |
994.4 GB |
2026-07-22 13:21 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/pl_voxpopuli_full_K50 |
| #316 |
shar |
active |
2.3M
|
shar summary |
1.1 TB |
2026-07-22 13:38 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/pl_voxpopuli_rest_spk1636 |
| #735 |
shar |
active |
487.3K
|
shar summary |
53.9 GB |
2026-07-22 13:58 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/pl_yodas2_K50 |
| #308 |
shar |
active |
490.4K
|
shar summary |
55.8 GB |
2026-07-22 13:38 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/pl_yodas2_spk1636 |
| #581 |
shar |
active |
120.1K
|
shar summary |
10.3 GB |
2026-07-22 13:48 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/zh_aishell1_K50 |
| #36 |
shar |
active |
119.9K
|
shar summary |
7.4 GB |
2026-07-22 13:22 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/zh_aishell1_spk0668 |
| #242 |
shar |
active |
63.3K
|
shar summary |
4.4 GB |
2026-07-22 13:35 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/zh_aishell3_K50 |
| #265 |
shar |
active |
63.2K
|
shar summary |
3.2 GB |
2026-07-22 13:36 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/zh_aishell3_spk0668 |
| #230 |
shar |
active |
10.6K
|
shar summary |
1.3 GB |
2026-07-22 13:35 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/zh_aishell4_L_K50 |
| #612 |
shar |
active |
8.6K
|
shar summary |
879.9 MB |
2026-07-22 13:49 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/zh_aishell4_L_spk0668 |
| #846 |
shar |
active |
42.1K
|
shar summary |
4.4 GB |
2026-07-22 14:13 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/zh_aishell4_M_K50 |
| #647 |
shar |
active |
32.4K
|
shar summary |
3.0 GB |
2026-07-22 13:52 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/zh_aishell4_M_spk0668 |
| #886 |
shar |
active |
21.9K
|
shar summary |
2.3 GB |
2026-07-22 14:14 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/zh_aishell4_S_K50 |
| #514 |
shar |
active |
17.0K
|
shar summary |
1.6 GB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/zh_aishell4_S_spk0668 |
| #529 |
shar |
active |
167.0K
|
shar summary |
15.0 GB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/zh_cv25_K50 |
| #202 |
shar |
active |
167.0K
|
shar summary |
10.8 GB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/zh_cv25_spk0668 |
| #145 |
shar |
active |
110.1K
|
shar summary |
23.9 GB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/zh_emilia_full_K50 |
| #860 |
shar |
active |
110.0K
|
shar summary |
17.3 GB |
2026-07-22 14:14 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/zh_emilia_full_spk0668 |
| #623 |
shar |
active |
19.0K
|
shar summary |
2.3 GB |
2026-07-22 13:49 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/zh_emilia_spk0668 |
| #360 |
shar |
active |
4.1M
|
shar summary |
925.1 GB |
2026-07-22 13:40 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/zh_fineweb2_10kh_K50 |
| #363 |
shar |
active |
1.2M
|
shar summary |
311.6 GB |
2026-07-22 13:40 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/zh_fineweb2_10kh_b_K50 |
| #853 |
shar |
active |
1.0M
|
shar summary |
61.1 GB |
2026-07-22 14:13 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/zh_wenetspeech_1kh_spk0668 |
| #609 |
shar |
active |
13.3M
|
shar summary |
854.9 GB |
2026-07-22 13:49 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/zh_wenetspeech_full_K50 |
| #540 |
shar |
active |
6.3M
|
shar summary |
382.0 GB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/zh_wenetspeech_rest_spk0668 |
| #589 |
shar |
active |
250.2K
|
shar summary |
20.2 GB |
2026-07-22 13:48 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/zh_yodas2_K50 |
| #460 |
shar |
active |
250.1K
|
shar summary |
14.5 GB |
2026-07-22 13:44 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/SHAR/voxcpm2/zh_yodas2_spk0668 |
| #356 |
tokenized |
active |
43.2M
|
megatron idx |
55.2 GB |
2026-07-22 13:39 |
/capstor/store/cscs/swissai/infra01/audio-datasets/reality_gap/tokenized |
| #77 |
parquet |
active |
121.9K
|
parquet footer |
22.3 GB |
2026-07-22 13:26 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/pl_cv25_K50 |
| #642 |
parquet |
active |
91.4K
|
parquet footer |
19.0 GB |
2026-07-22 13:50 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/pl_cv25_spk1636 |
| #239 |
parquet |
active |
4.6M
|
parquet footer |
1.7 TB |
2026-07-22 13:35 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/pl_fineweb2_10kh_K50 |
| #549 |
parquet |
active |
4.5M
|
parquet footer |
1.7 TB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/pl_fineweb2_10kh_b_K50 |
| #778 |
parquet |
active |
3.2K
|
parquet footer |
1.1 GB |
2026-07-22 14:10 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/pl_granary_yodas_spk1636 |
| #302 |
parquet |
active |
2.9K
|
parquet footer |
1.6 GB |
2026-07-22 13:37 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/pl_granary_ytc_K50 |
| #767 |
parquet |
active |
2.6K
|
parquet footer |
1.5 GB |
2026-07-22 14:09 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/pl_granary_ytc_spk1636 |
| #884 |
parquet |
active |
21.9K
|
parquet footer |
15.6 GB |
2026-07-22 14:14 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/pl_mls_spk1636 |
| #494 |
parquet |
active |
25.0K
|
parquet footer |
18.1 GB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/pl_mls_v2_K50 |
| #180 |
parquet |
active |
164.6K
|
parquet footer |
146.5 GB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/pl_voxpopuli_1kh_spk1636 |
| #575 |
parquet |
active |
2.0M
|
parquet footer |
1.9 TB |
2026-07-22 13:48 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/pl_voxpopuli_full_K50 |
| #879 |
parquet |
active |
2.3M
|
parquet footer |
2.1 TB |
2026-07-22 14:14 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/pl_voxpopuli_rest_spk1636 |
| #526 |
parquet |
active |
491.0K
|
parquet footer |
103.4 GB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/pl_yodas2_K50 |
| #189 |
parquet |
active |
490.4K
|
parquet footer |
105.0 GB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/pl_yodas2_spk1636 |
| #585 |
parquet |
active |
120.1K
|
parquet footer |
21.5 GB |
2026-07-22 13:48 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/zh_aishell1_K50 |
| #552 |
parquet |
active |
119.9K
|
parquet footer |
19.2 GB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/zh_aishell1_spk0668 |
| #433 |
parquet |
active |
63.3K
|
parquet footer |
9.2 GB |
2026-07-22 13:43 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/zh_aishell3_K50 |
| #58 |
parquet |
active |
63.3K
|
parquet footer |
8.3 GB |
2026-07-22 13:25 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/zh_aishell3_spk0668 |
| #551 |
parquet |
active |
10.7K
|
parquet footer |
2.7 GB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/zh_aishell4_L_K50 |
| #56 |
parquet |
active |
8.6K
|
parquet footer |
2.4 GB |
2026-07-22 13:25 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/zh_aishell4_L_spk0668 |
| #348 |
parquet |
active |
42.3K
|
parquet footer |
9.5 GB |
2026-07-22 13:39 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/zh_aishell4_M_K50 |
| #70 |
parquet |
active |
32.5K
|
parquet footer |
8.2 GB |
2026-07-22 13:26 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/zh_aishell4_M_spk0668 |
| #648 |
parquet |
active |
22.0K
|
parquet footer |
4.9 GB |
2026-07-22 13:52 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/zh_aishell4_S_K50 |
| #641 |
parquet |
active |
17.0K
|
parquet footer |
4.3 GB |
2026-07-22 13:50 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/zh_aishell4_S_spk0668 |
| #135 |
parquet |
active |
167.0K
|
parquet footer |
31.8 GB |
2026-07-22 13:28 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/zh_cv25_K50 |
| #645 |
parquet |
active |
167.0K
|
parquet footer |
28.3 GB |
2026-07-22 13:52 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/zh_cv25_spk0668 |
| #881 |
parquet |
active |
110.2K
|
parquet footer |
51.3 GB |
2026-07-22 14:14 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/zh_emilia_full_K50 |
| #329 |
parquet |
active |
110.2K
|
parquet footer |
46.8 GB |
2026-07-22 13:38 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/zh_emilia_full_spk0668 |
| #170 |
parquet |
active |
19.1K
|
parquet footer |
6.2 GB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/zh_emilia_spk0668 |
| #752 |
parquet |
active |
4.1M
|
parquet footer |
2.0 TB |
2026-07-22 14:04 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/zh_fineweb2_10kh_K50 |
| #786 |
parquet |
active |
1.2M
|
parquet footer |
585.1 GB |
2026-07-22 14:10 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/zh_fineweb2_10kh_b_K50 |
| #651 |
parquet |
active |
1.0M
|
parquet footer |
162.5 GB |
2026-07-22 13:52 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/zh_wenetspeech_1kh_spk0668 |
| #54 |
parquet |
active |
13.3M
|
parquet footer |
1.8 TB |
2026-07-22 13:25 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/zh_wenetspeech_full_K50 |
| #406 |
parquet |
active |
6.3M
|
parquet footer |
1.0 TB |
2026-07-22 13:41 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/zh_wenetspeech_rest_spk0668 |
| #184 |
parquet |
active |
250.2K
|
parquet footer |
42.8 GB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/zh_yodas2_K50 |
| #102 |
parquet |
active |
250.2K
|
parquet footer |
38.1 GB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/audio-datasets/synthesized/voxcpm2/zh_yodas2_spk0668 |
| #248 |
tokenized |
active |
275.0K
|
megatron idx |
205.6 MB |
2026-07-22 13:35 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/archive/unfilted/aishell_1_3_direct_dur0-200 |
| #21 |
tokenized |
active |
10.1M
|
megatron idx |
9.9 GB |
2026-07-22 13:21 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/archive/unfilted/commonvoice_48lang_S2_dur3-200 |
| #100 |
tokenized |
active |
79.1K
|
megatron idx |
94.1 MB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/archive/unfilted/coral_v3_conversation_train_interleaved_dur0p1-200/indexed |
| #269 |
parquet |
active |
147.2K
|
parquet footer |
43.1 MB |
2026-07-22 13:36 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/archive/unfilted/coral_v3_conversation_train_interleaved_dur0p1-200/parquet |
| #34 |
tokenized |
active |
14.4K
|
megatron idx |
14.4 MB |
2026-07-22 13:22 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/archive/unfilted/coral_v3_conversation_train_interleaved_normalized_dur0p1-200/indexed |
| #649 |
tokenized |
active |
598.5K
|
megatron idx |
664.5 MB |
2026-07-22 13:52 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/archive/unfilted/coral_v3_read_aloud_train_direct_dur0p1-200 |
| #650 |
tokenized |
active |
23.9M
|
megatron idx |
69.0 GB |
2026-07-22 13:52 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/archive/unfilted/emilia_yodas_interleaved_dur2-200/indexed |
| #214 |
parquet |
active |
41.9M
|
parquet footer |
33.9 GB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/archive/unfilted/emilia_yodas_interleaved_dur2-200/parquet |
| #66 |
tokenized |
active |
4.1M
|
megatron idx |
6.1 GB |
2026-07-22 13:26 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/archive/unfilted/emilia_yodas_isolated_dur2-30 |
| #535 |
tokenized |
active |
3.4M
|
megatron idx |
9.0 GB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/archive/unfilted/eurospeech_permissive_direct_dur0p1-200 |
| #172 |
tokenized |
active |
19.0M
|
megatron idx |
15.9 GB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/archive/unfilted/gigaspeech2_th_id_vi_direct_dur2-200 |
| #452 |
tokenized |
active |
193.1K
|
megatron idx |
322.8 MB |
2026-07-22 13:44 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/archive/unfilted/hui_audio_corpus_german_clean_dur0-200 |
| #93 |
tokenized |
active |
4.8M
|
megatron idx |
14.3 GB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/archive/unfilted/legco_speech_train_interleaved_dur0p1-200/indexed |
| #463 |
parquet |
active |
9.6M
|
parquet footer |
6.4 GB |
2026-07-22 13:45 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/archive/unfilted/legco_speech_train_interleaved_dur0p1-200/parquet |
| #320 |
tokenized |
active |
24.5M
|
megatron idx |
63.3 GB |
2026-07-22 13:38 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/archive/unfilted/mls_8lang_direct_dur0-200 |
| #862 |
tokenized |
active |
4.8M
|
megatron idx |
16.8 GB |
2026-07-22 14:14 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/archive/unfilted/peoples_speech_train_interleaved_dur0p1-200/indexed |
| #706 |
parquet |
active |
6.8M
|
parquet footer |
7.9 GB |
2026-07-22 13:57 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/archive/unfilted/peoples_speech_train_interleaved_dur0p1-200/parquet |
| #414 |
parquet |
active |
127.3K
|
parquet footer |
132.7 MB |
2026-07-22 13:42 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/archive/unfilted/spc_r_interleaved_dur2-200 |
| #195 |
tokenized |
active |
9.9M
|
megatron idx |
6.5 GB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/archive/unfilted/wenetspeech_interleaved_dur0-200/indexed |
| #293 |
parquet |
active |
14.6M
|
parquet footer |
3.3 GB |
2026-07-22 13:37 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/archive/unfilted/wenetspeech_interleaved_dur0-200/parquet |
| #545 |
tokenized |
active |
18.7K
|
megatron idx |
30.3 MB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/audio_only/audioset_bal_train_audio_only_dur2-200 |
| #696 |
tokenized |
active |
18.7K
|
megatron idx |
30.3 MB |
2026-07-22 13:57 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/audio_only/audioset_bal_train_shar_lhotse_audio_only_dur2-200 |
| #237 |
tokenized |
active |
1.7M
|
megatron idx |
2.8 GB |
2026-07-22 13:35 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/audio_only/audioset_unbal_train_shar_lhotse_audio_only_dur2-200 |
| #354 |
tokenized |
active |
2.0M
|
megatron idx |
1.7 GB |
2026-07-22 13:39 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/audio_only/commonvoice_ca_de_en_es_fr_it_zh-CN_S1_audio_only_dur3-500 |
| #499 |
tokenized |
active |
72.1K
|
megatron idx |
692.1 MB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/audio_only/gemeinderat_shar_lhotse_audio_only_dur1-200 |
| #521 |
tokenized |
active |
19.5K
|
megatron idx |
430.8 MB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/audio_only/mtg_jamendo_train_S1_audio_only_dur5-200 |
| #144 |
tokenized |
active |
235.4K
|
megatron idx |
5.7 GB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/audio_only/suno_train_S1_audio_only_dur5-200 |
| #47 |
tokenized |
active |
15.5M
|
megatron idx |
205.0 GB |
2026-07-22 13:24 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/audio_only/ups_all_lang_vad_v2_audio_only_dur5-200 |
| #15 |
tokenized |
active |
31.9M
|
megatron idx |
227.6 GB |
2026-07-22 13:20 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/audio_only/voxpopuli_vad_audio_only_dur5-200 |
| #478 |
tokenized |
active |
2.6M
|
megatron idx |
2.9 GB |
2026-07-22 13:45 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/cooldown/aozora_hurigana_interleaved |
| #850 |
tokenized |
active |
238.5K
|
megatron idx |
1.8 GB |
2026-07-22 14:13 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/cooldown/ccpodcasts_interleaved |
| #816 |
tokenized |
active |
329.7K
|
megatron idx |
321.5 MB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/cooldown/farsi_asr_radio_interleaved |
| #807 |
tokenized |
active |
265.8K
|
megatron idx |
278.6 MB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/cooldown/infore2_interleaved |
| #436 |
parquet |
active |
5.7M
|
parquet footer |
7.5 GB |
2026-07-22 13:43 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/cooldown/interleave_cache_v3 |
| #652 |
tokenized |
active |
31.3K
|
megatron idx |
59.0 MB |
2026-07-22 13:52 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/cooldown/russian_librispeech_interleaved |
| #227 |
tokenized |
active |
243.3K
|
megatron idx |
1.8 GB |
2026-07-22 13:35 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/cooldown/slopalspeech_interleaved |
| #216 |
tokenized |
active |
14.3M
|
megatron idx |
16.0 GB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/cooldown/transcribe |
| #386 |
tokenized |
active |
78.9M
|
megatron idx |
418.3 GB |
2026-07-22 13:41 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/interleave |
| #231 |
tokenized |
active |
320.3K
|
megatron idx |
2.3 GB |
2026-07-22 13:35 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/internal-only/srg_apertus_interleaved |
| #516 |
tokenized |
active |
10.5K
|
megatron idx |
25.9 MB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/sft/audiomcq_gemini_cot_speech |
| #439 |
tokenized |
active |
10.5K
|
megatron idx |
18.3 MB |
2026-07-22 13:43 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/sft/audiomcq_speech |
| #655 |
tokenized |
active |
49.6K
|
megatron idx |
95.0 MB |
2026-07-22 13:52 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/sft/heysquad_human_accepted |
| #335 |
tokenized |
active |
26.3K
|
megatron idx |
50.2 MB |
2026-07-22 13:39 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/sft/heysquad_human_refusal_canonical |
| #53 |
tokenized |
active |
98.2K
|
megatron idx |
146.8 MB |
2026-07-22 13:25 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/sft/heysquad_machine |
| #285 |
tokenized |
active |
204.9K
|
megatron idx |
22.0 GB |
2026-07-22 13:36 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/sft/marco_longspeech_sft |
| #13 |
tokenized |
active |
58.4K
|
megatron idx |
239.3 MB |
2026-07-22 13:20 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/sft/tcm_shizhengpt_speech |
| #257 |
tokenized |
active |
34.0K
|
megatron idx |
532.6 MB |
2026-07-22 13:36 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/sft/teleantifraud_matching_sft |
| #11 |
tokenized |
active |
635.3K
|
megatron idx |
2.9 GB |
2026-07-22 13:20 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/sft/vocalized_sft |
| #451 |
tokenized |
active |
242.2K
|
megatron idx |
582.3 MB |
2026-07-22 13:44 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/sft/voiceassistant_400k |
| #141 |
tokenized |
active |
54.6M
|
megatron idx |
451.1 GB |
2026-07-22 13:30 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/stage_1_rebuild |
| #193 |
tokenized |
active |
40.5M
|
megatron idx |
42.7 GB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/transcribe |
| #176 |
tokenized |
active |
38.1M
|
megatron idx |
71.1 GB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/audio-datasets/tokenized/translate |
| #502 |
tokenized |
active |
72.8M
|
megatron idx |
305.0 GB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_cooldown_tokenized/70B |
| #125 |
tokenized |
active |
38.6M
|
megatron idx |
171.0 GB |
2026-07-22 13:28 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_cooldown_tokenized/8B |
| #156 |
tokenized |
active |
1.6K
|
megatron idx |
56.6 MB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_lct_tokenized/70B |
| #197 |
tokenized |
active |
2.5M
|
megatron idx |
260.2 GB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_lct_tokenized/8B |
| #134 |
tokenized |
active |
11.5M
|
megatron idx |
177.2 GB |
2026-07-22 13:28 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_sft_lct_tokenized |
| #212 |
tokenized |
active |
62.7M
|
megatron idx |
820.5 GB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_sft_tokenized |
| #705 |
tokenized |
active |
222.7M
|
megatron idx |
1.5 TB |
2026-07-22 13:57 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage1_tokenized/8B |
| #525 |
tokenized |
active |
765.5K
|
megatron idx |
17.6 GB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage1_tokenized/bio-treeoflife10m |
| #602 |
tokenized |
active |
266.6K
|
megatron idx |
510.6 MB |
2026-07-22 13:48 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage1_tokenized/egocentric-holoassist |
| #542 |
tokenized |
active |
4.4M
|
megatron idx |
34.7 GB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage1_tokenized/general-laion_aestetics12mumap |
| #359 |
tokenized |
active |
125.0M
|
megatron idx |
914.1 GB |
2026-07-22 13:39 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage1_tokenized/general-mint1THTML |
| #366 |
tokenized |
active |
1.8M
|
megatron idx |
11.4 GB |
2026-07-22 13:40 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage1_tokenized/general-mint1Tpdf_01 |
| #213 |
tokenized |
active |
2.1M
|
megatron idx |
13.9 GB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage1_tokenized/general-mint1Tpdf_02 |
| #424 |
tokenized |
active |
3.7M
|
megatron idx |
23.3 GB |
2026-07-22 13:42 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage1_tokenized/general-mint1Tpdf_03 |
| #362 |
tokenized |
active |
5.4M
|
megatron idx |
36.0 GB |
2026-07-22 13:40 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage1_tokenized/general-mint1Tpdf_04 |
| #608 |
tokenized |
active |
6.4M
|
megatron idx |
50.0 GB |
2026-07-22 13:49 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage1_tokenized/general-mint1Tpdf_05 |
| #206 |
tokenized |
active |
16.5M
|
megatron idx |
103.7 GB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage1_tokenized/general-mint1Tpdf_06 |
| #42 |
tokenized |
active |
22.9M
|
megatron idx |
145.4 GB |
2026-07-22 13:22 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage1_tokenized/general-mint1Tpdf_07 |
| #804 |
tokenized |
active |
24.0K
|
megatron idx |
24.5 MB |
2026-07-22 14:11 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage1_tokenized/geo-bigearthnet |
| #828 |
tokenized |
active |
5.1K
|
megatron idx |
5.9 MB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage1_tokenized/geo-dfc2020 |
| #605 |
tokenized |
active |
1.3M
|
megatron idx |
20.2 GB |
2026-07-22 13:48 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage1_tokenized/geo-swissimage |
| #387 |
tokenized |
active |
732
|
megatron idx |
3.8 MB |
2026-07-22 13:41 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage1_tokenized/medical-busi |
| #704 |
tokenized |
active |
9.7K
|
megatron idx |
44.5 MB |
2026-07-22 13:57 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage1_tokenized/medical-covidus |
| #27 |
tokenized |
active |
347
|
megatron idx |
1.1 MB |
2026-07-22 13:21 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage1_tokenized/medical-ddti |
| #160 |
tokenized |
active |
216.3K
|
megatron idx |
76.0 MB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage1_tokenized/medical-isic |
| #383 |
tokenized |
active |
1.5M
|
megatron idx |
12.4 GB |
2026-07-22 13:41 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage1_tokenized/medical-mammoth |
| #274 |
tokenized |
active |
446.0K
|
megatron idx |
2.9 GB |
2026-07-22 13:36 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage1_tokenized/medical-medmax |
| #805 |
tokenized |
active |
236.6K
|
megatron idx |
212.7 MB |
2026-07-22 14:11 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage1_tokenized/medical-medmnist |
| #601 |
tokenized |
active |
4.4M
|
megatron idx |
8.2 GB |
2026-07-22 13:48 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage1_tokenized/medical-medtrinityfull |
| #560 |
tokenized |
active |
17.3M
|
megatron idx |
19.4 GB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage1_tokenized/medical-openpmc18m |
| #763 |
tokenized |
active |
1.3M
|
megatron idx |
1.5 GB |
2026-07-22 14:09 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage1_tokenized/medical-pmcoa |
| #840 |
tokenized |
active |
754
|
megatron idx |
9.6 MB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage1_tokenized/medical-rfmid2 |
| #233 |
tokenized |
active |
10.4K
|
megatron idx |
126.4 MB |
2026-07-22 13:35 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage1_tokenized/medical-scin |
| #113 |
tokenized |
active |
3.0K
|
megatron idx |
21.3 MB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage1_tokenized/medical-slide |
| #670 |
tokenized |
active |
700
|
megatron idx |
14.7 MB |
2026-07-22 13:54 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage1_tokenized/medical-uwf |
| #557 |
tokenized |
active |
2.2M
|
megatron idx |
24.6 GB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage1_tokenized/ocr-bigDocs7_5m |
| #103 |
tokenized |
active |
4.6M
|
megatron idx |
57.6 GB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage1_tokenized/ocr-mint1Tarxiv |
| #147 |
tokenized |
active |
15.0K
|
megatron idx |
199.7 MB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage1_tokenized/ocr-nicola_handwriting/data |
| #205 |
tokenized |
active |
2.5K
|
megatron idx |
17.3 MB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage1_tokenized/ocr-nicola_handwriting/data_slides |
| #517 |
tokenized |
active |
137.9K
|
megatron idx |
4.7 GB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage2_lct_tokenized/8B |
| #372 |
tokenized |
active |
272.6M
|
megatron idx |
2.1 TB |
2026-07-22 13:40 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage2_tokenized/70B |
| #790 |
tokenized |
active |
90.6M
|
megatron idx |
752.2 GB |
2026-07-22 14:10 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage2_tokenized/70B_leftover |
| #567 |
tokenized |
active |
484.1M
|
megatron idx |
3.4 TB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Apertus1p5_stage2_tokenized/8B |
| #490 |
tokenized |
active |
45.1M
|
megatron idx |
305.0 GB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/vision-datasets/LLaVA-OneVision-1.5-Mid-Training/tokenized_apertus_emu3_5_image_only |
| #689 |
tokenized |
active |
44.8M
|
megatron idx |
272.4 GB |
2026-07-22 13:56 |
/capstor/store/cscs/swissai/infra01/vision-datasets/LLaVA-OneVision-1.5-Mid-Training/tokenized_apertus_emu3_5_paired |
| #742 |
tokenized |
active |
45.0M
|
megatron idx |
303.3 GB |
2026-07-22 13:58 |
/capstor/store/cscs/swissai/infra01/vision-datasets/LLaVA-OneVision-1.5-Mid-Training/tokenized_apertus_emu3_5_paired_reversed |
| #138 |
media |
active |
653.2K
|
file count |
118.8 GB |
2026-07-22 13:29 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Non-commercial/Quilt_1M/quilt_1m |
| #631 |
parquet |
active |
1.0M
|
parquet footer |
133.5 GB |
2026-07-22 13:50 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Non-commercial/Quilt_1M/quilt_1m_parquet |
| #198 |
tokenized |
active |
1.0M
|
megatron idx |
20.0 GB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Non-commercial/Quilt_1M/tokenized |
| #667 |
parquet |
active |
29.2M
|
parquet footer |
11.4 TB |
2026-07-22 13:54 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Spectrum-25M/dataset |
| #776 |
parquet |
active |
1.0K
|
parquet footer |
422.2 MB |
2026-07-22 14:09 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Spectrum-25M/spectrum_toy/train |
| #106 |
parquet |
active |
1.0K
|
parquet footer |
424.8 MB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Spectrum-25M/spectrum_toy/val |
| #384 |
media |
active |
1.1K
|
file count |
215.0 MB |
2026-07-22 13:41 |
/capstor/store/cscs/swissai/infra01/vision-datasets/Spectrum-25M/spectrum_toy/viz |
| #431 |
tokenized |
active |
6.8M
|
megatron idx |
1.0 TB |
2026-07-22 13:43 |
/capstor/store/cscs/swissai/infra01/vision-datasets/archive/Apertus1p5_sft_lct_tokenized |
| #137 |
tokenized |
active |
40.8M
|
megatron idx |
447.7 GB |
2026-07-22 13:28 |
/capstor/store/cscs/swissai/infra01/vision-datasets/archive/Apertus1p5_sft_tokenized |
| #117 |
tokenized |
active |
4.9M
|
megatron idx |
27.5 GB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/vision-datasets/archive/Apertus1p5_stage2_tokenized |
| #593 |
tokenized |
active |
85.4M
|
megatron idx |
393.9 GB |
2026-07-22 13:48 |
/capstor/store/cscs/swissai/infra01/vision-datasets/archive/cooldown_70B_full_originals |
| #51 |
media |
active |
332.2K
|
file count |
182.8 GB |
2026-07-22 13:24 |
/capstor/store/cscs/swissai/infra01/vision-datasets/benchmark/VLMEval_Data |
| #294 |
webdataset |
active |
n/a
|
|
1.2 TB |
2026-07-22 13:37 |
/capstor/store/cscs/swissai/infra01/vision-datasets/conceptual-12m/data |
| #866 |
tokenized |
active |
7.4M
|
megatron idx |
211.0 GB |
2026-07-22 14:14 |
/capstor/store/cscs/swissai/infra01/vision-datasets/conceptual-12m/merged |
| #132 |
hf_arrow |
active |
n/a
|
|
139.6 MB |
2026-07-22 13:28 |
/capstor/store/cscs/swissai/infra01/vision-datasets/eval/hf_home/datasets |
| #64 |
media |
active |
1.1K
|
file count |
206.3 MB |
2026-07-22 13:26 |
/capstor/store/cscs/swissai/infra01/vision-datasets/eval/histo/Osteo |
| #367 |
media |
active |
37.6K
|
file count |
2.2 GB |
2026-07-22 13:40 |
/capstor/store/cscs/swissai/infra01/vision-datasets/eval/histo/SICAPv2 |
| #765 |
manual |
active |
n/a
|
|
7.8 GB |
2026-07-22 14:09 |
/capstor/store/cscs/swissai/infra01/vision-datasets/eval/histo/SkinCancer/SkinCancer |
| #761 |
media |
active |
4.3K
|
file count |
5.3 GB |
2026-07-22 14:09 |
/capstor/store/cscs/swissai/infra01/vision-datasets/eval/histo/arch/books_set |
| #215 |
media |
active |
3.3K
|
file count |
490.8 MB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/vision-datasets/eval/histo/arch/pubmed_set |
| #276 |
media |
active |
440
|
file count |
14.2 GB |
2026-07-22 13:36 |
/capstor/store/cscs/swissai/infra01/vision-datasets/eval/histo/bach/ICIAR2018_BACH_Challenge |
| #678 |
media |
active |
110
|
file count |
4.0 GB |
2026-07-22 13:56 |
/capstor/store/cscs/swissai/infra01/vision-datasets/eval/histo/bach/ICIAR2018_BACH_Challenge_TestDataset |
| #253 |
media |
active |
100.0K
|
file count |
15.2 GB |
2026-07-22 13:35 |
/capstor/store/cscs/swissai/infra01/vision-datasets/eval/histo/crc-100k |
| #582 |
media |
active |
7.2K
|
file count |
1.1 GB |
2026-07-22 13:48 |
/capstor/store/cscs/swissai/infra01/vision-datasets/eval/histo/crc-7k/CRC-VAL-HE-7K |
| #108 |
media |
active |
25.0K
|
file count |
1.9 GB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/vision-datasets/eval/histo/lc25000 |
| #315 |
media |
active |
3.2K
|
file count |
349.6 MB |
2026-07-22 13:38 |
/capstor/store/cscs/swissai/infra01/vision-datasets/eval/histo/mhist |
| #43 |
media |
active |
2.2K
|
file count |
1.3 GB |
2026-07-22 13:22 |
/capstor/store/cscs/swissai/infra01/vision-datasets/eval/histo/socialpath_dl |
| #819 |
media |
active |
10.4K
|
file count |
1.6 GB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/vision-datasets/eval/histo/wsss4luad |
| #148 |
media |
active |
67
|
file count |
159.2 MB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/vision-datasets/filtered/common_canvas/sample |
| #523 |
media |
active |
24
|
file count |
3.3 MB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/vision-datasets/filtered/datacomp_1b/samples |
| #682 |
parquet |
active |
51.4K
|
parquet footer |
1.9 GB |
2026-07-22 13:56 |
/capstor/store/cscs/swissai/infra01/vision-datasets/filtered/ground_cap |
| #616 |
parquet |
active |
36.6K
|
parquet footer |
77.9 GB |
2026-07-22 13:49 |
/capstor/store/cscs/swissai/infra01/vision-datasets/filtered/hq_50k |
| #611 |
parquet |
active |
278
|
parquet footer |
597.5 MB |
2026-07-22 13:49 |
/capstor/store/cscs/swissai/infra01/vision-datasets/filtered/hq_50k_scratch_xyixuan |
| #380 |
webdataset |
active |
n/a
|
|
981.5 GB |
2026-07-22 13:41 |
/capstor/store/cscs/swissai/infra01/vision-datasets/filtered/laion_aesthetics |
| #39 |
hf_arrow |
active |
n/a
|
|
46.2 TB |
2026-07-22 13:22 |
/capstor/store/cscs/swissai/infra01/vision-datasets/filtered/llava_onevision |
| #578 |
media |
active |
569
|
file count |
106.3 MB |
2026-07-22 13:48 |
/capstor/store/cscs/swissai/infra01/vision-datasets/filtered/megalith_10m/00001/sample |
| #109 |
webdataset |
active |
n/a
|
|
410.6 GB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/vision-datasets/filtered/text_to_image_2m |
| #833 |
media |
active |
80.5K
|
file count |
95.5 GB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/vision-datasets/handwriting-apertus__handwriting_data |
| #72 |
parquet |
active |
116.8K
|
parquet footer |
25.2 GB |
2026-07-22 13:26 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/CoSyn_400k_chart |
| #695 |
parquet |
active |
8.9K
|
parquet footer |
273.1 MB |
2026-07-22 13:57 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/CoSyn_400k_chemical |
| #471 |
parquet |
active |
10.5K
|
parquet footer |
381.9 MB |
2026-07-22 13:45 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/CoSyn_400k_circuit |
| #351 |
parquet |
active |
35.0K
|
parquet footer |
7.2 GB |
2026-07-22 13:39 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/CoSyn_400k_diagram |
| #435 |
parquet |
active |
71.3K
|
parquet footer |
24.0 GB |
2026-07-22 13:43 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/CoSyn_400k_document |
| #154 |
parquet |
active |
27.0K
|
parquet footer |
313.4 MB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/CoSyn_400k_graphic |
| #143 |
parquet |
active |
66.7K
|
parquet footer |
6.1 GB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/CoSyn_400k_math |
| #194 |
parquet |
active |
12.0K
|
parquet footer |
377.7 MB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/CoSyn_400k_music |
| #97 |
parquet |
active |
6.9K
|
parquet footer |
1.5 GB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/CoSyn_400k_nutrition |
| #327 |
parquet |
active |
46.5K
|
parquet footer |
7.6 GB |
2026-07-22 13:38 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/CoSyn_400k_table |
| #358 |
parquet |
active |
1.3M
|
parquet footer |
950.8 GB |
2026-07-22 13:39 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/DoclingMatix |
| #405 |
parquet |
active |
157.7K
|
parquet footer |
76.6 GB |
2026-07-22 13:41 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/LLaVA_Instruct_150K |
| #258 |
parquet |
active |
611.9K
|
parquet footer |
16.9 GB |
2026-07-22 13:36 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/Unichart |
| #166 |
parquet |
active |
459.0K
|
parquet footer |
227.8 GB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/aguvis-stage-1 |
| #281 |
parquet |
active |
4.9K
|
parquet footer |
860.6 MB |
2026-07-22 13:36 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/ai2d_merged |
| #447 |
parquet |
active |
5.5K
|
parquet footer |
5.1 GB |
2026-07-22 13:43 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/art |
| #190 |
parquet |
active |
54.2K
|
parquet footer |
14.2 GB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/chinesememe |
| #12 |
parquet |
active |
70.0K
|
parquet footer |
9.3 GB |
2026-07-22 13:20 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/clevr_math |
| #59 |
parquet |
active |
118.3K
|
parquet footer |
55.3 GB |
2026-07-22 13:25 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/coco_colors |
| #659 |
parquet |
active |
46.3K
|
parquet footer |
2.4 GB |
2026-07-22 13:52 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/cocoqa |
| #271 |
parquet |
active |
16.2K
|
parquet footer |
7.9 GB |
2026-07-22 13:36 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/cocotext |
| #571 |
parquet |
active |
200.0K
|
parquet footer |
4.3 GB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/dvqa |
| #417 |
parquet |
active |
2.1K
|
parquet footer |
37.4 MB |
2026-07-22 13:42 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/geo3k |
| #489 |
parquet |
active |
1.4K
|
parquet footer |
164.7 MB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/handwriting_forms |
| #115 |
parquet |
active |
39.6K
|
parquet footer |
12.7 GB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/latex_handwritten |
| #814 |
parquet |
active |
552.3K
|
parquet footer |
5.5 GB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/latexformulas |
| #679 |
parquet |
active |
302.8K
|
parquet footer |
266.1 GB |
2026-07-22 13:56 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/lnqa |
| #576 |
parquet |
active |
200.0K
|
parquet footer |
21.3 GB |
2026-07-22 13:48 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/localized_narratives |
| #404 |
parquet |
active |
300.0K
|
parquet footer |
12.2 GB |
2026-07-22 13:41 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/mathwriting-google |
| #325 |
parquet |
active |
7.0K
|
parquet footer |
2.5 GB |
2026-07-22 13:38 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/memotion |
| #277 |
parquet |
active |
160.2K
|
parquet footer |
25.5 GB |
2026-07-22 13:36 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/mmevol |
| #283 |
parquet |
active |
1.0K
|
parquet footer |
1.2 GB |
2026-07-22 13:36 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/mmra |
| #556 |
parquet |
active |
7.6K
|
parquet footer |
1.4 GB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/multihiertt |
| #291 |
parquet |
active |
50.4K
|
parquet footer |
23.5 GB |
2026-07-22 13:37 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/nlvr2 |
| #867 |
parquet |
active |
15.2K
|
parquet footer |
6.6 GB |
2026-07-22 14:14 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/olmOCR-mix-0225-books |
| #91 |
parquet |
active |
228.9K
|
parquet footer |
97.3 GB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/olmOCR-mix-0225-documents |
| #626 |
parquet |
active |
8.6K
|
parquet footer |
1.6 GB |
2026-07-22 13:49 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/pdfvqa |
| #398 |
parquet |
active |
5.0K
|
parquet footer |
283.3 MB |
2026-07-22 13:41 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/scienceqa |
| #646 |
parquet |
active |
3.9K
|
parquet footer |
1.1 GB |
2026-07-22 13:52 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/spark |
| #842 |
parquet |
active |
10.4K
|
parquet footer |
3.5 GB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/spatialsense |
| #349 |
parquet |
active |
8.6K
|
parquet footer |
1.6 GB |
2026-07-22 13:39 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/spot_the_diff |
| #736 |
parquet |
active |
17.2K
|
parquet footer |
876.0 MB |
2026-07-22 13:58 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/st_vqa |
| #379 |
parquet |
active |
4.4K
|
parquet footer |
4.3 GB |
2026-07-22 13:41 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/svrd |
| #259 |
parquet |
active |
22.7K
|
parquet footer |
306.4 MB |
2026-07-22 13:36 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/tabmwp |
| #627 |
parquet |
active |
256.6K
|
parquet footer |
4.6 GB |
2026-07-22 13:49 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/tal_ocr_eng |
| #809 |
parquet |
active |
98.7K
|
parquet footer |
4.7 GB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/tallyqa |
| #738 |
parquet |
active |
2.2K
|
parquet footer |
51.8 MB |
2026-07-22 13:58 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/tat_dqa |
| #796 |
hf_arrow |
active |
1.0M
|
hf meta |
1.4 GB |
2026-07-22 14:11 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/text_OpenMathInstruct-2 |
| #684 |
parquet |
active |
253.0K
|
parquet footer |
149.9 GB |
2026-07-22 13:56 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/ureader_qa_processed |
| #262 |
parquet |
active |
14.4K
|
parquet footer |
4.4 GB |
2026-07-22 13:36 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/visual7w |
| #544 |
parquet |
active |
263.6K
|
parquet footer |
36.2 GB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/visualwebinstruct(filtered) |
| #527 |
parquet |
active |
82.8K
|
parquet footer |
4.3 GB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/vqav2 |
| #111 |
parquet |
active |
4.8K
|
parquet footer |
2.8 GB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/wordart |
| #60 |
parquet |
active |
4.3K
|
parquet footer |
3.2 GB |
2026-07-22 13:25 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/finevision/yesbut |
| #243 |
parquet |
active |
3.1K
|
parquet footer |
139.5 MB |
2026-07-22 13:35 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/lmms-lab_ai2d |
| #745 |
media |
active |
23.1K
|
file count |
1.8 GB |
2026-07-22 13:58 |
/capstor/store/cscs/swissai/infra01/vision-datasets/hf_downloads/spatialsense_original/images |
| #89 |
parquet |
active |
813.4K
|
parquet footer |
200.7 GB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/alignment |
| #88 |
media |
active |
10.0K
|
file count |
12.0 GB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/copernicus___sentinel-2-rgb-captioned |
| #247 |
media |
active |
9.8K
|
file count |
11.8 GB |
2026-07-22 13:35 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/copernicus___sentinel-2-rgb-captioned_merged |
| #290 |
archive |
active |
n/a
|
|
78.4 GB |
2026-07-22 13:37 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/gh___wangzhecheng___SkyScript |
| #639 |
webdataset |
active |
n/a
|
|
93.0 GB |
2026-07-22 13:50 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/gh___wangzhecheng___SkyScript___downloaded |
| #654 |
webdataset |
active |
n/a
|
|
93.0 GB |
2026-07-22 13:52 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/gh___wangzhecheng___SkyScript___processed |
| #566 |
manual |
active |
n/a
|
|
722.8 GB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___DeepGlint-AI___DanQing100M___downloaded |
| #267 |
parquet |
active |
46.1M
|
parquet footer |
11.5 TB |
2026-07-22 13:36 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___InnovatorLab___Innovator-VL-Instruct-46M___restored_think_tokens |
| #698 |
parquet |
active |
46.1M
|
parquet footer |
11.5 TB |
2026-07-22 13:57 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___InnovatorLab___Innovator-VL-Instruct-46M___restored_think_tokens2 |
| #62 |
media |
active |
524.3K
|
file count |
40.6 GB |
2026-07-22 13:26 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___JessicaYuan___ChatEarthNet |
| #171 |
webdataset |
active |
n/a
|
|
238.6 GB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___MBZUAI___GeoChat_Instruct___processed |
| #167 |
webdataset |
active |
n/a
|
|
102.3 GB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___Mitsua___art-museums-pd-440k___recap |
| #286 |
manual |
active |
n/a
|
|
801.3 GB |
2026-07-22 13:37 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___OpenFace-CQUPT___FaceCaption-15M___crop_processed |
| #14 |
manual |
active |
n/a
|
|
3.0 TB |
2026-07-22 13:20 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___OpenFace-CQUPT___FaceCaption-15M___downloaded |
| #620 |
parquet |
active |
52.4M
|
parquet footer |
91.2 GB |
2026-07-22 13:49 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___Salesforce___blip3-grounding-50m___downloaded |
| #270 |
webdataset |
active |
n/a
|
|
135.7 GB |
2026-07-22 13:36 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___ServiceNow___BigDocs-7.5M___downloaded |
| #30 |
webdataset |
active |
n/a
|
|
83.0 GB |
2026-07-22 13:21 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___SlytherinGe___RSTeller___processed |
| #57 |
webdataset |
active |
n/a
|
|
29.3 TB |
2026-07-22 13:25 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___Spawning___pd12m-full___recap |
| #756 |
parquet |
active |
940.9M
|
parquet footer |
527.4 GB |
2026-07-22 14:08 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___UCSC-VLAA___Recap-DataComp-1B |
| #306 |
webdataset |
active |
n/a
|
|
21.0 TB |
2026-07-22 13:38 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___UCSC-VLAA___Recap-DataComp-1B___downloaded_p1 |
| #409 |
manual |
active |
n/a
|
|
19.0 TB |
2026-07-22 13:42 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___UCSC-VLAA___Recap-DataComp-1B___downloaded_p2 |
| #458 |
parquet |
active |
73.6K
|
parquet footer |
153.6 GB |
2026-07-22 13:44 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___YangQiee___HQ-50K |
| #312 |
parquet |
active |
n/a
|
|
300.0 GB |
2026-07-22 13:38 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___YangQiee___HQ-50K___flat_v7 |
| #298 |
webdataset |
active |
n/a
|
|
3.5 GB |
2026-07-22 13:37 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___ai4ce___EgoPAT3Dv2___downloaded |
| #737 |
webdataset |
active |
n/a
|
|
3.5 GB |
2026-07-22 13:58 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___ai4ce___EgoPAT3Dv2___processed |
| #87 |
manual |
active |
n/a
|
|
1.7 TB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___aipicasso___megalith-10m-florence2___downloaded |
| #162 |
parquet |
active |
26.2K
|
parquet footer |
33.6 GB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___allenai___Molmo2-MultiImageQA___doc_keyed |
| #338 |
parquet |
active |
95.5K
|
parquet footer |
40.5 GB |
2026-07-22 13:39 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___allenai___Molmo2-MultiImageQA___downloaded |
| #844 |
parquet |
active |
73.1K
|
parquet footer |
31.2 GB |
2026-07-22 14:13 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___allenai___pixmo-ask-model-anything___downloaded |
| #656 |
parquet |
active |
15.0K
|
parquet footer |
5.8 GB |
2026-07-22 13:52 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___allenai___pixmo-point-explanations___downloaded |
| #758 |
webdataset |
active |
n/a
|
|
378.2 GB |
2026-07-22 14:09 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___anthracite-org___pixmo-cap-images___processed |
| #817 |
webdataset |
active |
n/a
|
|
616.4 GB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___bitmind___open-images-v7___recap |
| #883 |
media |
active |
27.0K
|
file count |
57.9 MB |
2026-07-22 14:14 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___blanchon___EuroSAT_RGB |
| #744 |
media |
active |
27.0K
|
file count |
261.6 MB |
2026-07-22 13:58 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___blanchon___EuroSAT_RGB_work |
| #518 |
webdataset |
active |
n/a
|
|
1.4 TB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___bytedance-research___UNO-1M___recap |
| #873 |
webdataset |
active |
n/a
|
|
21.5 TB |
2026-07-22 14:14 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___common-canvas___commoncatalog-cc-by___recap |
| #128 |
webdataset |
active |
n/a
|
|
987.2 GB |
2026-07-22 13:28 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___dclure___laion-aesthetics-12m-umap___processed |
| #441 |
webdataset |
active |
n/a
|
|
200.4 GB |
2026-07-22 13:43 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___google___MapTrace___processed |
| #153 |
webdataset |
active |
n/a
|
|
546.7 GB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___imageomics___TreeOfLife-10M___processed |
| #533 |
webdataset |
active |
n/a
|
|
76.7 GB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___liboaccn___MIT-10M___recap |
| #346 |
parquet |
active |
4.4M
|
parquet footer |
669.5 GB |
2026-07-22 13:39 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___mlfoundations___MINT-1T-ArXiv___cooldown |
| #838 |
webdataset |
active |
n/a
|
|
932.9 GB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___mlfoundations___MINT-1T-ArXiv___processed |
| #876 |
archive |
active |
n/a
|
|
321.2 TB |
2026-07-22 14:14 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___mlfoundations___MINT-1T-HTML___processed |
| #238 |
webdataset |
active |
n/a
|
|
283.3 GB |
2026-07-22 13:35 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___mlfoundations___MINT-1T-PDF-CC-2023-06___processed |
| #204 |
webdataset |
active |
n/a
|
|
347.3 GB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___mlfoundations___MINT-1T-PDF-CC-2023-14___processed |
| #300 |
webdataset |
active |
n/a
|
|
594.6 GB |
2026-07-22 13:37 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___mlfoundations___MINT-1T-PDF-CC-2023-23___processed |
| #568 |
webdataset |
active |
n/a
|
|
883.5 GB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___mlfoundations___MINT-1T-PDF-CC-2023-40___processed |
| #538 |
webdataset |
active |
n/a
|
|
1.1 TB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___mlfoundations___MINT-1T-PDF-CC-2023-50___processed |
| #353 |
webdataset |
active |
n/a
|
|
2.6 TB |
2026-07-22 13:39 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___mlfoundations___MINT-1T-PDF-CC-2024-10___processed |
| #264 |
webdataset |
active |
n/a
|
|
3.6 TB |
2026-07-22 13:36 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___mlfoundations___MINT-1T-PDF-CC-2024-18___processed |
| #822 |
webdataset |
active |
n/a
|
|
2.3 GB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/hf___wangyi111___Copernicus-Bench___processed |
| #466 |
hf_arrow |
active |
266.6K
|
hf meta |
43.6 GB |
2026-07-22 13:45 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/holoassist |
| #146 |
webdataset |
active |
n/a
|
|
190.9 GB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/ign___IGNF___FLAIR-HUB___processed |
| #885 |
webdataset |
active |
n/a
|
|
190.8 GB |
2026-07-22 14:14 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/ign___IGNF___FLAIR-HUB___processed___cleaned |
| #878 |
webdataset |
active |
n/a
|
|
2.8 GB |
2026-07-22 14:14 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/ign___ign_city_tiles___processed |
| #801 |
webdataset |
active |
n/a
|
|
2.9 GB |
2026-07-22 14:11 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/ign___ign_city_tiles___processed___cleaned |
| #574 |
parquet |
active |
37.0K
|
parquet footer |
228.4 GB |
2026-07-22 13:48 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/nasa_cooldown/qwen3p6_27b_image_captioned |
| #1 |
parquet |
active |
11.4K
|
parquet footer |
2.3 GB |
2026-07-22 13:20 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/owid___charts |
| #410 |
parquet |
active |
795.2K
|
parquet footer |
323.2 GB |
2026-07-22 13:42 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/rl |
| #851 |
parquet |
active |
205.5K
|
parquet footer |
35.4 GB |
2026-07-22 14:13 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/finevision/CoSyn_400k |
| #289 |
parquet |
active |
525.3K
|
parquet footer |
406.4 GB |
2026-07-22 13:37 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/finevision/DoclingMatix |
| #314 |
parquet |
active |
187.0K
|
parquet footer |
108.0 GB |
2026-07-22 13:38 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/finevision/aguvis-stage-1 |
| #101 |
parquet |
active |
4.9K
|
parquet footer |
858.6 MB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/finevision/ai2d_merged_decontaminated |
| #313 |
parquet |
active |
5.0K
|
parquet footer |
4.7 GB |
2026-07-22 13:38 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/finevision/art |
| #391 |
parquet |
active |
43.6K
|
parquet footer |
11.2 GB |
2026-07-22 13:41 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/finevision/chinesememe |
| #618 |
parquet |
active |
43.5K
|
parquet footer |
10.9 GB |
2026-07-22 13:49 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/finevision/chinesememe_recap_en |
| #49 |
parquet |
active |
114.5K
|
parquet footer |
53.6 GB |
2026-07-22 13:24 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/finevision/coco_colors |
| #273 |
parquet |
active |
45.7K
|
parquet footer |
2.4 GB |
2026-07-22 13:36 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/finevision/cocoqa |
| #339 |
parquet |
active |
1.4K
|
parquet footer |
164.8 MB |
2026-07-22 13:39 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/finevision/handwriting_forms |
| #442 |
parquet |
active |
36.6K
|
parquet footer |
11.8 GB |
2026-07-22 13:43 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/finevision/latex_handwritten |
| #653 |
parquet |
active |
143.8K
|
parquet footer |
1.6 GB |
2026-07-22 13:52 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/finevision/latexformulas |
| #587 |
parquet |
active |
23.3K
|
parquet footer |
20.9 GB |
2026-07-22 13:48 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/finevision/lnqa |
| #299 |
parquet |
active |
302.8K
|
parquet footer |
266.2 GB |
2026-07-22 13:37 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/finevision/lnqa_recap |
| #84 |
parquet |
active |
181.3K
|
parquet footer |
19.4 GB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/finevision/localized_narratives |
| #746 |
parquet |
active |
6.8K
|
parquet footer |
2.5 GB |
2026-07-22 13:58 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/finevision/memotion |
| #268 |
parquet |
active |
5.9K
|
parquet footer |
2.1 GB |
2026-07-22 13:36 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/finevision/memotion_recap_en |
| #416 |
parquet |
active |
136.5K
|
parquet footer |
21.8 GB |
2026-07-22 13:42 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/finevision/mmevol |
| #570 |
parquet |
active |
92.4K
|
parquet footer |
14.3 GB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/finevision/mmevol_judged |
| #444 |
parquet |
active |
729
|
parquet footer |
989.3 MB |
2026-07-22 13:43 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/finevision/mmra |
| #636 |
parquet |
active |
5.4K
|
parquet footer |
911.8 MB |
2026-07-22 13:50 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/finevision/multihiertt |
| #250 |
parquet |
active |
5.4K
|
parquet footer |
909.1 MB |
2026-07-22 13:35 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/finevision/multihiertt_cleaned |
| #123 |
parquet |
active |
43.2K
|
parquet footer |
19.4 GB |
2026-07-22 13:28 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/finevision/nlvr2 |
| #468 |
parquet |
active |
13.4K
|
parquet footer |
5.9 GB |
2026-07-22 13:45 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/finevision/olmOCR-mix-0225-books |
| #484 |
parquet |
active |
198.1K
|
parquet footer |
84.4 GB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/finevision/olmOCR-mix-0225-documents |
| #445 |
parquet |
active |
3.2K
|
parquet footer |
852.4 MB |
2026-07-22 13:43 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/finevision/spark |
| #553 |
parquet |
active |
9.4K
|
parquet footer |
3.2 GB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/finevision/spatialsense |
| #820 |
parquet |
active |
7.7K
|
parquet footer |
2.6 GB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/finevision/spatialsense_recap |
| #836 |
parquet |
active |
6.8K
|
parquet footer |
1.0 GB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/finevision/spatialsense_recap_gold |
| #453 |
parquet |
active |
3.6K
|
parquet footer |
695.1 MB |
2026-07-22 13:44 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/finevision/spot_the_diff |
| #688 |
parquet |
active |
4.3K
|
parquet footer |
4.6 GB |
2026-07-22 13:56 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/finevision/svrd |
| #99 |
parquet |
active |
56.8K
|
parquet footer |
954.3 MB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/finevision/tal_ocr_eng |
| #69 |
parquet |
active |
771
|
parquet footer |
18.1 MB |
2026-07-22 13:26 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/finevision/tat_dqa |
| #503 |
parquet |
active |
3.2K
|
parquet footer |
2.0 GB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/finevision/wordart |
| #676 |
parquet |
active |
4.1K
|
parquet footer |
3.0 GB |
2026-07-22 13:56 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/finevision/yesbut |
| #179 |
webdataset |
active |
n/a
|
|
10.2 GB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/gmai_vl_permissive |
| #770 |
parquet |
active |
405
|
parquet footer |
26.0 MB |
2026-07-22 14:09 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/hf___ShadenA___MathNet___image_in_both |
| #573 |
parquet |
active |
721
|
parquet footer |
24.1 MB |
2026-07-22 13:48 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/hf___ShadenA___MathNet___image_in_question |
| #288 |
parquet |
active |
4.0K
|
parquet footer |
231.9 MB |
2026-07-22 13:37 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/hf___ShadenA___MathNet___image_in_response |
| #472 |
parquet |
active |
22.6K
|
parquet footer |
13.8 MB |
2026-07-22 13:45 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/hf___ShadenA___MathNet___text_only |
| #182 |
parquet |
active |
187.7K
|
parquet footer |
166.6 GB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/hf___allenai___pixmo-cap-qa___downloaded |
| #217 |
parquet |
active |
103.9K
|
parquet footer |
1.5 GB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/hf___google___RSRCC |
| #133 |
parquet |
active |
4.5M
|
parquet footer |
673.0 GB |
2026-07-22 13:28 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/hf___mlfoundations___MINT-1T-ArXiv___qa_captioned |
| #4 |
webdataset |
active |
n/a
|
|
47.2 GB |
2026-07-22 13:20 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/hf___mvp-lab___LLaVA-OneVision-2-Data___osd |
| #223 |
webdataset |
active |
n/a
|
|
4.7 GB |
2026-07-22 13:35 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/hf___mvp-lab___LLaVA-OneVision-2-Data___roborefer_sim |
| #152 |
parquet |
active |
40.0K
|
parquet footer |
45.4 GB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/messytable_si |
| #119 |
parquet |
active |
36.2K
|
parquet footer |
14.0 GB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/molmopoint_guisyn |
| #201 |
parquet |
active |
1.5M
|
parquet footer |
201.3 GB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/nemotron_image_training_v3___repacked |
| #355 |
webdataset |
active |
n/a
|
|
430.2 GB |
2026-07-22 13:39 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/pangea_instruct |
| #500 |
webdataset |
active |
n/a
|
|
63.3 GB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/sft/pubmedvision |
| #764 |
parquet |
active |
41.8K
|
parquet footer |
413.8 GB |
2026-07-22 14:09 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/smithsonian/smithsonian_cleaned5 |
| #534 |
webdataset |
active |
n/a
|
|
2.0 TB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/swisstopo___SWISSIMAGE___processed |
| #459 |
manual |
active |
n/a
|
|
2.3 TB |
2026-07-22 13:44 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/swisstopo___map_sat___downloaded |
| #619 |
webdataset |
active |
n/a
|
|
768.9 GB |
2026-07-22 13:49 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/swisstopo___map_sat___processed |
| #825 |
webdataset |
active |
n/a
|
|
768.5 GB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/swisstopo___map_sat___processed___cleaned |
| #802 |
media |
active |
42.7K
|
file count |
3.1 GB |
2026-07-22 14:11 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/swisstopo___swissimage |
| #872 |
media |
active |
919
|
file count |
30.5 GB |
2026-07-22 14:14 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/swisstopo___swissmap |
| #782 |
media |
active |
55.1K
|
file count |
25.6 GB |
2026-07-22 14:10 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/swisstopo___swissmap_split_6_10 |
| #245 |
parquet |
active |
36.3K
|
parquet footer |
41.9 GB |
2026-07-22 13:35 |
/capstor/store/cscs/swissai/infra01/vision-datasets/processed/waffle_captions |
| #33 |
media |
active |
24.7K
|
file count |
8.7 TB |
2026-07-22 13:22 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/ego4d |
| #777 |
media |
active |
50.4K
|
file count |
12.1 TB |
2026-07-22 14:10 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/egoexo4D |
| #486 |
archive |
active |
n/a
|
|
0 B |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/fs___BioMediTech_RPE_dataset |
| #875 |
media |
active |
700
|
file count |
12.6 GB |
2026-07-22 14:14 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/fs___Open_UFI_and_clinical_IQA |
| #390 |
archive |
active |
n/a
|
|
0 B |
2026-07-22 13:41 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/fs___PAPILA |
| #481 |
archive |
active |
n/a
|
|
9.6 GB |
2026-07-22 13:45 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/fs___SLID-E |
| #279 |
archive |
active |
n/a
|
|
13.3 MB |
2026-07-22 13:36 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/gh___Shenggan___BCCD_Dataset |
| #79 |
webdataset |
active |
n/a
|
|
111.7 GB |
2026-07-22 13:26 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/gh___allenai___medicat |
| #859 |
webdataset |
active |
n/a
|
|
283.8 MB |
2026-07-22 14:14 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/gh___dataset-ninja___ebhi-seg |
| #382 |
media |
active |
175
|
file count |
183.3 GB |
2026-07-22 13:41 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/gh___facebookresearch___EgoCom-Dataset |
| #385 |
webdataset |
active |
n/a
|
|
3.4 TB |
2026-07-22 13:41 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/gh___facebookresearch___libri-light |
| #546 |
hf_arrow |
active |
30.1K
|
hf meta |
1.9 GB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/gh___nrc-cnrc___COVID-US |
| #615 |
parquet |
active |
99.9M
|
parquet footer |
20.3 GB |
2026-07-22 13:49 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/hf___DeepGlint-AI___DanQing100M |
| #275 |
parquet |
active |
5.9M
|
parquet footer |
882.4 GB |
2026-07-22 13:36 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/hf___LucasFang___FLUX-Reason-6M |
| #92 |
parquet |
active |
8.2M
|
parquet footer |
226.9 GB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/hf___MathLLMs___ImgCode-8.6M |
| #234 |
parquet |
active |
2.2K
|
parquet footer |
54.7 GB |
2026-07-22 13:35 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/hf___RUC-NLPIR___Omnimodal-Agent-SFT-2K |
| #374 |
parquet |
active |
12.4M
|
parquet footer |
40.4 GB |
2026-07-22 13:40 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/hf___Spawning___PD12M |
| #9 |
manual |
active |
n/a
|
|
1.7 TB |
2026-07-22 13:20 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/hf___UCSC-VLAA___MedTrinity-25M |
| #129 |
archive |
active |
n/a
|
|
218.8 GB |
2026-07-22 13:28 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/hf___allenai___mmc4 |
| #52 |
parquet |
active |
5.0K
|
parquet footer |
12.6 GB |
2026-07-22 13:25 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/hf___google___scin |
| #865 |
manual |
active |
n/a
|
|
134.4 GB |
2026-07-22 14:14 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/hf___infly___Infinity-Doc2-5M |
| #632 |
parquet |
active |
1.6M
|
parquet footer |
34.8 GB |
2026-07-22 13:50 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/hf___jaagli___othello_shuffle |
| #318 |
parquet |
active |
9.6M
|
parquet footer |
754.1 MB |
2026-07-22 13:38 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/hf___madebyollin___megalith-10m |
| #280 |
webdataset |
active |
n/a
|
|
189.6 GB |
2026-07-22 13:36 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/hf___mint-medmax___medmax_data |
| #419 |
manual |
active |
n/a
|
|
345.6 GB |
2026-07-22 13:42 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/hf___neulab___CulturalGround |
| #824 |
parquet |
active |
96.7K
|
parquet footer |
2.4 GB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/hf___openmed-community___multicare-case-images |
| #692 |
parquet |
active |
161.7K
|
parquet footer |
3.2 GB |
2026-07-22 13:56 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/hf___openmed-community___multicare-images |
| #780 |
parquet |
active |
36.8K
|
parquet footer |
5.8 GB |
2026-07-22 14:10 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/hf___ronantakizawa___webui |
| #124 |
media |
active |
20
|
file count |
43.1 GB |
2026-07-22 13:28 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/hpirsiav___ADLdataset |
| #740 |
archive |
active |
n/a
|
|
132.2 GB |
2026-07-22 13:58 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/jawaid___openego |
| #429 |
archive |
active |
n/a
|
|
653.1 MB |
2026-07-22 13:43 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/kg___abhii1929___isic-skin-disease-image-dataset-4-classes |
| #524 |
archive |
active |
n/a
|
|
1.4 GB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/kg___darsh22blc1378___abdominal-ultrasound-images |
| #181 |
hf_arrow |
active |
347
|
hf meta |
49.1 MB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/kg___dasmehdixtr___ddti-thyroid-ultrasound-images |
| #722 |
archive |
active |
n/a
|
|
397.1 MB |
2026-07-22 13:58 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/kg___ipythonx___notop-wg-radimagenet |
| #675 |
archive |
active |
n/a
|
|
154.2 MB |
2026-07-22 13:56 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/kg___karthikperupogu___consep |
| #418 |
archive |
active |
n/a
|
|
164.7 MB |
2026-07-22 13:42 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/kg___masoudnickparvar___brain-tumor-mri-dataset |
| #373 |
archive |
active |
n/a
|
|
45.1 GB |
2026-07-22 13:40 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/kg___nih-chest-xrays___data |
| #614 |
archive |
active |
n/a
|
|
70.4 MB |
2026-07-22 13:49 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/kg___orvile___annotated-ultrasound-liver-images-dataset |
| #211 |
media |
active |
860
|
file count |
69.3 MB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/kg___ozlemhakdagli___retinal-fundus-multi-disease-image-dataset-rfmid |
| #548 |
hf_arrow |
active |
3.0K
|
hf meta |
881.5 MB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/kg___raddar___chest-xrays-indiana-university |
| #594 |
hf_arrow |
active |
773
|
hf meta |
166.7 MB |
2026-07-22 13:48 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/kg___sabahesaraki___breast-ultrasound-images-dataset |
| #622 |
hf_arrow |
active |
6.5K
|
hf meta |
374.7 MB |
2026-07-22 13:49 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/kg___siatsyx___ct2usforkidneyseg |
| #244 |
archive |
active |
n/a
|
|
816.0 MB |
2026-07-22 13:35 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/kg___tawsifurrahman___covid19-radiography-database |
| #95 |
hf_arrow |
active |
61.0K
|
hf meta |
5.2 GB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/meditron___xiaoman-zhang___PMC-VQA |
| #228 |
hf_arrow |
active |
n/a
|
|
289.4 GB |
2026-07-22 13:35 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/medtrinity_conversations_1_formatted |
| #629 |
hf_arrow |
active |
n/a
|
|
257.1 GB |
2026-07-22 13:50 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/medtrinity_conversations_2_formatted |
| #140 |
parquet |
active |
n/a
|
|
12.6 TB |
2026-07-22 13:29 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/ms___deepglint___DanQing |
| #852 |
archive |
active |
n/a
|
|
46.6 GB |
2026-07-22 14:13 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/ragusa___MECCANO |
| #309 |
webdataset |
active |
n/a
|
|
117.7 GB |
2026-07-22 13:38 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/rsim___BigEarthNet |
| #192 |
media |
active |
1.3K
|
file count |
2.0 GB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/stanfordaimi___LERA |
| #122 |
hf_arrow |
active |
1.6M
|
hf meta |
2.3 TB |
2026-07-22 13:28 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/swissai___image_mammoth |
| #635 |
hf_arrow |
active |
624.3K
|
hf meta |
412.2 GB |
2026-07-22 13:50 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/swissai___llava_instruct |
| #748 |
hf_arrow |
active |
558.1K
|
hf meta |
88.7 GB |
2026-07-22 13:58 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/swissai___llava_pretrain_cleaned |
| #8 |
archive |
active |
n/a
|
|
12.8 GB |
2026-07-22 13:20 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/swissai___medical_data |
| #427 |
hf_arrow |
active |
101.5K
|
hf meta |
120.9 GB |
2026-07-22 13:43 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/swissai___pixmo_anything___meditron |
| #337 |
hf_arrow |
active |
717.0K
|
hf meta |
400.7 GB |
2026-07-22 13:39 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/swissai___pixmo_cap___meditron |
| #331 |
archive |
active |
n/a
|
|
51.3 KB |
2026-07-22 13:38 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/uci___Breast-Cancer-Wisconsin |
| #783 |
archive |
active |
n/a
|
|
328.2 MB |
2026-07-22 14:10 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/zn___MedPix-2 |
| #762 |
archive |
active |
n/a
|
|
24.2 GB |
2026-07-22 14:09 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/archive/zn___NCT-CRC-HE-100K |
| #29 |
media |
active |
5
|
file count |
3.3 GB |
2026-07-22 13:21 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/benchmark/hf___moonshotai___WorldVQA |
| #754 |
manual |
active |
n/a
|
|
78.4 GB |
2026-07-22 14:08 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/cooldown/hf___YangQiee___HQ-50K |
| #528 |
parquet |
active |
5.7K
|
parquet footer |
672.2 MB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/cooldown/owid___charts |
| #882 |
webdataset |
active |
n/a
|
|
41.4 TB |
2026-07-22 14:14 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/cooldown/s3___smithsonian___OpenAccess |
| #823 |
parquet |
active |
280.5K
|
parquet footer |
228.5 GB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/cooldown/swisstopo___maps_recap |
| #18 |
manual |
active |
n/a
|
|
21.7 GB |
2026-07-22 13:21 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/cooldown/tau-vailab___WAFFLE |
| #665 |
parquet |
active |
n/a
|
|
4.1 TB |
2026-07-22 13:52 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/cooldown/web___nasa___images |
| #155 |
parquet |
active |
50
|
parquet footer |
7.0 MB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/eval/hf___TuringEnterprises___Multimodal-STEM-HLE-plus-plus |
| #660 |
parquet |
active |
40
|
parquet footer |
31.1 MB |
2026-07-22 13:52 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/eval/hf___TuringEnterprises___Open-MM-RL |
| #78 |
parquet |
active |
2.5M
|
parquet footer |
405.9 GB |
2026-07-22 13:26 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/hf___ibm-granite___ChartNet |
| #393 |
parquet |
active |
148.9K
|
parquet footer |
7.9 GB |
2026-07-22 13:41 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/hf___jmhessel___newyorker_caption_contest |
| #457 |
webdataset |
active |
n/a
|
|
2.2 TB |
2026-07-22 13:44 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/hf___minuzero___videokr_train_source |
| #843 |
webdataset |
active |
n/a
|
|
13.0 TB |
2026-07-22 14:13 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/hf___stanford_vision_lab___gpic_source |
| #68 |
parquet |
active |
30.0K
|
parquet footer |
3.0 GB |
2026-07-22 13:26 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/image2text/hf___2077AIDataFoundation___ChartNet_RealWorldChart |
| #185 |
media |
active |
9
|
file count |
7.9 MB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/mathnet/assets |
| #495 |
parquet |
active |
55.6K
|
parquet footer |
705.6 MB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/mathnet/data |
| #793 |
manual |
active |
n/a
|
|
1.7 TB |
2026-07-22 14:10 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/multimodal_textbook/hf___damo_nlp_sg___multimodal_textbook_source |
| #63 |
hf_arrow |
active |
n/a
|
|
647.3 GB |
2026-07-22 13:26 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/non_commercial |
| #683 |
parquet |
active |
485.5K
|
parquet footer |
303.1 GB |
2026-07-22 13:56 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/rl/hf___zlab-princeton___Vero-600k |
| #266 |
webdataset |
active |
n/a
|
|
69.1 GB |
2026-07-22 13:36 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/sft/FineVision/wds |
| #747 |
manual |
active |
n/a
|
|
151.3 GB |
2026-07-22 13:58 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/sft/hf___BIFOLD-BigEarthNetv2-0___BigEarthNet |
| #731 |
webdataset |
active |
n/a
|
|
4.4 GB |
2026-07-22 13:58 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/sft/hf___ClareNie___PersonaVLM-Dataset |
| #769 |
parquet |
active |
58.1K
|
parquet footer |
13.0 GB |
2026-07-22 14:09 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/sft/hf___CorentinDumery___MixCount |
| #513 |
webdataset |
active |
n/a
|
|
97.8 GB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/sft/hf___FreedomIntelligence___TCM-Instruction-Tuning-ShizhenGPT |
| #446 |
archive |
active |
n/a
|
|
146.9 GB |
2026-07-22 13:43 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/sft/hf___General-Medical-AI___GMAI-VL-5.5M |
| #402 |
manual |
active |
n/a
|
|
201.1 GB |
2026-07-22 13:41 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/sft/hf___IPEC-COMMUNITY___EO-Data1.5M |
| #606 |
parquet |
active |
46.1M
|
parquet footer |
11.3 TB |
2026-07-22 13:48 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/sft/hf___InnovatorLab___Innovator-VL-Instruct-46M |
| #563 |
manual |
active |
n/a
|
|
152.9 GB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/sft/hf___JingkunAn___RefSpatial |
| #864 |
archive |
active |
n/a
|
|
816.1 GB |
2026-07-22 14:14 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/sft/hf___OS-Copilot___OS-Atlas-data |
| #759 |
archive |
active |
n/a
|
|
3.4 TB |
2026-07-22 14:09 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/sft/hf___OneThink___OneThinker-train-data |
| #539 |
parquet |
active |
55.6K
|
parquet footer |
738.2 MB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/sft/hf___ShadenA___MathNet |
| #480 |
parquet |
active |
472.9K
|
parquet footer |
213.4 MB |
2026-07-22 13:45 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/sft/hf___allenai___Molmo2-MultiImagePoint |
| #699 |
parquet |
active |
44.7K
|
parquet footer |
45.0 MB |
2026-07-22 13:57 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/sft/hf___allenai___Molmo2-MultiImageQA |
| #85 |
parquet |
active |
37.0K
|
parquet footer |
15.0 GB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/sft/hf___allenai___MolmoPoint-GUISyn |
| #114 |
parquet |
active |
221.5K
|
parquet footer |
31.3 GB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/sft/hf___allenai___pixmo-ask-model-anything |
| #690 |
parquet |
active |
439.1K
|
parquet footer |
166.9 GB |
2026-07-22 13:56 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/sft/hf___allenai___pixmo-cap-qa |
| #6 |
parquet |
active |
102.7K
|
parquet footer |
11.6 GB |
2026-07-22 13:20 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/sft/hf___allenai___pixmo-point-explanations |
| #407 |
parquet |
active |
23.0K
|
parquet footer |
382.5 MB |
2026-07-22 13:42 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/sft/hf___facebook___Common-O |
| #829 |
media |
active |
19.0K
|
file count |
1.8 GB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/sft/hf___google___RSRCC |
| #826 |
hf_arrow |
active |
n/a
|
|
5.7 TB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/sft/hf___mvp-lab___LLaVA-OneVision-1.5-Instruct-Data |
| #440 |
webdataset |
active |
n/a
|
|
274.1 GB |
2026-07-22 13:43 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/sft/hf___mvp-lab___LLaVA-OneVision-2-Data |
| #497 |
manual |
active |
n/a
|
|
789.4 GB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/sft/hf___neulab___PangeaInstruct |
| #604 |
parquet |
active |
22.9K
|
parquet footer |
13.7 GB |
2026-07-22 13:48 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/sft/hf___racineai___VDR_Cooking_Recipes |
| #854 |
parquet |
active |
1.7M
|
parquet footer |
77.2 GB |
2026-07-22 14:13 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/sft/hf___raidium___RadImageNet-VQA |
| #61 |
archive |
active |
n/a
|
|
32.2 GB |
2026-07-22 13:25 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/sft/hf___scimdr___SPIQA_50K_Re |
| #863 |
parquet |
active |
8.2M
|
parquet footer |
1.1 TB |
2026-07-22 14:14 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/sft/hf___sensenova___SenseNova-SI-8M |
| #127 |
media |
active |
17.1K
|
file count |
58.3 GB |
2026-07-22 13:28 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/sft/hf___xiuhuywh___DRIM-VisualReasonHard |
| #717 |
parquet |
active |
7.5M
|
parquet footer |
2.4 TB |
2026-07-22 13:58 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/sft/nemotron_image_training_v3/archive |
| #750 |
webdataset |
active |
n/a
|
|
526.2 GB |
2026-07-22 14:04 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/sft/nemotron_image_training_v3/datasets |
| #877 |
parquet |
active |
6.7M
|
parquet footer |
7.7 TB |
2026-07-22 14:14 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/sft/nemotron_image_training_v3/swissai___Nemotron-Image-Training-v3 |
| #26 |
parquet |
active |
1.1M
|
parquet footer |
3.7 GB |
2026-07-22 13:21 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/sft/text-sft-pre-tts |
| #789 |
parquet |
active |
1.8M
|
parquet footer |
82.9 GB |
2026-07-22 14:10 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/sft_cot/hf___OpenDataArena___MMFineReason-1.8M-Qwen3-VL-235B-Thinking |
| #779 |
parquet |
active |
1.8M
|
parquet footer |
78.7 GB |
2026-07-22 14:10 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/sft_cot/hf___OpenDataArena___MMFineReason-1.8M-Qwen3-VL-235B-Thinking___license_filtered |
| #830 |
hf_arrow |
active |
n/a
|
|
29.1 GB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/sft_cot/hf___mvp-lab___LLaVA-OneVision-1.5-Instruct-Data___llava_cot_100k |
| #421 |
webdataset |
active |
n/a
|
|
113.2 GB |
2026-07-22 13:42 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage1/gh___allenai___medicat |
| #768 |
webdataset |
active |
n/a
|
|
2.0 GB |
2026-07-22 14:09 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage1/gh___nrc-cnrc___COVID-US |
| #547 |
webdataset |
active |
n/a
|
|
5.5 GB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage1/gh___xiaoman-zhang___PMC-VQA |
| #537 |
manual |
active |
n/a
|
|
587.6 GB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage1/hf___UCSC-VLAA___MedTrinity-25M |
| #16 |
hf_arrow |
active |
1.4M
|
hf meta |
188.1 GB |
2026-07-22 13:21 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage1/hf___axiong___pmc_oa |
| #487 |
hf_arrow |
active |
723.7K
|
hf meta |
1.1 TB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage1/hf___mint-medmax___medmax_data |
| #284 |
webdataset |
active |
n/a
|
|
273.8 GB |
2026-07-22 13:36 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage1/hf___vector-institute___open-pmc-18m |
| #222 |
webdataset |
active |
n/a
|
|
99.4 MB |
2026-07-22 13:35 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage1/kg___dasmehdixtr___ddti-thyroid-ultrasound-images |
| #150 |
webdataset |
active |
n/a
|
|
897.1 MB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage1/kg___raddar___chest-xrays-indiana-university |
| #328 |
hf_arrow |
active |
732
|
hf meta |
784.6 MB |
2026-07-22 13:38 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage1/kg___sabahesaraki___breast-ultrasound-images-dataset |
| #73 |
webdataset |
active |
n/a
|
|
398.0 MB |
2026-07-22 13:26 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage1/kg___siatsyx___ct2usforkidneyseg |
| #714 |
webdataset |
active |
n/a
|
|
1.3 GB |
2026-07-22 13:57 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage1/kg___tawsifurrahman___covid19-radiography-database |
| #7 |
webdataset |
active |
n/a
|
|
1.4 TB |
2026-07-22 13:20 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage1/swissai___medtrinity_conv_1 |
| #792 |
webdataset |
active |
n/a
|
|
1.7 TB |
2026-07-22 14:10 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage1/swissai___medtrinity_conv_2 |
| #532 |
webdataset |
active |
n/a
|
|
321.8 MB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage1/zn___MedPix-2 |
| #855 |
webdataset |
active |
n/a
|
|
2.1 TB |
2026-07-22 14:13 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/argimi_finance_interleave |
| #870 |
hf_arrow |
active |
700
|
hf meta |
5.1 GB |
2026-07-22 14:14 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/fs___Open_UFI_and_clinical_IQA |
| #741 |
hf_arrow |
active |
3.0K
|
hf meta |
3.8 GB |
2026-07-22 13:58 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/fs___SLID-E |
| #364 |
webdataset |
active |
n/a
|
|
365.6 MB |
2026-07-22 13:40 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/gh___dataset-ninja___ebhi-seg |
| #787 |
hf_arrow |
active |
9.7K
|
hf meta |
2.9 GB |
2026-07-22 14:10 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/gh___nrc-cnrc___COVID-US |
| #75 |
webdataset |
active |
n/a
|
|
2.0 GB |
2026-07-22 13:26 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/gh___nrc-cnrc___COVID-US___cleaned |
| #226 |
webdataset |
active |
n/a
|
|
605.8 GB |
2026-07-22 13:35 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/google___openimages_v7_dense |
| #163 |
parquet |
active |
5.8M
|
parquet footer |
572.0 GB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___HuggingFaceM4___WebSight |
| #837 |
parquet |
active |
78.2M
|
parquet footer |
686.4 GB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___OleehyO___latex-formulas-80M |
| #668 |
manual |
active |
n/a
|
|
3.1 TB |
2026-07-22 13:54 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___Salesforce___blip3-grounding-50m |
| #661 |
webdataset |
active |
n/a
|
|
2.6 TB |
2026-07-22 13:52 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___Salesforce___blip3-grounding-50m___recap |
| #835 |
parquet |
active |
48.3K
|
parquet footer |
9.5 GB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___Shopify___product-catalogue |
| #187 |
manual |
active |
n/a
|
|
29.3 TB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___Spawning___pd12m-full |
| #588 |
hf_arrow |
active |
4.4M
|
hf meta |
1.6 TB |
2026-07-22 13:48 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___UCSC-VLAA___MedTrinity-25M |
| #834 |
webdataset |
active |
n/a
|
|
571.8 GB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___UCSC-VLAA___MedTrinity-25M___cleaned |
| #687 |
webdataset |
active |
n/a
|
|
23.5 TB |
2026-07-22 13:56 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___UCSC-VLAA___Recap-DataComp-1B___recap_p1 |
| #260 |
manual |
active |
n/a
|
|
1.5 TB |
2026-07-22 13:36 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___ai4ce___EgoPAT3Dv2 |
| #5 |
webdataset |
active |
n/a
|
|
3.6 GB |
2026-07-22 13:20 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___ai4ce___EgoPAT3Dv2___cleaned |
| #307 |
parquet |
active |
191.8K
|
parquet footer |
295.8 GB |
2026-07-22 13:38 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___allenai___Molmo2-SynMultiImageQA |
| #715 |
parquet |
active |
717.0K
|
parquet footer |
1.1 GB |
2026-07-22 13:57 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___allenai___pixmo-cap |
| #203 |
parquet |
active |
707.6K
|
parquet footer |
376.0 GB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___anthracite-org___pixmo-cap-images |
| #712 |
webdataset |
active |
n/a
|
|
3.3 TB |
2026-07-22 13:57 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___artefactory___Argimi-Ardian-Finance-10k-text-image |
| #455 |
manual |
active |
n/a
|
|
140.1 GB |
2026-07-22 13:44 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___axiong___pmc_oa |
| #788 |
manual |
active |
n/a
|
|
140.1 GB |
2026-07-22 14:10 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___axiong___pmc_oa___cleaned |
| #263 |
webdataset |
active |
n/a
|
|
2.2 TB |
2026-07-22 13:36 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___bytedance-research___UNO-1M |
| #519 |
parquet |
active |
23.3K
|
parquet footer |
18.3 GB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___cyberagent___crello |
| #365 |
hf_arrow |
active |
n/a
|
|
7.6 GB |
2026-07-22 13:40 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___google___docci |
| #485 |
hf_arrow |
active |
10.4K
|
hf meta |
18.2 GB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___google___scin |
| #352 |
parquet |
active |
50.0K
|
parquet footer |
38.9 MB |
2026-07-22 13:39 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___jxu124___refcoco |
| #131 |
parquet |
active |
49.8K
|
parquet footer |
46.0 MB |
2026-07-22 13:28 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___jxu124___refcocog |
| #808 |
parquet |
active |
49.9K
|
parquet footer |
39.8 MB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___jxu124___refcocoplus |
| #370 |
archive |
active |
n/a
|
|
230.8 GB |
2026-07-22 13:40 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___liboaccn___MIT-10M |
| #45 |
parquet |
active |
17.6K
|
parquet footer |
2.3 GB |
2026-07-22 13:22 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___lmms-lab___RefCOCO |
| #241 |
parquet |
active |
12.6K
|
parquet footer |
2.1 GB |
2026-07-22 13:35 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___lmms-lab___RefCOCOg |
| #430 |
parquet |
active |
7.6K
|
parquet footer |
526.6 MB |
2026-07-22 13:43 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___lmms-lab___RefCOCOplus |
| #50 |
webdataset |
active |
n/a
|
|
306.7 TB |
2026-07-22 13:24 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___m-a-p___PIN-200M |
| #628 |
webdataset |
active |
n/a
|
|
2.3 TB |
2026-07-22 13:49 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___ma-xu___fine-t2i |
| #625 |
webdataset |
active |
n/a
|
|
314.6 GB |
2026-07-22 13:49 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___mint-medmax___medmax_data |
| #634 |
parquet |
active |
427.8K
|
parquet footer |
11.1 GB |
2026-07-22 13:50 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___nllg___DaTikZ-V4 |
| #24 |
webdataset |
active |
n/a
|
|
2.7 GB |
2026-07-22 13:21 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___openmed-community___multicare-case-images |
| #80 |
webdataset |
active |
n/a
|
|
3.7 GB |
2026-07-22 13:26 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___openmed-community___multicare-images |
| #46 |
hf_arrow |
active |
17.4M
|
hf meta |
594.7 GB |
2026-07-22 13:22 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___vector-institute___open-pmc-18m |
| #83 |
webdataset |
active |
n/a
|
|
255.7 GB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___vector-institute___open-pmc-18m___cleaned |
| #577 |
hf_arrow |
active |
550.4K
|
hf meta |
175.3 GB |
2026-07-22 13:48 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/hf___wisdomik___Quilt-LLaVA-Pretrain |
| #278 |
hf_arrow |
active |
217.4K
|
hf meta |
20.1 GB |
2026-07-22 13:36 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/kg___abhii1929___isic-skin-disease-image-dataset-4-classes |
| #725 |
hf_arrow |
active |
347
|
hf meta |
242.0 MB |
2026-07-22 13:58 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/kg___dasmehdixtr___ddti-thyroid-ultrasound-images |
| #31 |
webdataset |
active |
n/a
|
|
59.7 MB |
2026-07-22 13:21 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/kg___dasmehdixtr___ddti-thyroid-ultrasound-images___cleaned |
| #831 |
webdataset |
active |
n/a
|
|
936.5 MB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/kg___masoudnickparvar___brain-tumor-mri-dataset |
| #501 |
webdataset |
active |
n/a
|
|
945.8 MB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/kg___masoudnickparvar___brain-tumor-mri-dataset___cleaned |
| #86 |
webdataset |
active |
n/a
|
|
72.5 GB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/kg___nih-chest-xrays___data |
| #506 |
webdataset |
active |
n/a
|
|
71.6 GB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/kg___nih-chest-xrays___data___cleaned |
| #210 |
webdataset |
active |
n/a
|
|
219.4 MB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/kg___orvile___annotated-ultrasound-liver-images-dataset |
| #139 |
hf_arrow |
active |
754
|
hf meta |
1.3 GB |
2026-07-22 13:29 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/kg___ozlemhakdagli___retinal-fundus-multi-disease-image-dataset-rfmid |
| #90 |
webdataset |
active |
n/a
|
|
244.2 MB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/kg___sabahesaraki___breast-ultrasound-images-dataset |
| #781 |
webdataset |
active |
n/a
|
|
306.3 MB |
2026-07-22 14:10 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/kg___sabahesaraki___breast-ultrasound-images-dataset___cleaned |
| #708 |
webdataset |
active |
n/a
|
|
2.1 GB |
2026-07-22 13:57 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/kg___sovitrath___diabetic-retinopathy-2015-data-colored-resized |
| #858 |
parquet |
active |
234.6M
|
parquet footer |
46.7 TB |
2026-07-22 14:13 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/mvp-lab__LLaVA-OneVision-1.5-Mid-Training-85M |
| #586 |
hf_arrow |
active |
255.5K
|
hf meta |
536.2 GB |
2026-07-22 13:48 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/swissai___llava_instruct |
| #672 |
hf_arrow |
active |
1.5M
|
hf meta |
1.6 TB |
2026-07-22 13:54 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/swissai___mammoth |
| #371 |
hf_arrow |
active |
51.6K
|
hf meta |
287.2 GB |
2026-07-22 13:40 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/swissai___pixmo_anything |
| #112 |
hf_arrow |
active |
596.6K
|
hf meta |
1.0 TB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/swissai___pixmo_cap |
| #509 |
media |
active |
108.2K
|
file count |
15.3 GB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/visual_genome/images |
| #388 |
parquet |
active |
102.0K
|
parquet footer |
14.4 GB |
2026-07-22 13:41 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/visual_genome/parquet_blip3_clean |
| #232 |
hf_arrow |
active |
236.6K
|
hf meta |
71.6 GB |
2026-07-22 13:35 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/zn___MedMNIST |
| #558 |
webdataset |
active |
n/a
|
|
346.1 MB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/zn___MedPix-2___cleaned |
| #218 |
webdataset |
active |
n/a
|
|
10.3 GB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/vision-datasets/raw/stage2/zn___NCT-CRC-HE-100K |
| #716 |
tokenized |
active |
22.3M
|
megatron idx |
135.1 GB |
2026-07-22 13:57 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/LLaVA-OneVision-1.5-Instruct-Data |
| #110 |
manual |
active |
n/a
|
|
9.1 GB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/alignment/deepvision_rl |
| #295 |
manual |
active |
n/a
|
|
94.7 MB |
2026-07-22 13:37 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/alignment/deepvision_rl_smoke |
| #794 |
parquet |
active |
1.1M
|
parquet footer |
8.9 GB |
2026-07-22 14:10 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/alignment/innovator_rl |
| #81 |
manual |
active |
n/a
|
|
441.1 MB |
2026-07-22 13:26 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/alignment/mllm_dpo |
| #479 |
manual |
active |
n/a
|
|
441.4 MB |
2026-07-22 13:45 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/alignment/mllm_dpo_p2 |
| #322 |
manual |
active |
n/a
|
|
67.2 GB |
2026-07-22 13:38 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/alignment/mmpr_v1_2_p2 |
| #753 |
parquet |
active |
3.6M
|
parquet footer |
261.2 GB |
2026-07-22 14:08 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/alignment/vero_rl |
| #710 |
parquet |
active |
303.1K
|
parquet footer |
2.0 GB |
2026-07-22 13:57 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/alignment/virl_rl |
| #344 |
tokenized |
active |
12.6M
|
megatron idx |
319.6 GB |
2026-07-22 13:39 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/archive |
| #378 |
tokenized |
active |
139.6K
|
megatron idx |
149.4 GB |
2026-07-22 13:41 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/argimi_finance_interleave |
| #732 |
tokenized |
active |
1.6K
|
megatron idx |
54.7 MB |
2026-07-22 13:58 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/art_museums_recap_perlang |
| #357 |
tokenized |
active |
307.9K
|
megatron idx |
7.4 GB |
2026-07-22 13:39 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/bigDocs7_5m |
| #343 |
tokenized |
active |
10.0M
|
megatron idx |
184.2 GB |
2026-07-22 13:39 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/cooldown/image2text |
| #561 |
manual |
active |
n/a
|
|
87.7 MB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/cooldown/interleave |
| #811 |
tokenized |
active |
11.6K
|
megatron idx |
192.1 MB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/cooldown/sft |
| #464 |
tokenized |
active |
10.6M
|
megatron idx |
107.1 GB |
2026-07-22 13:45 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/image2text/art_museums_recap_perlang |
| #550 |
tokenized |
active |
33.7M
|
megatron idx |
191.3 GB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/image2text/blip3_grounding_50m |
| #469 |
tokenized |
active |
30.0K
|
megatron idx |
358.9 MB |
2026-07-22 13:45 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/image2text/chartnet_realworldchart |
| #126 |
tokenized |
active |
14.6M
|
megatron idx |
340.0 GB |
2026-07-22 13:28 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/image2text/commoncatalog_recap_v2 |
| #173 |
tokenized |
active |
427.8K
|
megatron idx |
1.7 GB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/image2text/datikz_v4 |
| #408 |
tokenized |
active |
1
|
megatron idx |
68.6 KB |
2026-07-22 13:42 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/image2text/egopat3dv2/lct |
| #673 |
tokenized |
active |
6.8K
|
megatron idx |
117.0 MB |
2026-07-22 13:55 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/image2text/egopat3dv2/stage2 |
| #28 |
tokenized |
active |
10.6M
|
megatron idx |
16.6 GB |
2026-07-22 13:21 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/image2text/facecaption_15m |
| #208 |
tokenized |
active |
168.4K
|
megatron idx |
4.9 GB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/image2text/fine_t2i_curated |
| #55 |
tokenized |
active |
14.4K
|
megatron idx |
73.7 MB |
2026-07-22 13:25 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/image2text/ign_city_tiles |
| #701 |
tokenized |
active |
241.1K
|
megatron idx |
1.2 GB |
2026-07-22 13:57 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/image2text/ignf_flair_hub |
| #448 |
tokenized |
active |
45.6M
|
megatron idx |
59.3 GB |
2026-07-22 13:43 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/image2text/latex_formulas_80m |
| #301 |
tokenized |
active |
29.4M
|
megatron idx |
13.1 GB |
2026-07-22 13:37 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/image2text/latex_formulas_80m_inline |
| #178 |
tokenized |
active |
90.0M
|
megatron idx |
614.2 GB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/image2text/llava85m_midtrain |
| #559 |
tokenized |
active |
6.9M
|
megatron idx |
20.6 GB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/image2text/medtrinity_full |
| #596 |
tokenized |
active |
8.9M
|
megatron idx |
105.7 GB |
2026-07-22 13:48 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/image2text/megalith_10m_florence2_v2 |
| #772 |
tokenized |
active |
11.8M
|
megatron idx |
122.1 GB |
2026-07-22 14:09 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/image2text/mit_10m_recap_perlang |
| #304 |
tokenized |
active |
4.1K
|
megatron idx |
79.8 MB |
2026-07-22 13:38 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/image2text/nicolas_handwriting_latex |
| #760 |
tokenized |
active |
112.1K
|
megatron idx |
1.9 GB |
2026-07-22 14:09 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/image2text/nih_chest_xray |
| #488 |
tokenized |
active |
1.9M
|
megatron idx |
25.5 GB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/image2text/openimages_v7_recap |
| #757 |
tokenized |
active |
12.5M
|
megatron idx |
334.7 GB |
2026-07-22 14:09 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/image2text/pd12m_full_recap2 |
| #580 |
tokenized |
active |
706.5K
|
megatron idx |
13.5 GB |
2026-07-22 13:48 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/image2text/pixmo_cap_filtered |
| #600 |
tokenized |
active |
1.6M
|
megatron idx |
2.4 GB |
2026-07-22 13:48 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/image2text/pmc_oa |
| #686 |
tokenized |
active |
153.3M
|
megatron idx |
976.5 GB |
2026-07-22 13:56 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/image2text/recap_datacomp_1b |
| #177 |
tokenized |
active |
36.7K
|
megatron idx |
549.4 MB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/image2text/shopify_product_catalogue |
| #610 |
tokenized |
active |
121.8K
|
megatron idx |
4.2 GB |
2026-07-22 13:49 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/image2text/swisstopo/lct |
| #474 |
tokenized |
active |
1.2M
|
megatron idx |
19.3 GB |
2026-07-22 13:45 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/image2text/uno_1m_recap_v3 |
| #422 |
tokenized |
active |
1.5M
|
megatron idx |
48.8 GB |
2026-07-22 13:42 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/image2text/websight |
| #803 |
parquet |
active |
57.3M
|
parquet footer |
150.2 GB |
2026-07-22 14:11 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/interleave/argimi_finance |
| #246 |
parquet |
active |
11.0M
|
parquet footer |
13.5 GB |
2026-07-22 13:35 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/interleave/art_museums_recap |
| #305 |
tokenized |
active |
10.7K
|
megatron idx |
728.4 MB |
2026-07-22 13:38 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/interleave/dailymed_spl/lct |
| #224 |
tokenized |
active |
77.4K
|
megatron idx |
1.3 GB |
2026-07-22 13:35 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/interleave/dailymed_spl/stage2 |
| #199 |
tokenized |
active |
11
|
megatron idx |
455.7 KB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/interleave/medpix/lct |
| #591 |
tokenized |
active |
405
|
megatron idx |
4.0 MB |
2026-07-22 13:48 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/interleave/medpix/stage2 |
| #729 |
parquet |
active |
12.6M
|
parquet footer |
15.7 GB |
2026-07-22 13:58 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/interleave/mit_10m_recap |
| #771 |
parquet |
active |
1.9M
|
parquet footer |
22.0 GB |
2026-07-22 14:09 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/interleave/molmo_syn_multiimage |
| #336 |
tokenized |
active |
938.9K
|
megatron idx |
45.2 GB |
2026-07-22 13:39 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/interleave/pin_200m/lct |
| #164 |
tokenized |
active |
16.6M
|
megatron idx |
152.2 GB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/interleave/pin_200m/stage2 |
| #347 |
tokenized |
active |
18.1K
|
megatron idx |
648.1 MB |
2026-07-22 13:39 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/interleave/shizhen_book_vision |
| #251 |
tokenized |
active |
113.8K
|
megatron idx |
7.8 GB |
2026-07-22 13:35 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/interleave/shizhen_web_vision/lct |
| #341 |
tokenized |
active |
384.1K
|
megatron idx |
6.1 GB |
2026-07-22 13:39 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/interleave/shizhen_web_vision/stage2 |
| #434 |
tokenized |
active |
466.2K
|
megatron idx |
29.8 GB |
2026-07-22 13:43 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/molmo_syn_multiimage/lct |
| #2 |
tokenized |
active |
564.3K
|
megatron idx |
10.5 GB |
2026-07-22 13:20 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/molmo_syn_multiimage/stage2 |
| #196 |
tokenized |
active |
229.1K
|
megatron idx |
1.1 GB |
2026-07-22 13:32 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/bigearthnet |
| #583 |
tokenized |
active |
1.9M
|
megatron idx |
98.5 GB |
2026-07-22 13:48 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/chartverse_1_8m |
| #252 |
tokenized |
active |
134.8K
|
megatron idx |
4.5 GB |
2026-07-22 13:35 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/finevision___CoSyn_400k/lct |
| #718 |
tokenized |
active |
276.1K
|
megatron idx |
5.4 GB |
2026-07-22 13:58 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/finevision___CoSyn_400k/stage2 |
| #565 |
tokenized |
active |
42.7K
|
megatron idx |
293.7 MB |
2026-07-22 13:47 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/finevision___chinesememe_recap_en/stage2 |
| #707 |
tokenized |
active |
3
|
megatron idx |
99.4 KB |
2026-07-22 13:57 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/finevision___lnqa_recap/lct |
| #845 |
tokenized |
active |
302.8K
|
megatron idx |
4.1 GB |
2026-07-22 14:13 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/finevision___lnqa_recap/stage2 |
| #157 |
tokenized |
active |
5.9K
|
megatron idx |
40.1 MB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/finevision___memotion_recap_en/stage2 |
| #723 |
tokenized |
active |
2.2K
|
megatron idx |
72.3 MB |
2026-07-22 13:58 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/finevision___mmevol_judged/lct |
| #19 |
tokenized |
active |
90.2K
|
megatron idx |
792.7 MB |
2026-07-22 13:21 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/finevision___mmevol_judged/stage2 |
| #41 |
tokenized |
active |
87
|
megatron idx |
3.2 MB |
2026-07-22 13:22 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/finevision___multihiertt/lct |
| #319 |
tokenized |
active |
5.4K
|
megatron idx |
91.6 MB |
2026-07-22 13:38 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/finevision___multihiertt/stage2 |
| #773 |
tokenized |
active |
6.8K
|
megatron idx |
25.6 MB |
2026-07-22 14:09 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/finevision___spatialsense_gold/stage2 |
| #96 |
tokenized |
active |
1.3M
|
megatron idx |
2.9 GB |
2026-07-22 13:27 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/gmai_vl_permissive |
| #443 |
tokenized |
active |
1.9M
|
megatron idx |
66.3 GB |
2026-07-22 13:43 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/google_maptrace |
| #531 |
manual |
active |
n/a
|
|
3.0 GB |
2026-07-22 13:46 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/google_rsrcc |
| #694 |
tokenized |
active |
3.2M
|
megatron idx |
125.2 GB |
2026-07-22 13:57 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/innovator_vl_46m/lct |
| #454 |
tokenized |
active |
33.8M
|
megatron idx |
321.6 GB |
2026-07-22 13:44 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/innovator_vl_46m/stage2 |
| #693 |
tokenized |
active |
10.3M
|
megatron idx |
109.6 GB |
2026-07-22 13:56 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/llava_ov_permissive |
| #613 |
tokenized |
active |
780.9K
|
megatron idx |
6.9 GB |
2026-07-22 13:49 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/lov2_osd/stage2 |
| #766 |
tokenized |
active |
245.9K
|
megatron idx |
2.7 GB |
2026-07-22 14:09 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/lov2_roborefer_sim/stage2 |
| #287 |
manual |
active |
n/a
|
|
6.3 GB |
2026-07-22 13:37 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/messytable_si |
| #713 |
tokenized |
active |
3.5M
|
megatron idx |
50.6 GB |
2026-07-22 13:57 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/mmfinereason_1_8m |
| #841 |
tokenized |
active |
1.8M
|
megatron idx |
10.3 GB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/mmfinereason_1_8m_no_cot |
| #174 |
tokenized |
active |
13.0K
|
megatron idx |
648.5 MB |
2026-07-22 13:31 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/molmo2_multiimage_qa/lct |
| #44 |
tokenized |
active |
13.1K
|
megatron idx |
253.7 MB |
2026-07-22 13:22 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/molmo2_multiimage_qa/stage2 |
| #413 |
tokenized |
active |
156.7K
|
megatron idx |
23.8 GB |
2026-07-22 13:42 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/molmo2_syn_multiimage/lct |
| #669 |
tokenized |
active |
30.3K
|
megatron idx |
641.8 MB |
2026-07-22 13:54 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/molmo2_syn_multiimage/stage2 |
| #470 |
tokenized |
active |
36.2K
|
megatron idx |
1.0 GB |
2026-07-22 13:45 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/molmopoint_guisyn |
| #340 |
tokenized |
active |
1.0M
|
megatron idx |
499.8 GB |
2026-07-22 13:39 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/nemotron_image_training_v3/lct |
| #310 |
tokenized |
active |
5.7M
|
megatron idx |
76.6 GB |
2026-07-22 13:38 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/nemotron_image_training_v3/stage2 |
| #812 |
tokenized |
active |
19.7K
|
megatron idx |
129.6 MB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/path_vqa |
| #711 |
manual |
active |
n/a
|
|
1.3 GB |
2026-07-22 13:57 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/personavlm |
| #272 |
tokenized |
active |
59.7K
|
megatron idx |
845.4 MB |
2026-07-22 13:36 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/pixmo_ask_model_anything |
| #800 |
tokenized |
active |
167.3K
|
megatron idx |
3.2 GB |
2026-07-22 14:11 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/pixmo_cap_qa |
| #397 |
tokenized |
active |
110
|
megatron idx |
10.0 MB |
2026-07-22 13:41 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/pubmedvision/lct |
| #584 |
tokenized |
active |
1.3M
|
megatron idx |
7.9 GB |
2026-07-22 13:48 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/pubmedvision/stage2 |
| #658 |
tokenized |
active |
2.7M
|
megatron idx |
412.8 GB |
2026-07-22 13:52 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/sensenova_si_8m/lct |
| #323 |
tokenized |
active |
5.2M
|
megatron idx |
87.6 GB |
2026-07-22 13:38 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/sensenova_si_8m/stage2 |
| #839 |
manual |
active |
n/a
|
|
1.8 GB |
2026-07-22 14:12 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/tcm_shizhen_vision |
| #256 |
tokenized |
active |
11.7K
|
megatron idx |
321.2 MB |
2026-07-22 13:36 |
/capstor/store/cscs/swissai/infra01/vision-datasets/tokenized/sft/vdr_cooking_recipes |