metadata
tags:
- sparse sparsity quantized onnx embeddings int8
- mteb
model-index:
- name: gte-small-quant
results:
- task:
type: Classification
dataset:
type: mteb/amazon_counterfactual
name: MTEB AmazonCounterfactualClassification (en)
config: en
split: test
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
metrics:
- type: accuracy
value: 72.88059701492537
- type: ap
value: 35.74239003564444
- type: f1
value: 66.98065758287116
- task:
type: Classification
dataset:
type: mteb/amazon_polarity
name: MTEB AmazonPolarityClassification
config: default
split: test
revision: e2d317d38cd51312af73b3d32a06d1a08b442046
metrics:
- type: accuracy
value: 91.031575
- type: ap
value: 87.60741691468986
- type: f1
value: 91.00983458583187
- task:
type: Classification
dataset:
type: mteb/amazon_reviews_multi
name: MTEB AmazonReviewsClassification (en)
config: en
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 46.943999999999996
- type: f1
value: 46.33280307575562
- task:
type: Reranking
dataset:
type: mteb/askubuntudupquestions-reranking
name: MTEB AskUbuntuDupQuestions
config: default
split: test
revision: 2000358ca161889fa9c082cb41daa8dcfb161a54
metrics:
- type: map
value: 60.75683986813218
- type: mrr
value: 73.51624675724399
- task:
type: STS
dataset:
type: mteb/biosses-sts
name: MTEB BIOSSES
config: default
split: test
revision: d3fb88f8f02e40887cd149695127462bbcf29b4a
metrics:
- type: cos_sim_pearson
value: 89.07092347634877
- type: cos_sim_spearman
value: 87.80621759170344
- type: euclidean_pearson
value: 87.29751551472525
- type: euclidean_spearman
value: 87.5634409755362
- type: manhattan_pearson
value: 87.56100206227441
- type: manhattan_spearman
value: 87.45982415672536
- task:
type: Classification
dataset:
type: mteb/banking77
name: MTEB Banking77Classification
config: default
split: test
revision: 0fd18e25b25c072e09e0d92ab615fda904d66300
metrics:
- type: accuracy
value: 83.46753246753246
- type: f1
value: 83.39526091362032
- task:
type: Classification
dataset:
type: mteb/emotion
name: MTEB EmotionClassification
config: default
split: test
revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37
metrics:
- type: accuracy
value: 45.800000000000004
- type: f1
value: 40.76055487612189
- task:
type: Classification
dataset:
type: mteb/imdb
name: MTEB ImdbClassification
config: default
split: test
revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7
metrics:
- type: accuracy
value: 85.0096
- type: ap
value: 79.91059611360778
- type: f1
value: 84.9738791599706
- task:
type: Classification
dataset:
type: mteb/mtop_domain
name: MTEB MTOPDomainClassification (en)
config: en
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 92.51025991792065
- type: f1
value: 92.2852224639839
- task:
type: Classification
dataset:
type: mteb/mtop_intent
name: MTEB MTOPIntentClassification (en)
config: en
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 69.61924304605563
- type: f1
value: 51.832892524807505
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (en)
config: en
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 70.2320107599193
- type: f1
value: 68.03367707473218
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (en)
config: en
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 75.28581035642232
- type: f1
value: 75.43554941058956
- task:
type: STS
dataset:
type: mteb/sickr-sts
name: MTEB SICK-R
config: default
split: test
revision: a6ea5a8cab320b040a23452cc28066d9beae2cee
metrics:
- type: cos_sim_pearson
value: 83.58628262329275
- type: cos_sim_spearman
value: 77.30534089053104
- type: euclidean_pearson
value: 80.86400799226335
- type: euclidean_spearman
value: 77.26947744139412
- type: manhattan_pearson
value: 80.79442484789072
- type: manhattan_spearman
value: 77.18043722794019
- task:
type: STS
dataset:
type: mteb/sts12-sts
name: MTEB STS12
config: default
split: test
revision: a0d554a64d88156834ff5ae9920b964011b16384
metrics:
- type: cos_sim_pearson
value: 82.77293561742106
- type: cos_sim_spearman
value: 73.98616407095425
- type: euclidean_pearson
value: 78.7096804108132
- type: euclidean_spearman
value: 73.52379687387366
- type: manhattan_pearson
value: 78.80694876432868
- type: manhattan_spearman
value: 73.64907838788528
- task:
type: STS
dataset:
type: mteb/sts13-sts
name: MTEB STS13
config: default
split: test
revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca
metrics:
- type: cos_sim_pearson
value: 82.12995363427328
- type: cos_sim_spearman
value: 84.23345798311749
- type: euclidean_pearson
value: 83.94003648503143
- type: euclidean_spearman
value: 84.74522675669463
- type: manhattan_pearson
value: 83.82868963165394
- type: manhattan_spearman
value: 84.61059125620956
- task:
type: STS
dataset:
type: mteb/sts14-sts
name: MTEB STS14
config: default
split: test
revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375
metrics:
- type: cos_sim_pearson
value: 81.88504872832357
- type: cos_sim_spearman
value: 80.09345991196561
- type: euclidean_pearson
value: 81.99899431994811
- type: euclidean_spearman
value: 80.25520445997002
- type: manhattan_pearson
value: 81.9635758954928
- type: manhattan_spearman
value: 80.24335353637277
- task:
type: STS
dataset:
type: mteb/sts15-sts
name: MTEB STS15
config: default
split: test
revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3
metrics:
- type: cos_sim_pearson
value: 86.55052353126385
- type: cos_sim_spearman
value: 88.1950992730786
- type: euclidean_pearson
value: 87.83472249083056
- type: euclidean_spearman
value: 88.43301043636015
- type: manhattan_pearson
value: 87.75102815516877
- type: manhattan_spearman
value: 88.34719608377306
- task:
type: STS
dataset:
type: mteb/sts16-sts
name: MTEB STS16
config: default
split: test
revision: 4d8694f8f0e0100860b497b999b3dbed754a0513
metrics:
- type: cos_sim_pearson
value: 81.58832350766542
- type: cos_sim_spearman
value: 83.60857270697358
- type: euclidean_pearson
value: 82.9059299279255
- type: euclidean_spearman
value: 83.87380773329784
- type: manhattan_pearson
value: 82.76009241925925
- type: manhattan_spearman
value: 83.72876466499108
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (en-en)
config: en-en
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 87.96440735880392
- type: cos_sim_spearman
value: 87.79655666183349
- type: euclidean_pearson
value: 88.47129589774806
- type: euclidean_spearman
value: 87.95235258398374
- type: manhattan_pearson
value: 88.37144209103296
- type: manhattan_spearman
value: 87.81869790317533
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (en)
config: en
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 66.66468384683428
- type: cos_sim_spearman
value: 66.84275911821702
- type: euclidean_pearson
value: 67.73972664535547
- type: euclidean_spearman
value: 66.57863145583491
- type: manhattan_pearson
value: 67.91309920462287
- type: manhattan_spearman
value: 66.67487869242575
- task:
type: STS
dataset:
type: mteb/stsbenchmark-sts
name: MTEB STSBenchmark
config: default
split: test
revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831
metrics:
- type: cos_sim_pearson
value: 84.07668437020894
- type: cos_sim_spearman
value: 85.13186558138277
- type: euclidean_pearson
value: 85.28607166042313
- type: euclidean_spearman
value: 85.25082312265897
- type: manhattan_pearson
value: 85.0870328315141
- type: manhattan_spearman
value: 85.10612962221282
- task:
type: Reranking
dataset:
type: mteb/scidocs-reranking
name: MTEB SciDocsRR
config: default
split: test
revision: d3c5e1fc0b855ab6097bf1cda04dd73947d7caab
metrics:
- type: map
value: 84.33835340608282
- type: mrr
value: 95.54063220729888
- task:
type: PairClassification
dataset:
type: mteb/sprintduplicatequestions-pairclassification
name: MTEB SprintDuplicateQuestions
config: default
split: test
revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46
metrics:
- type: cos_sim_accuracy
value: 99.81386138613861
- type: cos_sim_ap
value: 95.49398397880566
- type: cos_sim_f1
value: 90.5050505050505
- type: cos_sim_precision
value: 91.42857142857143
- type: cos_sim_recall
value: 89.60000000000001
- type: dot_accuracy
value: 99.75742574257426
- type: dot_ap
value: 93.40675781804289
- type: dot_f1
value: 87.45519713261648
- type: dot_precision
value: 89.61175236096537
- type: dot_recall
value: 85.39999999999999
- type: euclidean_accuracy
value: 99.81485148514851
- type: euclidean_ap
value: 95.39724876386569
- type: euclidean_f1
value: 90.5793450881612
- type: euclidean_precision
value: 91.26903553299492
- type: euclidean_recall
value: 89.9
- type: manhattan_accuracy
value: 99.81485148514851
- type: manhattan_ap
value: 95.46515830873487
- type: manhattan_f1
value: 90.56974459724951
- type: manhattan_precision
value: 88.996138996139
- type: manhattan_recall
value: 92.2
- type: max_accuracy
value: 99.81485148514851
- type: max_ap
value: 95.49398397880566
- type: max_f1
value: 90.5793450881612
- task:
type: Reranking
dataset:
type: mteb/stackoverflowdupquestions-reranking
name: MTEB StackOverflowDupQuestions
config: default
split: test
revision: e185fbe320c72810689fc5848eb6114e1ef5ec69
metrics:
- type: map
value: 51.68384236354744
- type: mrr
value: 52.52933749257278
- task:
type: Classification
dataset:
type: mteb/toxic_conversations_50k
name: MTEB ToxicConversationsClassification
config: default
split: test
revision: d7c0de2777da35d6aae2200a62c6e0e5af397c4c
metrics:
- type: accuracy
value: 69.7972
- type: ap
value: 13.790209566654962
- type: f1
value: 53.73625700975159
- task:
type: Classification
dataset:
type: mteb/tweet_sentiment_extraction
name: MTEB TweetSentimentExtractionClassification
config: default
split: test
revision: d604517c81ca91fe16a244d1248fc021f9ecee7a
metrics:
- type: accuracy
value: 57.81550650820599
- type: f1
value: 58.22494506904567
- task:
type: PairClassification
dataset:
type: mteb/twittersemeval2015-pairclassification
name: MTEB TwitterSemEval2015
config: default
split: test
revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1
metrics:
- type: cos_sim_accuracy
value: 84.30589497526375
- type: cos_sim_ap
value: 68.60854966172107
- type: cos_sim_f1
value: 65.06926244852113
- type: cos_sim_precision
value: 61.733364906464594
- type: cos_sim_recall
value: 68.7862796833773
- type: dot_accuracy
value: 81.63557250998392
- type: dot_ap
value: 58.80135920860792
- type: dot_f1
value: 57.39889705882353
- type: dot_precision
value: 50.834350834350836
- type: dot_recall
value: 65.91029023746702
- type: euclidean_accuracy
value: 84.37742146986946
- type: euclidean_ap
value: 68.88494996210581
- type: euclidean_f1
value: 65.23647001462702
- type: euclidean_precision
value: 60.62528318985048
- type: euclidean_recall
value: 70.60686015831135
- type: manhattan_accuracy
value: 84.21648685700661
- type: manhattan_ap
value: 68.54917405273397
- type: manhattan_f1
value: 64.97045701193778
- type: manhattan_precision
value: 59.826782145236514
- type: manhattan_recall
value: 71.08179419525065
- type: max_accuracy
value: 84.37742146986946
- type: max_ap
value: 68.88494996210581
- type: max_f1
value: 65.23647001462702
- task:
type: PairClassification
dataset:
type: mteb/twitterurlcorpus-pairclassification
name: MTEB TwitterURLCorpus
config: default
split: test
revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf
metrics:
- type: cos_sim_accuracy
value: 88.60752124810804
- type: cos_sim_ap
value: 85.16030341274225
- type: cos_sim_f1
value: 77.50186985789081
- type: cos_sim_precision
value: 75.34904013961605
- type: cos_sim_recall
value: 79.781336618417
- type: dot_accuracy
value: 86.00147475453099
- type: dot_ap
value: 79.24446611557556
- type: dot_f1
value: 72.34317740892433
- type: dot_precision
value: 67.81624680048498
- type: dot_recall
value: 77.51770865414228
- type: euclidean_accuracy
value: 88.7026041060271
- type: euclidean_ap
value: 85.30879801684605
- type: euclidean_f1
value: 77.60992108229988
- type: euclidean_precision
value: 75.80384671854354
- type: euclidean_recall
value: 79.50415768401602
- type: manhattan_accuracy
value: 88.75305623471883
- type: manhattan_ap
value: 85.24656615741652
- type: manhattan_f1
value: 77.5542141739325
- type: manhattan_precision
value: 75.14079422382672
- type: manhattan_recall
value: 80.12781028641824
- type: max_accuracy
value: 88.75305623471883
- type: max_ap
value: 85.30879801684605
- type: max_f1
value: 77.60992108229988
license: mit
language:
- en
gte-small-quant
This is the quantized (INT8) ONNX variant of the gte-small embeddings model created with DeepSparse Optimum for ONNX export/inference and Neural Magic's Sparsify for one-shot quantization.
Current list of sparse and quantized gte ONNX models:
| Links | Sparsification Method |
|---|---|
| zeroshot/gte-large-sparse | Quantization (INT8) & 50% Pruning |
| zeroshot/gte-large-quant | Quantization (INT8) |
| zeroshot/gte-base-sparse | Quantization (INT8) & 50% Pruning |
| zeroshot/gte-base-quant | Quantization (INT8) |
| zeroshot/gte-small-sparse | Quantization (INT8) & 50% Pruning |
| zeroshot/gte-small-quant | Quantization (INT8) |
pip install -U deepsparse-nightly[sentence_transformers]
from deepsparse.sentence_transformers import SentenceTransformer
model = SentenceTransformer('zeroshot/gte-small-quant', export=False)
# Our sentences we like to encode
sentences = ['This framework generates embeddings for each input sentence',
'Sentences are passed as a list of string.',
'The quick brown fox jumps over the lazy dog.']
# Sentences are encoded by calling model.encode()
embeddings = model.encode(sentences)
# Print the embeddings
for sentence, embedding in zip(sentences, embeddings):
print("Sentence:", sentence)
print("Embedding:", embedding.shape)
print("")
For further details regarding DeepSparse & Sentence Transformers integration, refer to the DeepSparse README.
For general questions on these models and sparsification methods, reach out to the engineering team on our community Slack.
