nlpai-lab/KoE5

`nlpai-lab/KoE5` powered by Text Embeddings Inference (TEI) - [Original Model Card](https://huggingface.co/nlpai-lab/KoE5) - [Text Embeddings Inference Documentation](https://huggingface.co/docs/text…

azureFoundry/HuggingFace/nlpai-lab-koe5@1

nlpai-lab/KoE5 powered by Text Embeddings Inference (TEI)

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): The input sentence to create the embeddings for.
  • parameters (object):
    • normalize: Whether to normalize returned vectors to have length 1. Defaults to False.
    • prompt_name: The name of the prompt to use for encoding. Must be a key in the prompts dictionary, which is either set in the constructor or loaded from the model configuration. For example if prompt_name is "query" and the prompts is {"query": "query: ", ...}, then the sentence "What is the capital of France?" will be encoded as "query: What is the capital of France?" because the sentence is appended to the prompt. If prompt is also set, this argument is ignored. Defaults to null.
    • truncate: Truncate the inputs that are longer than the maximum supported size. Defaults to False.
    • truncation_direction: Can either be "left" or "right", defaults to "right". Truncating to the "right" means that tokens are removed from the end of the sequence until the maximum supported size is matched, whilst truncating to the "left" means from the beginning of the sequence.

Example payload

{
  "inputs": "What is Deep Learning?",
  "normalize": false,
  "prompt_name": null,
  "truncate": false,
  "truncation_direction": "right"
}

OpenAI Embeddings API compatibility

Additionally, Text Embeddings Inference (TEI) offers an OpenAI Chat Completion API compatible layer under the endpoint /v1/embeddings, check the full specification in the OpenAI Embeddings Create Documentation.

Specifications & capabilities

Input
text
Output
embeddings
Published model ID
KoE5
Capabilities
embeddings

Evaluations

1–7 / 7

MTEB

72.44%

source id
mteb
leaderboard name
MTEB Other
dimension
embedding
metric
Average task score
rank
62
sample size
6
aggregation scope
splits
  • dev
  • test
  • validation
subsets
  • default
  • korean
task_count
6
task_names
  • KLUE-NLI
  • KLUE-TC
  • Ko-StrategyQA
  • KorNLI
  • LawIRKo
  • PublicHealthQA
sample_size
6
subset_count
2
subset_sample
  • default
  • korean
aggregation_method
mean-of-task-means
model_revision_count
1
model_revision_sample
  • bc6d284c60fe5a973e74c1751b92594c9f581213
source model id
nlpai-lab/KoE5
Original result ↗

MTEB

83.764%

source id
mteb
leaderboard name
MTEB Semantic Similarity
dimension
embedding
metric
Average task score
rank
86
sample size
13
aggregation scope
splits
  • test
  • validation
subsets
  • ar-ar
  • default
  • en-ar
  • en-de
  • en-en
  • en-tr
  • es-en
  • es-es
  • fr-en
  • it-en
  • ko-ko
  • nl-en
task_count
3
task_names
  • KLUE-STS
  • KorSTS
  • STS17
sample_size
13
subset_count
12
subset_sample
  • ar-ar
  • default
  • en-ar
  • en-de
  • en-en
  • en-tr
  • es-en
  • es-es
  • fr-en
  • it-en
  • ko-ko
  • nl-en
aggregation_method
mean-of-task-means
model_revision_count
1
model_revision_sample
  • bc6d284c60fe5a973e74c1751b92594c9f581213
source model id
nlpai-lab/KoE5
Original result ↗

MTEB

58.451%

source id
mteb
leaderboard name
MTEB Clustering
dimension
embedding
metric
Average task score
rank
104
sample size
199
aggregation scope
splits
  • test
subsets
  • ace_Latn
  • acm_Arab
  • acq_Arab
  • aeb_Arab
  • afr_Latn
  • ajp_Arab
  • aka_Latn
  • als_Latn
  • amh_Ethi
  • apc_Arab
  • arb_Latn
  • ars_Arab
  • ary_Arab
  • arz_Arab
  • asm_Beng
  • ast_Latn
  • awa_Deva
  • ayr_Latn
  • azb_Arab
  • azj_Latn
  • bak_Cyrl
  • bam_Latn
  • ban_Latn
  • bel_Cyrl
  • bem_Latn
  • ben_Beng
  • bho_Deva
  • bjn_Latn
  • bod_Tibt
  • bos_Latn
  • bug_Latn
  • bul_Cyrl
  • cat_Latn
  • ceb_Latn
  • ces_Latn
  • cjk_Latn
  • ckb_Arab
  • crh_Latn
  • cym_Latn
  • dan_Latn
  • default
  • deu_Latn
  • dik_Latn
  • dyu_Latn
  • dzo_Tibt
  • ell_Grek
  • eng_Latn
  • epo_Latn
  • est_Latn
  • eus_Latn
  • ewe_Latn
  • fao_Latn
  • fij_Latn
  • fin_Latn
  • fon_Latn
  • fra_Latn
  • fur_Latn
  • fuv_Latn
  • gaz_Latn
  • gla_Latn
  • gle_Latn
  • glg_Latn
  • grn_Latn
  • guj_Gujr
  • hat_Latn
  • hau_Latn
  • heb_Hebr
  • hin_Deva
  • hne_Deva
  • hrv_Latn
  • hun_Latn
  • hye_Armn
  • ibo_Latn
  • ilo_Latn
  • ind_Latn
  • isl_Latn
  • ita_Latn
  • jav_Latn
  • jpn_Jpan
  • kab_Latn
  • kac_Latn
  • kam_Latn
  • kan_Knda
  • kas_Deva
  • kat_Geor
  • kaz_Cyrl
  • kbp_Latn
  • kea_Latn
  • khk_Cyrl
  • khm_Khmr
  • kik_Latn
  • kin_Latn
  • kir_Cyrl
  • kmb_Latn
  • kmr_Latn
  • knc_Latn
  • kon_Latn
  • kor_Hang
  • lao_Laoo
  • lij_Latn
  • lim_Latn
  • lin_Latn
  • lit_Latn
  • lmo_Latn
  • ltg_Latn
  • ltz_Latn
  • lua_Latn
  • lug_Latn
  • luo_Latn
  • lus_Latn
  • lvs_Latn
  • mag_Deva
  • mai_Deva
  • mal_Mlym
  • mar_Deva
  • min_Latn
  • mkd_Cyrl
  • mlt_Latn
  • mni_Beng
  • mos_Latn
  • mri_Latn
  • mya_Mymr
  • nld_Latn
  • nno_Latn
  • nob_Latn
  • npi_Deva
  • nqo_Nkoo
  • nso_Latn
  • nus_Latn
  • nya_Latn
  • oci_Latn
  • ory_Orya
  • pag_Latn
  • pan_Guru
  • pap_Latn
  • pbt_Arab
  • pes_Arab
  • plt_Latn
  • pol_Latn
  • por_Latn
  • prs_Arab
  • quy_Latn
  • ron_Latn
  • run_Latn
  • rus_Cyrl
  • sag_Latn
  • san_Deva
  • sat_Olck
  • scn_Latn
  • shn_Mymr
  • sin_Sinh
  • slk_Latn
  • slv_Latn
  • smo_Latn
  • sna_Latn
  • snd_Arab
  • som_Latn
  • sot_Latn
  • spa_Latn
  • srd_Latn
  • srp_Cyrl
  • ssw_Latn
  • sun_Latn
  • swe_Latn
  • swh_Latn
  • szl_Latn
  • tam_Taml
  • taq_Tfng
  • tat_Cyrl
  • tel_Telu
  • tgk_Cyrl
  • tgl_Latn
  • tha_Thai
  • tir_Ethi
  • tpi_Latn
  • tsn_Latn
  • tso_Latn
  • tuk_Latn
  • tum_Latn
  • tur_Latn
  • twi_Latn
  • tzm_Tfng
  • uig_Arab
  • ukr_Cyrl
  • umb_Latn
  • urd_Arab
  • uzn_Latn
  • vec_Latn
  • vie_Latn
  • war_Latn
  • wol_Latn
  • xho_Latn
  • ydd_Hebr
  • yor_Latn
  • yue_Hant
  • zho_Hant
  • zsm_Latn
  • zul_Latn
task_count
3
task_names
  • KlueMrcDomainClustering
  • KlueYnatMrcCategoryClustering
  • SIB200ClusteringS2S
sample_size
199
subset_count
198
subset_sample
  • ace_Latn
  • acm_Arab
  • acq_Arab
  • aeb_Arab
  • afr_Latn
  • ajp_Arab
  • aka_Latn
  • als_Latn
  • amh_Ethi
  • apc_Arab
  • arb_Latn
  • ars_Arab
  • ary_Arab
  • arz_Arab
  • asm_Beng
  • ast_Latn
  • awa_Deva
  • ayr_Latn
  • azb_Arab
  • azj_Latn
  • bak_Cyrl
  • bam_Latn
  • ban_Latn
  • bel_Cyrl
  • bem_Latn
  • ben_Beng
  • bho_Deva
  • bjn_Latn
  • bod_Tibt
  • bos_Latn
aggregation_method
mean-of-task-means
model_revision_count
1
model_revision_sample
  • bc6d284c60fe5a973e74c1751b92594c9f581213
source model id
nlpai-lab/KoE5
Original result ↗

MTEB

70.014%

source id
mteb
leaderboard name
MTEB Overall
dimension
embedding
metric
Average task score
rank
110
sample size
259
aggregation scope
splits
  • dev
  • test
  • validation
subsets
  • ace_Latn
  • acm_Arab
  • acq_Arab
  • aeb_Arab
  • afr_Latn
  • ajp_Arab
  • aka_Latn
  • als_Latn
  • amh_Ethi
  • apc_Arab
  • ar
  • ar-ar
  • arb_Latn
  • ars_Arab
  • ary_Arab
  • arz_Arab
  • asm_Beng
  • ast_Latn
  • awa_Deva
  • ayr_Latn
  • azb_Arab
  • azj_Latn
  • bak_Cyrl
  • bam_Latn
  • ban_Latn
  • bel_Cyrl
  • bem_Latn
  • ben_Beng
  • bho_Deva
  • bjn_Latn
  • bn
  • bod_Tibt
  • bos_Latn
  • bug_Latn
  • bul_Cyrl
  • cat_Latn
  • ceb_Latn
  • ces_Latn
  • cjk_Latn
  • ckb_Arab
  • crh_Latn
  • cym_Latn
  • dan_Latn
  • de
  • default
  • deu_Latn
  • dik_Latn
  • dyu_Latn
  • dzo_Tibt
  • ell_Grek
  • en
  • en-ar
  • en-de
  • en-en
  • en-tr
  • eng_Latn
  • eng_Latn-kor_Hang
  • epo_Latn
  • es
  • es-en
  • es-es
  • est_Latn
  • eus_Latn
  • ewe_Latn
  • fa
  • fao_Latn
  • fi
  • fij_Latn
  • fin_Latn
  • fon_Latn
  • fr
  • fr-en
  • fra_Latn
  • fur_Latn
  • fuv_Latn
  • gaz_Latn
  • gla_Latn
  • gle_Latn
  • glg_Latn
  • grn_Latn
  • guj_Gujr
  • hat_Latn
  • hau_Latn
  • heb_Hebr
  • hi
  • hin_Deva
  • hne_Deva
  • hrv_Latn
  • hun_Latn
  • hye_Armn
  • ibo_Latn
  • id
  • ilo_Latn
  • ind_Latn
  • isl_Latn
  • it-en
  • ita_Latn
  • ja
  • jav_Latn
  • jpn_Jpan
  • kab_Latn
  • kac_Latn
  • kam_Latn
  • kan_Knda
  • kas_Deva
  • kat_Geor
  • kaz_Cyrl
  • kbp_Latn
  • kea_Latn
  • khk_Cyrl
  • khm_Khmr
  • kik_Latn
  • kin_Latn
  • kir_Cyrl
  • kmb_Latn
  • kmr_Latn
  • knc_Latn
  • ko
  • ko-ko
  • kon_Latn
  • kor_Hang
  • kor_Hang-eng_Latn
  • kor_Hang-kor_Hang
  • korean
  • lao_Laoo
  • lij_Latn
  • lim_Latn
  • lin_Latn
  • lit_Latn
  • lmo_Latn
  • ltg_Latn
  • ltz_Latn
  • lua_Latn
  • lug_Latn
  • luo_Latn
  • lus_Latn
  • lvs_Latn
  • mag_Deva
  • mai_Deva
  • mal_Mlym
  • mar_Deva
  • min_Latn
  • mkd_Cyrl
  • mlt_Latn
  • mni_Beng
  • mos_Latn
  • mri_Latn
  • mya_Mymr
  • nl-en
  • nld_Latn
  • nno_Latn
  • nob_Latn
  • npi_Deva
  • nqo_Nkoo
  • nso_Latn
  • nus_Latn
  • nya_Latn
  • oci_Latn
  • ory_Orya
  • pag_Latn
  • pan_Guru
  • pap_Latn
  • pbt_Arab
  • pes_Arab
  • plt_Latn
  • pol_Latn
  • por_Latn
  • prs_Arab
  • quy_Latn
  • ron_Latn
  • ru
  • run_Latn
  • rus_Cyrl
  • sag_Latn
  • san_Deva
  • sat_Olck
  • scn_Latn
  • shn_Mymr
  • sin_Sinh
  • slk_Latn
  • slv_Latn
  • smo_Latn
  • sna_Latn
  • snd_Arab
  • som_Latn
  • sot_Latn
  • spa_Latn
  • srd_Latn
  • srp_Cyrl
  • ssw_Latn
  • sun_Latn
  • sw
  • swe_Latn
  • swh_Latn
  • szl_Latn
  • tam_Taml
  • taq_Tfng
  • tat_Cyrl
  • te
  • tel_Telu
  • tgk_Cyrl
  • tgl_Latn
  • th
  • tha_Thai
  • tir_Ethi
  • tpi_Latn
  • tsn_Latn
  • tso_Latn
  • tuk_Latn
  • tum_Latn
  • tur_Latn
  • twi_Latn
  • tzm_Tfng
  • uig_Arab
  • ukr_Cyrl
  • umb_Latn
  • urd_Arab
  • uzn_Latn
  • vec_Latn
  • vie_Latn
  • war_Latn
  • wol_Latn
  • xho_Latn
  • ydd_Hebr
  • yo
  • yor_Latn
  • yue_Hant
  • zh
  • zho_Hant
  • zsm_Latn
  • zul_Latn
task_count
20
task_names
  • AutoRAGRetrieval
  • BelebeleRetrieval
  • KLUE-NLI
  • KLUE-STS
  • KLUE-TC
  • KlueMrcDomainClustering
  • KlueYnatMrcCategoryClustering
  • Ko-StrategyQA
  • KorNLI
  • KorSTS
  • LawIRKo
  • MIRACLReranking
  • MIRACLRetrieval
  • MrTidyRetrieval
  • MultiLongDocRetrieval
  • PawsXPairClassification
  • PublicHealthQA
  • SIB200ClusteringS2S
  • SQuADKorV1Retrieval
  • STS17
sample_size
259
subset_count
231
subset_sample
  • ace_Latn
  • acm_Arab
  • acq_Arab
  • aeb_Arab
  • afr_Latn
  • ajp_Arab
  • aka_Latn
  • als_Latn
  • amh_Ethi
  • apc_Arab
  • ar
  • ar-ar
  • arb_Latn
  • ars_Arab
  • ary_Arab
  • arz_Arab
  • asm_Beng
  • ast_Latn
  • awa_Deva
  • ayr_Latn
  • azb_Arab
  • azj_Latn
  • bak_Cyrl
  • bam_Latn
  • ban_Latn
  • bel_Cyrl
  • bem_Latn
  • ben_Beng
  • bho_Deva
  • bjn_Latn
aggregation_method
mean-of-task-means
model_revision_count
1
model_revision_sample
  • bc6d284c60fe5a973e74c1751b92594c9f581213
source model id
nlpai-lab/KoE5
Original result ↗

MTEB

69.634%

source id
mteb
leaderboard name
MTEB Retrieval
dimension
embedding
metric
Average task score
rank
173
sample size
9
aggregation scope
splits
  • dev
  • test
subsets
  • default
  • eng_Latn-kor_Hang
  • ko
  • kor_Hang-eng_Latn
  • kor_Hang-kor_Hang
  • korean
task_count
6
task_names
  • AutoRAGRetrieval
  • BelebeleRetrieval
  • MIRACLRetrieval
  • MrTidyRetrieval
  • MultiLongDocRetrieval
  • SQuADKorV1Retrieval
sample_size
9
subset_count
6
subset_sample
  • default
  • eng_Latn-kor_Hang
  • ko
  • kor_Hang-eng_Latn
  • kor_Hang-kor_Hang
  • korean
aggregation_method
mean-of-task-means
model_revision_count
1
model_revision_sample
  • bc6d284c60fe5a973e74c1751b92594c9f581213
source model id
nlpai-lab/KoE5
Original result ↗

MTEB

63.878%

source id
mteb
leaderboard name
MTEB Reranking
dimension
embedding
metric
Average task score
rank
182
sample size
18
aggregation scope
splits
  • dev
subsets
  • ar
  • bn
  • de
  • en
  • es
  • fa
  • fi
  • fr
  • hi
  • id
  • ja
  • ko
  • ru
  • sw
  • te
  • th
  • yo
  • zh
task_count
1
task_names
  • MIRACLReranking
sample_size
18
subset_count
18
subset_sample
  • ar
  • bn
  • de
  • en
  • es
  • fa
  • fi
  • fr
  • hi
  • id
  • ja
  • ko
  • ru
  • sw
  • te
  • th
  • yo
  • zh
aggregation_method
mean-of-task-means
model_revision_count
1
model_revision_sample
  • bc6d284c60fe5a973e74c1751b92594c9f581213
source model id
nlpai-lab/KoE5
Original result ↗

MTEB

57.304%

source id
mteb
leaderboard name
MTEB Pair Classification
dimension
embedding
metric
Average task score
rank
237
sample size
14
aggregation scope
splits
  • test
  • validation
subsets
  • de
  • en
  • es
  • fr
  • ja
  • ko
  • zh
task_count
1
task_names
  • PawsXPairClassification
sample_size
14
subset_count
7
subset_sample
  • de
  • en
  • es
  • fr
  • ja
  • ko
  • zh
aggregation_method
mean-of-task-means
model_revision_count
1
model_revision_sample
  • bc6d284c60fe5a973e74c1751b92594c9f581213
source model id
nlpai-lab/KoE5
Original result ↗

Provider specifications & access

1–1 / 1

nlpai-lab/KoE5 ↗

source model id
HuggingFace/nlpai-lab-koe5@1
hosting
foundry-managed-compute
platforms
  • Microsoft Foundry
license
mit
architecture
input_modalities
  • text
output_modalities
  • embeddings
capabilities

    Original sources

    1–5 / 5

    Hugging Face · nlpai-lab/KoE5 ↗

    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