metadata
license: mit
language:
- en
tags:
- sparse sparsity quantized onnx embeddings int8
- mteb
model-index:
- name: bge-large-en-v1.5-sparse
results:
- task:
type: STS
dataset:
type: mteb/biosses-sts
name: MTEB BIOSSES
config: default
split: test
revision: d3fb88f8f02e40887cd149695127462bbcf29b4a
metrics:
- type: cos_sim_pearson
value: 87.73305831153709
- type: cos_sim_spearman
value: 85.64351771070989
- type: euclidean_pearson
value: 86.06880877736519
- type: euclidean_spearman
value: 85.60676988543395
- type: manhattan_pearson
value: 85.69108036145253
- type: manhattan_spearman
value: 85.05314281283421
- task:
type: STS
dataset:
type: mteb/sickr-sts
name: MTEB SICK-R
config: default
split: test
revision: a6ea5a8cab320b040a23452cc28066d9beae2cee
metrics:
- type: cos_sim_pearson
value: 85.61833776000717
- type: cos_sim_spearman
value: 80.73718686921521
- type: euclidean_pearson
value: 83.9368704709159
- type: euclidean_spearman
value: 80.64477415487963
- type: manhattan_pearson
value: 83.92383757341743
- type: manhattan_spearman
value: 80.59625506933862
- task:
type: STS
dataset:
type: mteb/sts12-sts
name: MTEB STS12
config: default
split: test
revision: a0d554a64d88156834ff5ae9920b964011b16384
metrics:
- type: cos_sim_pearson
value: 83.81272888013494
- type: cos_sim_spearman
value: 76.07038564455931
- type: euclidean_pearson
value: 80.33676600912023
- type: euclidean_spearman
value: 75.86575335744111
- type: manhattan_pearson
value: 80.36973770593211
- type: manhattan_spearman
value: 75.88787860200954
- task:
type: STS
dataset:
type: mteb/sts13-sts
name: MTEB STS13
config: default
split: test
revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca
metrics:
- type: cos_sim_pearson
value: 85.58781524090651
- type: cos_sim_spearman
value: 86.80508359626748
- type: euclidean_pearson
value: 85.22891409219575
- type: euclidean_spearman
value: 85.78295876926319
- type: manhattan_pearson
value: 85.2193177032458
- type: manhattan_spearman
value: 85.74049940198427
- task:
type: STS
dataset:
type: mteb/sts14-sts
name: MTEB STS14
config: default
split: test
revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375
metrics:
- type: cos_sim_pearson
value: 84.0862821699066
- type: cos_sim_spearman
value: 81.67856196476185
- type: euclidean_pearson
value: 83.38475353138897
- type: euclidean_spearman
value: 81.45279784228292
- type: manhattan_pearson
value: 83.29235221714131
- type: manhattan_spearman
value: 81.3971683104493
- task:
type: STS
dataset:
type: mteb/sts15-sts
name: MTEB STS15
config: default
split: test
revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3
metrics:
- type: cos_sim_pearson
value: 87.44459051393112
- type: cos_sim_spearman
value: 88.74673154561383
- type: euclidean_pearson
value: 88.13112382236628
- type: euclidean_spearman
value: 88.56241954487271
- type: manhattan_pearson
value: 88.11098632041256
- type: manhattan_spearman
value: 88.55607051247829
- task:
type: STS
dataset:
type: mteb/sts16-sts
name: MTEB STS16
config: default
split: test
revision: 4d8694f8f0e0100860b497b999b3dbed754a0513
metrics:
- type: cos_sim_pearson
value: 82.8825746257794
- type: cos_sim_spearman
value: 84.6066555379785
- type: euclidean_pearson
value: 84.12438131112606
- type: euclidean_spearman
value: 84.75862802179907
- type: manhattan_pearson
value: 84.12791217960807
- type: manhattan_spearman
value: 84.7739597139034
- 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: 89.19971502207773
- type: cos_sim_spearman
value: 89.75109780507901
- type: euclidean_pearson
value: 89.5913898113725
- type: euclidean_spearman
value: 89.20244860773123
- type: manhattan_pearson
value: 89.68755363801112
- type: manhattan_spearman
value: 89.3105024782381
- 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: 61.73885819503523
- type: cos_sim_spearman
value: 64.09521607825829
- type: euclidean_pearson
value: 64.22116001518724
- type: euclidean_spearman
value: 63.84189650719827
- type: manhattan_pearson
value: 64.23930191730729
- type: manhattan_spearman
value: 63.7536172795383
- task:
type: STS
dataset:
type: mteb/stsbenchmark-sts
name: MTEB STSBenchmark
config: default
split: test
revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831
metrics:
- type: cos_sim_pearson
value: 85.68505574064375
- type: cos_sim_spearman
value: 86.87614324154406
- type: euclidean_pearson
value: 86.96751967489614
- type: euclidean_spearman
value: 86.78979082790067
- type: manhattan_pearson
value: 86.92578795715433
- type: manhattan_spearman
value: 86.74076104131726
- task:
type: PairClassification
dataset:
type: mteb/sprintduplicatequestions-pairclassification
name: MTEB SprintDuplicateQuestions
config: default
split: test
revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46
metrics:
- type: cos_sim_accuracy
value: 99.80990099009901
- type: cos_sim_ap
value: 95.00187845875503
- type: cos_sim_f1
value: 90.37698412698413
- type: cos_sim_precision
value: 89.66535433070865
- type: cos_sim_recall
value: 91.10000000000001
- type: dot_accuracy
value: 99.63366336633663
- type: dot_ap
value: 87.6642728041652
- type: dot_f1
value: 81.40803173029252
- type: dot_precision
value: 80.7276302851524
- type: dot_recall
value: 82.1
- type: euclidean_accuracy
value: 99.8079207920792
- type: euclidean_ap
value: 94.88531851782375
- type: euclidean_f1
value: 90.49019607843137
- type: euclidean_precision
value: 88.75
- type: euclidean_recall
value: 92.30000000000001
- type: manhattan_accuracy
value: 99.81188118811882
- type: manhattan_ap
value: 94.87944331919043
- type: manhattan_f1
value: 90.5
- type: manhattan_precision
value: 90.5
- type: manhattan_recall
value: 90.5
- type: max_accuracy
value: 99.81188118811882
- type: max_ap
value: 95.00187845875503
- type: max_f1
value: 90.5
- task:
type: PairClassification
dataset:
type: mteb/twittersemeval2015-pairclassification
name: MTEB TwitterSemEval2015
config: default
split: test
revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1
metrics:
- type: cos_sim_accuracy
value: 86.3861238600465
- type: cos_sim_ap
value: 74.50058066578084
- type: cos_sim_f1
value: 69.25949774629748
- type: cos_sim_precision
value: 67.64779874213836
- type: cos_sim_recall
value: 70.94986807387863
- type: dot_accuracy
value: 81.57000655659535
- type: dot_ap
value: 59.10193583653485
- type: dot_f1
value: 58.39352155832786
- type: dot_precision
value: 49.88780852655198
- type: dot_recall
value: 70.3957783641161
- type: euclidean_accuracy
value: 86.37420277761221
- type: euclidean_ap
value: 74.41671247141966
- type: euclidean_f1
value: 69.43907156673114
- type: euclidean_precision
value: 64.07853636769299
- type: euclidean_recall
value: 75.77836411609499
- type: manhattan_accuracy
value: 86.30267628300649
- type: manhattan_ap
value: 74.34438603336339
- type: manhattan_f1
value: 69.41888619854721
- type: manhattan_precision
value: 64.13870246085011
- type: manhattan_recall
value: 75.64643799472296
- type: max_accuracy
value: 86.3861238600465
- type: max_ap
value: 74.50058066578084
- type: max_f1
value: 69.43907156673114
- task:
type: PairClassification
dataset:
type: mteb/twitterurlcorpus-pairclassification
name: MTEB TwitterURLCorpus
config: default
split: test
revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf
metrics:
- type: cos_sim_accuracy
value: 88.87530562347187
- type: cos_sim_ap
value: 85.69496469410068
- type: cos_sim_f1
value: 77.96973052787007
- type: cos_sim_precision
value: 74.8900865125514
- type: cos_sim_recall
value: 81.3135201724669
- type: dot_accuracy
value: 86.70780455621532
- type: dot_ap
value: 80.03489678512908
- type: dot_f1
value: 73.26376129933124
- type: dot_precision
value: 70.07591733445804
- type: dot_recall
value: 76.75546658453958
- type: euclidean_accuracy
value: 88.85978189156674
- type: euclidean_ap
value: 85.67894953317325
- type: euclidean_f1
value: 78.04295942720763
- type: euclidean_precision
value: 75.67254845241538
- type: euclidean_recall
value: 80.56667693255312
- type: manhattan_accuracy
value: 88.88306748942446
- type: manhattan_ap
value: 85.66556510677526
- type: manhattan_f1
value: 78.06278290950576
- type: manhattan_precision
value: 74.76912231230173
- type: manhattan_recall
value: 81.65999384046813
- type: max_accuracy
value: 88.88306748942446
- type: max_ap
value: 85.69496469410068
- type: max_f1
value: 78.06278290950576
bge-large-en-v1.5-sparse
Usage
This is the sparse ONNX variant of the bge-small-en-v1.5 embeddings model accelerated with Sparsify for quantization/pruning and DeepSparseSentenceTransformers for inference.
pip install -U deepsparse-nightly[sentence_transformers]
from deepsparse.sentence_transformers import DeepSparseSentenceTransformer
model = DeepSparseSentenceTransformer('neuralmagic/bge-large-en-v1.5-sparse', 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 general questions on these models and sparsification methods, reach out to the engineering team on our community Slack.