royokong/e5-v

`royokong/e5-v` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/r…

azureFoundry/HuggingFace/royokong-e5-v@1

royokong/e5-v powered by Text Generation Inference (TGI)

Send Request

You can use cURL or any REST Client to send a request to the AzureML endpoint with your AzureML token.

curl <AZUREML_ENDPOINT_URL> \
    -X POST \
    -d '{"inputs":"What is Deep Learning?"}' \
    -H "Authorization: Bearer <AZUREML_TOKEN>" \
    -H "Content-Type: application/json"

Supported Parameters

  • inputs (string): Input prompt.
  • parameters (object):
    • best_of (integer): Generate best_of sequences and return the one if the highest token logprobs.
    • decoder_input_details (boolean): Whether to return decoder input token logprobs and ids.
    • details (boolean): Whether to return generation details.
    • do_sample (boolean): Activate logits sampling.
    • frequency_penalty (float): The parameter for frequency penalty. 1.0 means no penalty Penalize new tokens based on their existing frequency in the text so far, decreasing the model’s likelihood to repeat the same line verbatim.
    • grammar (object): One of the following
      • #1 (object):
        • type (enum): Possible values: json.
        • value (string): A string that represents a JSON Schema. JSON Schema is a declarative language that allows to annotate JSON documents with types and descriptions.
      • #2 (object):
        • type (enum): Possible values: regex.
        • value (string): The regular expression.
      • #3 (object):
        • type (enum): Possible values: json_schema.
        • value (object):
          • name (string): Optional name identifier for the schema
          • schema (object): The actual JSON schema definition
    • max_new_tokens (integer): Maximum number of tokens to generate.
    • repetition_penalty (float): The parameter for repetition penalty. 1.0 means no penalty. See this paper for more details.
    • return_full_text (boolean): Whether to prepend the prompt to the generated text
    • seed (integer): Random sampling seed.
    • stop (string[]): Stop generating tokens if a member of stop is generated.
    • temperature (float): The value used to module the logits distribution.
    • top_k (integer): The number of highest probability vocabulary tokens to keep for top-k-filtering.
    • top_n_tokens (integer): The number of highest probability vocabulary tokens to keep for top-n-filtering.
    • top_p (float): Top-p value for nucleus sampling.
    • truncate (integer): Truncate inputs tokens to the given size.
    • typical_p (float): Typical Decoding mass See Typical Decoding for Natural Language Generation for more information.
    • watermark (boolean): Watermarking with A Watermark for Large Language Models.
    • stream (boolean): Whether to stream the output tokens or not. Defaults to false.

Example payload

{
  "inputs": "What is Deep Learning?",
  "parameters": {
    "do_sample": true,
    "top_p": 0.95,
    "temperature": 0.2,
    "top_k": 50,
    "max_new_tokens": 256,
    "repetition_penalty": 1.03,
    "stop": ["\nUser:", "<|endoftext|>", "</s>"]
  }
}

OpenAI Chat Completion API compatibility

Additionally, Text Generation Inference (TGI) offers an OpenAI Chat Completion API compatible layer under the endpoint /v1/chat/completions, check the full specification in the OpenAI Chat Completion Create Documentation.

Specifications & capabilities

Input
text, image
Output
text
Published model ID
e5-v
Capabilities
multimodal, visionInput

Evaluations

1–6 / 6

MTEB

89.735%

source id
mteb
leaderboard name
MTEB Classification
dimension
embedding
metric
Average task score
rank
41
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
  • 0c1f22679417b3ae925d779442221c40cd1861ab
source model id
royokong/e5-v
Original result ↗

MTEB

70.045%

source id
mteb
leaderboard name
MTEB Clustering
dimension
embedding
metric
Average task score
rank
46
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
  • 0c1f22679417b3ae925d779442221c40cd1861ab
source model id
royokong/e5-v
Original result ↗

MTEB

57.827%

source id
mteb
leaderboard name
MTEB Other
dimension
embedding
metric
Average task score
rank
291
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
  • 0c1f22679417b3ae925d779442221c40cd1861ab
source model id
royokong/e5-v
Original result ↗

MTEB

68.237%

source id
mteb
leaderboard name
MTEB Semantic Similarity
dimension
embedding
metric
Average task score
rank
356
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
  • 0c1f22679417b3ae925d779442221c40cd1861ab
source model id
royokong/e5-v
Original result ↗

MTEB

51.978%

source id
mteb
leaderboard name
MTEB Overall
dimension
embedding
metric
Average task score
rank
528
sample size
227
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
  • english
  • es
  • es-en
  • es-es
  • et
  • fa
  • fi
  • fil
  • fr
  • fr-en
  • french
  • german
  • he
  • hi
  • hr
  • hu
  • id
  • it
  • it-en
  • ja
  • ko
  • ko-ko
  • mi
  • nl
  • nl-en
  • no
  • pl
  • pt
  • quz
  • ro
  • ru
  • spanish
  • sv
  • sw
  • te
  • th
  • tr
  • uk
  • vi
  • zh
task_count
137
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
  • ROxfordEasyI2IRetrieval
  • ROxfordHardI2IRetrieval
  • ROxfordMediumI2IRetrieval
  • RP2kI2IRetrieval
  • RParisEasyI2IRetrieval
  • RParisHardI2IRetrieval
  • RParisMediumI2IRetrieval
  • 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
  • Vidore2BioMedicalLecturesRetrieval
  • Vidore2ESGReportsHLRetrieval
  • Vidore2ESGReportsRetrieval
  • Vidore2EconomicsReportsRetrieval
  • 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
227
subset_count
54
subset_sample
  • ar
  • ar-ar
  • bg
  • bn
  • cs
  • da
  • de
  • default
  • el
  • en
  • en-ar
  • en-de
  • en-en
  • en-tr
  • english
  • es
  • es-en
  • es-es
  • et
  • fa
  • fi
  • fil
  • fr
  • fr-en
  • french
  • german
  • he
  • hi
  • hr
  • hu
aggregation_method
mean-of-task-means
model_revision_count
1
model_revision_sample
  • 0c1f22679417b3ae925d779442221c40cd1861ab
source model id
royokong/e5-v
Original result ↗

MTEB

41.041%

source id
mteb
leaderboard name
MTEB Retrieval
dimension
embedding
metric
Average task score
rank
584
sample size
123
aggregation scope
splits
  • test
subsets
  • ar
  • bg
  • bn
  • cs
  • da
  • de
  • default
  • el
  • en
  • english
  • es
  • et
  • fa
  • fi
  • fil
  • fr
  • french
  • german
  • he
  • hi
  • hr
  • hu
  • id
  • it
  • ja
  • ko
  • mi
  • nl
  • no
  • pl
  • pt
  • quz
  • ro
  • ru
  • spanish
  • sv
  • sw
  • te
  • th
  • tr
  • uk
  • vi
  • zh
task_count
62
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
  • ROxfordEasyI2IRetrieval
  • ROxfordHardI2IRetrieval
  • ROxfordMediumI2IRetrieval
  • RP2kI2IRetrieval
  • RParisEasyI2IRetrieval
  • RParisHardI2IRetrieval
  • RParisMediumI2IRetrieval
  • SOPI2IRetrieval
  • SciMMIRI2TRetrieval
  • SciMMIRT2IRetrieval
  • SketchyI2IRetrieval
  • StanfordCarsI2IRetrieval
  • TUBerlinT2IRetrieval
  • VQA2IT2TRetrieval
  • Vidore2BioMedicalLecturesRetrieval
  • Vidore2ESGReportsHLRetrieval
  • Vidore2ESGReportsRetrieval
  • Vidore2EconomicsReportsRetrieval
  • VidoreArxivQARetrieval
  • VidoreDocVQARetrieval
  • VidoreInfoVQARetrieval
  • VidoreShiftProjectRetrieval
  • VidoreSyntheticDocQAAIRetrieval
  • VidoreSyntheticDocQAEnergyRetrieval
  • VidoreSyntheticDocQAGovernmentReportsRetrieval
  • VidoreSyntheticDocQAHealthcareIndustryRetrieval
  • VidoreTabfquadRetrieval
  • VidoreTatdqaRetrieval
  • VisualNewsI2TRetrieval
  • VisualNewsT2IRetrieval
  • VizWizIT2TRetrieval
  • WITT2IRetrieval
  • WebQAT2ITRetrieval
  • WebQAT2TRetrieval
  • XFlickr30kCoT2IRetrieval
  • XM3600T2IRetrieval
sample_size
123
subset_count
43
subset_sample
  • ar
  • bg
  • bn
  • cs
  • da
  • de
  • default
  • el
  • en
  • english
  • es
  • et
  • fa
  • fi
  • fil
  • fr
  • french
  • german
  • he
  • hi
  • hr
  • hu
  • id
  • it
  • ja
  • ko
  • mi
  • nl
  • no
  • pl
aggregation_method
mean-of-task-means
model_revision_count
1
model_revision_sample
  • 0c1f22679417b3ae925d779442221c40cd1861ab
source model id
royokong/e5-v
Original result ↗

Provider specifications & access

1–1 / 1

royokong/e5-v ↗

source model id
HuggingFace/royokong-e5-v@1
hosting
foundry-managed-compute
platforms
  • Microsoft Foundry
license
unknown
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities

    Original sources

    1–5 / 5

    Hugging Face · royokong/e5-v ↗

    Microsoft Foundry · Model page ↗

    Microsoft Foundry · Model documentation ↗

    Hugging Face · Catalog ↗

    Microsoft Foundry · Catalog ↗

    Source links

    1–2 / 2

    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