SigLIP2
Datasets
All datasets matching “SigLIP2”openaccess-embeddings-siglip2
metmuseum/openaccess-embeddings-siglip2
Image embeddings for every public-domain artwork in metmuseum/openaccess, produced by google/siglip2-so400m-patch14-384.
Column
Type
Notes
objectID
int64
Primary key — matches objectID in metmuseum/openaccess
embedding
list<float32>
L2-normalised, dim = 1152
model
string
Source model id
dim
int32
Embedding dimension
Image bytes are not stored here; join against the main dataset to recover them.Embedding spec: dim=1152… See the full description on the dataset page: https://huggingface.co/datasets/metmuseum/openaccess-embeddings-siglip2.aloha_real_agilex_nesting_doll-siglip2-droid-ft
aloha_real_agilex_nesting_doll with SigLIP2-DROID targets
This LeRobot v2.1 dataset is a copy of SakikoTogawa/aloha_real_agilex_nesting_doll with observation.concept added.
For every timestep, the three camera images are processed independently by the
fine-tuned SakikoTogawa/siglip2-base-droid vision encoder. The vision_model.pooler_output vectors
(768 dimensions each) are concatenated in the order left wrist, right wrist,
and high camera, producing a 2304-dimensional float32… See the full description on the dataset page: https://huggingface.co/datasets/JackieMM/aloha_real_agilex_nesting_doll-siglip2-droid-ft.openaccess-embeddings-siglip2-naflex
metmuseum/openaccess-embeddings-siglip2-naflex
Image embeddings for every public-domain artwork in metmuseum/openaccess, produced by google/siglip2-so400m-patch16-naflex.
Column
Type
Notes
objectID
int64
Primary key — matches objectID in metmuseum/openaccess
embedding
list<float32>
L2-normalised, dim = 1152
model
string
Source model id
dim
int32
Embedding dimension
Image bytes are not stored here; join against the main dataset to recover them.Embedding spec:… See the full description on the dataset page: https://huggingface.co/datasets/metmuseum/openaccess-embeddings-siglip2-naflex.bl-images-siglip2-index
BL book images - SigLIP2 search index
Derived index for the biglam/british-library-book-images siglip2_embeddings config, built for a text-to-image search Space.
embeddings.npy - float32 (1080814, 1152), L2-normalized, rows ordered by split: covers, embellishments, medium, plates
metadata.parquet - fname, date, year, image_type, split (no vectors)
split_ranges.json - row range per split, so a split filter is a slice
Embeddings from google/siglip2-so400m-patch16-256. Because… See the full description on the dataset page: https://huggingface.co/datasets/davanstrien/bl-images-siglip2-index.aloha_real_agilex_clean_cup_drawer_and_clean_cube_container-20250809-siglip2-droid-ft
aloha_real_agilex_clean_cup_drawer_and_clean_cube_container-20250809 with SigLIP2-DROID targets
This LeRobot v2.1 dataset is a copy of SakikoTogawa/aloha_real_agilex_clean_cup_drawer_and_clean_cube_container-20250809 with observation.concept added.
For every timestep, the three camera images are processed independently by the
fine-tuned SakikoTogawa/siglip2-base-droid vision encoder. The vision_model.pooler_output vectors
(768 dimensions each) are concatenated in the order left… See the full description on the dataset page: https://huggingface.co/datasets/JackieMM/aloha_real_agilex_clean_cup_drawer_and_clean_cube_container-20250809-siglip2-droid-ft.aloha_real_agilex_folding_fabric-siglip2-droid-ft
aloha_real_agilex_folding_fabric with SigLIP2-DROID targets
This LeRobot v2.1 dataset is a copy of SakikoTogawa/aloha_real_agilex_folding_fabric with observation.concept added.
For every timestep, the three camera images are processed independently by the
fine-tuned SakikoTogawa/siglip2-base-droid vision encoder. The vision_model.pooler_output vectors
(768 dimensions each) are concatenated in the order left wrist, right wrist,
and high camera, producing a 2304-dimensional… See the full description on the dataset page: https://huggingface.co/datasets/JackieMM/aloha_real_agilex_folding_fabric-siglip2-droid-ft.