Salesforce/blip-image-captioning-base

Explore Salesforce/blip-image-captioning-base: model specifications, capabilities, benchmark results, platform pricing and original sources.

huggingface/Salesforce/blip-image-captioning-base

Specifications & capabilities

Published model ID
blip-image-captioning-base

Evaluations

1–6 / 6

MTEB

63.094%

source id
mteb
leaderboard name
MTEB Clustering
dimension
embedding
metric
Average task score
rank
69
sample size
5
aggregation scope
splits
  • test
  • valid
subsets
  • default
task_count
5
task_names
  • CIFAR100Clustering
  • CIFAR10Clustering
  • ImageNet10Clustering
  • ImageNetDog15Clustering
  • TinyImageNetClustering
sample_size
5
subset_count
1
subset_sample
  • default
aggregation_method
mean-of-task-means
model_revision_count
1
model_revision_sample
  • 89b09ea1789f7addf2f6d6f0dfc4ce10ab58ef84
source model id
Salesforce/blip-image-captioning-base
Original result ↗

MTEB

76.972%

source id
mteb
leaderboard name
MTEB Classification
dimension
embedding
metric
Average task score
rank
112
sample size
2
aggregation scope
splits
  • test
  • validation
subsets
  • default
task_count
2
task_names
  • Food101Classification
  • OxfordFlowersClassification
sample_size
2
subset_count
1
subset_sample
  • default
aggregation_method
mean-of-task-means
model_revision_count
1
model_revision_sample
  • 89b09ea1789f7addf2f6d6f0dfc4ce10ab58ef84
source model id
Salesforce/blip-image-captioning-base
Original result ↗

MTEB

47.266%

source id
mteb
leaderboard name
MTEB Semantic Similarity
dimension
embedding
metric
Average task score
rank
495
sample size
40
aggregation scope
splits
  • dev
  • test
subsets
  • ar-ar
  • de
  • default
  • en
  • en-ar
  • en-de
  • en-en
  • en-tr
  • es
  • es-en
  • es-es
  • fr
  • fr-en
  • it
  • it-en
  • ko-ko
  • nl
  • nl-en
  • pl
  • pt
  • ru
  • zh
task_count
11
task_names
  • STS12VisualSTS
  • STS13VisualSTS
  • STS14VisualSTS
  • STS15VisualSTS
  • STS16VisualSTS
  • STS17MultilingualVisualSTS
  • STSBenchmarkMultilingualVisualSTS
  • VisualSTS-b-Eng
  • VisualSTS-b-Multilingual
  • VisualSTS17Eng
  • VisualSTS17Multilingual
sample_size
40
subset_count
22
subset_sample
  • ar-ar
  • de
  • default
  • en
  • en-ar
  • en-de
  • en-en
  • en-tr
  • es
  • es-en
  • es-es
  • fr
  • fr-en
  • it
  • it-en
  • ko-ko
  • nl
  • nl-en
  • pl
  • pt
  • ru
  • zh
aggregation_method
mean-of-task-means
model_revision_count
1
model_revision_sample
  • 89b09ea1789f7addf2f6d6f0dfc4ce10ab58ef84
source model id
Salesforce/blip-image-captioning-base
Original result ↗

MTEB

31.689%

source id
mteb
leaderboard name
MTEB Other
dimension
embedding
metric
Average task score
rank
737
sample size
57
aggregation scope
splits
  • test
  • validation
subsets
  • default
task_count
57
task_names
  • AROCocoOrder
  • AROFlickrOrder
  • AROVisualAttribution
  • AROVisualRelation
  • BLINKIT2IMultiChoice
  • BLINKIT2TMultiChoice
  • Birdsnap
  • BirdsnapZeroShot
  • CIFAR10
  • CIFAR100
  • CIFAR100ZeroShot
  • CIFAR10ZeroShot
  • CLEVRCountZeroShot
  • CLEVRZeroShot
  • CVBenchCount
  • CVBenchDepth
  • CVBenchDistance
  • CVBenchRelation
  • Caltech101
  • Caltech101ZeroShot
  • Country211
  • Country211ZeroShot
  • DTD
  • DTDZeroShot
  • EuroSAT
  • EuroSATZeroShot
  • FER2013
  • FER2013ZeroShot
  • FGVCAircraft
  • FGVCAircraftZeroShot
  • Food101ZeroShot
  • GTSRB
  • GTSRBZeroShot
  • ImageCoDe
  • Imagenet1k
  • Imagenet1kZeroShot
  • MNIST
  • MNISTZeroShot
  • OxfordPets
  • OxfordPetsZeroShot
  • PatchCamelyon
  • PatchCamelyonZeroShot
  • RESISC45
  • RESISC45ZeroShot
  • RenderedSST2
  • STL10
  • STL10ZeroShot
  • SUN397
  • SUN397ZeroShot
  • SciMMIR
  • StanfordCars
  • StanfordCarsZeroShot
  • SugarCrepe
  • UCF101
  • UCF101ZeroShot
  • VOC2007
  • Winoground
sample_size
57
subset_count
1
subset_sample
  • default
aggregation_method
mean-of-task-means
model_revision_count
1
model_revision_sample
  • 89b09ea1789f7addf2f6d6f0dfc4ce10ab58ef84
source model id
Salesforce/blip-image-captioning-base
Original result ↗

MTEB

8.147%

source id
mteb
leaderboard name
MTEB Retrieval
dimension
embedding
metric
Average task score
rank
857
sample size
104
aggregation scope
splits
  • test
subsets
  • ar
  • bg
  • bn
  • cs
  • da
  • de
  • default
  • el
  • en
  • es
  • et
  • fa
  • fi
  • fil
  • fr
  • he
  • hi
  • hr
  • hu
  • id
  • it
  • ja
  • ko
  • mi
  • nl
  • no
  • pl
  • pt
  • quz
  • ro
  • ru
  • sv
  • sw
  • te
  • th
  • tr
  • uk
  • vi
  • zh
task_count
52
task_names
  • BLINKIT2IRetrieval
  • BLINKIT2TRetrieval
  • CIRRIT2IRetrieval
  • CUB200I2IRetrieval
  • EDIST2ITRetrieval
  • FORBI2IRetrieval
  • Fashion200kI2TRetrieval
  • Fashion200kT2IRetrieval
  • FashionIQIT2IRetrieval
  • Flickr30kI2TRetrieval
  • Flickr30kT2IRetrieval
  • GLDv2I2IRetrieval
  • GLDv2I2TRetrieval
  • HatefulMemesI2TRetrieval
  • HatefulMemesT2IRetrieval
  • ImageCoDeT2IRetrieval
  • InfoSeekIT2ITRetrieval
  • InfoSeekIT2TRetrieval
  • METI2IRetrieval
  • MSCOCOI2TRetrieval
  • MSCOCOT2IRetrieval
  • MemotionI2TRetrieval
  • MemotionT2IRetrieval
  • NIGHTSI2IRetrieval
  • OVENIT2ITRetrieval
  • OVENIT2TRetrieval
  • RP2kI2IRetrieval
  • SOPI2IRetrieval
  • SciMMIRI2TRetrieval
  • SciMMIRT2IRetrieval
  • SketchyI2IRetrieval
  • StanfordCarsI2IRetrieval
  • TUBerlinT2IRetrieval
  • VQA2IT2TRetrieval
  • VidoreArxivQARetrieval
  • VidoreDocVQARetrieval
  • VidoreInfoVQARetrieval
  • VidoreShiftProjectRetrieval
  • VidoreSyntheticDocQAAIRetrieval
  • VidoreSyntheticDocQAEnergyRetrieval
  • VidoreSyntheticDocQAGovernmentReportsRetrieval
  • VidoreSyntheticDocQAHealthcareIndustryRetrieval
  • VidoreTabfquadRetrieval
  • VidoreTatdqaRetrieval
  • VisualNewsI2TRetrieval
  • VisualNewsT2IRetrieval
  • VizWizIT2TRetrieval
  • WITT2IRetrieval
  • WebQAT2ITRetrieval
  • WebQAT2TRetrieval
  • XFlickr30kCoT2IRetrieval
  • XM3600T2IRetrieval
sample_size
104
subset_count
39
subset_sample
  • ar
  • bg
  • bn
  • cs
  • da
  • de
  • default
  • el
  • en
  • es
  • et
  • fa
  • fi
  • fil
  • fr
  • he
  • hi
  • hr
  • hu
  • id
  • it
  • ja
  • ko
  • mi
  • nl
  • no
  • pl
  • pt
  • quz
  • ro
aggregation_method
mean-of-task-means
model_revision_count
1
model_revision_sample
  • 89b09ea1789f7addf2f6d6f0dfc4ce10ab58ef84
source model id
Salesforce/blip-image-captioning-base
Original result ↗

MTEB

25.349%

source id
mteb
leaderboard name
MTEB Overall
dimension
embedding
metric
Average task score
rank
923
sample size
208
aggregation scope
splits
  • dev
  • test
  • valid
  • validation
subsets
  • ar
  • ar-ar
  • bg
  • bn
  • cs
  • da
  • de
  • default
  • el
  • en
  • en-ar
  • en-de
  • en-en
  • en-tr
  • es
  • es-en
  • es-es
  • et
  • fa
  • fi
  • fil
  • fr
  • fr-en
  • he
  • hi
  • hr
  • hu
  • id
  • it
  • it-en
  • ja
  • ko
  • ko-ko
  • mi
  • nl
  • nl-en
  • no
  • pl
  • pt
  • quz
  • ro
  • ru
  • sv
  • sw
  • te
  • th
  • tr
  • uk
  • vi
  • zh
task_count
127
task_names
  • AROCocoOrder
  • AROFlickrOrder
  • AROVisualAttribution
  • AROVisualRelation
  • BLINKIT2IMultiChoice
  • BLINKIT2IRetrieval
  • BLINKIT2TMultiChoice
  • BLINKIT2TRetrieval
  • Birdsnap
  • BirdsnapZeroShot
  • CIFAR10
  • CIFAR100
  • CIFAR100Clustering
  • CIFAR100ZeroShot
  • CIFAR10Clustering
  • CIFAR10ZeroShot
  • CIRRIT2IRetrieval
  • CLEVRCountZeroShot
  • CLEVRZeroShot
  • CUB200I2IRetrieval
  • CVBenchCount
  • CVBenchDepth
  • CVBenchDistance
  • CVBenchRelation
  • Caltech101
  • Caltech101ZeroShot
  • Country211
  • Country211ZeroShot
  • DTD
  • DTDZeroShot
  • EDIST2ITRetrieval
  • EuroSAT
  • EuroSATZeroShot
  • FER2013
  • FER2013ZeroShot
  • FGVCAircraft
  • FGVCAircraftZeroShot
  • FORBI2IRetrieval
  • Fashion200kI2TRetrieval
  • Fashion200kT2IRetrieval
  • FashionIQIT2IRetrieval
  • Flickr30kI2TRetrieval
  • Flickr30kT2IRetrieval
  • Food101Classification
  • Food101ZeroShot
  • GLDv2I2IRetrieval
  • GLDv2I2TRetrieval
  • GTSRB
  • GTSRBZeroShot
  • HatefulMemesI2TRetrieval
  • HatefulMemesT2IRetrieval
  • ImageCoDe
  • ImageCoDeT2IRetrieval
  • ImageNet10Clustering
  • ImageNetDog15Clustering
  • Imagenet1k
  • Imagenet1kZeroShot
  • InfoSeekIT2ITRetrieval
  • InfoSeekIT2TRetrieval
  • METI2IRetrieval
  • MNIST
  • MNISTZeroShot
  • MSCOCOI2TRetrieval
  • MSCOCOT2IRetrieval
  • MemotionI2TRetrieval
  • MemotionT2IRetrieval
  • NIGHTSI2IRetrieval
  • OVENIT2ITRetrieval
  • OVENIT2TRetrieval
  • OxfordFlowersClassification
  • OxfordPets
  • OxfordPetsZeroShot
  • PatchCamelyon
  • PatchCamelyonZeroShot
  • RESISC45
  • RESISC45ZeroShot
  • RP2kI2IRetrieval
  • RenderedSST2
  • SOPI2IRetrieval
  • STL10
  • STL10ZeroShot
  • STS12VisualSTS
  • STS13VisualSTS
  • STS14VisualSTS
  • STS15VisualSTS
  • STS16VisualSTS
  • STS17MultilingualVisualSTS
  • STSBenchmarkMultilingualVisualSTS
  • SUN397
  • SUN397ZeroShot
  • SciMMIR
  • SciMMIRI2TRetrieval
  • SciMMIRT2IRetrieval
  • SketchyI2IRetrieval
  • StanfordCars
  • StanfordCarsI2IRetrieval
  • StanfordCarsZeroShot
  • SugarCrepe
  • TUBerlinT2IRetrieval
  • TinyImageNetClustering
  • UCF101
  • UCF101ZeroShot
  • VOC2007
  • VQA2IT2TRetrieval
  • VidoreArxivQARetrieval
  • VidoreDocVQARetrieval
  • VidoreInfoVQARetrieval
  • VidoreShiftProjectRetrieval
  • VidoreSyntheticDocQAAIRetrieval
  • VidoreSyntheticDocQAEnergyRetrieval
  • VidoreSyntheticDocQAGovernmentReportsRetrieval
  • VidoreSyntheticDocQAHealthcareIndustryRetrieval
  • VidoreTabfquadRetrieval
  • VidoreTatdqaRetrieval
  • VisualNewsI2TRetrieval
  • VisualNewsT2IRetrieval
  • VisualSTS-b-Eng
  • VisualSTS-b-Multilingual
  • VisualSTS17Eng
  • VisualSTS17Multilingual
  • VizWizIT2TRetrieval
  • WITT2IRetrieval
  • WebQAT2ITRetrieval
  • WebQAT2TRetrieval
  • Winoground
  • XFlickr30kCoT2IRetrieval
  • XM3600T2IRetrieval
sample_size
208
subset_count
50
subset_sample
  • ar
  • ar-ar
  • bg
  • bn
  • cs
  • da
  • de
  • default
  • el
  • en
  • en-ar
  • en-de
  • en-en
  • en-tr
  • es
  • es-en
  • es-es
  • et
  • fa
  • fi
  • fil
  • fr
  • fr-en
  • he
  • hi
  • hr
  • hu
  • id
  • it
  • it-en
aggregation_method
mean-of-task-means
model_revision_count
1
model_revision_sample
  • 89b09ea1789f7addf2f6d6f0dfc4ce10ab58ef84
source model id
Salesforce/blip-image-captioning-base
Original result ↗

Provider specifications & access

1–1 / 1

BLIP Image Captioning Base ↗

source model id
publishers/salesforce/models/blip-image-captioning-base@blip-image-captioning-base
hosting
vertex-self-deployed
platforms
  • Google Cloud Vertex AI
architecture
input_modalities
    output_modalities
      capabilities

        Original sources

        1–7 / 7

        Hugging Face · Salesforce/blip-image-captioning-base ↗

        Google Cloud · Model page ↗

        Google Cloud · Model documentation ↗

        arXiv · Paper · 2201.12086 ↗

        Google Cloud · Catalog ↗

        Hugging Face · Catalog ↗

        Hugging Face · Catalog ↗

        Source links

        1–3 / 3

        Hugging Face model card

        1–1 / 1

        Explore more models

        Models

        Loading
        EVIDENCE / COMPARISON

        Benchmarks

        Explore every benchmark

        Loading

        These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

        Install TensorTrace