metadata
tags:
- sparse sparsity quantized onnx embeddings int8
- mteb
- mteb
model-index:
- name: gte-large-quant
results:
- task:
type: STS
dataset:
type: mteb/biosses-sts
name: MTEB BIOSSES
config: default
split: test
revision: d3fb88f8f02e40887cd149695127462bbcf29b4a
metrics:
- type: cos_sim_pearson
value: 90.27260027646717
- type: cos_sim_spearman
value: 87.97790825077952
- type: euclidean_pearson
value: 88.42832241523092
- type: euclidean_spearman
value: 87.97248644049293
- type: manhattan_pearson
value: 88.13802465778512
- type: manhattan_spearman
value: 87.43391995202266
- task:
type: STS
dataset:
type: mteb/sickr-sts
name: MTEB SICK-R
config: default
split: test
revision: a6ea5a8cab320b040a23452cc28066d9beae2cee
metrics:
- type: cos_sim_pearson
value: 85.1416039713116
- type: cos_sim_spearman
value: 79.13359419669726
- type: euclidean_pearson
value: 83.08042050989465
- type: euclidean_spearman
value: 79.31565112619433
- type: manhattan_pearson
value: 83.10376638254372
- type: manhattan_spearman
value: 79.30772376012946
- task:
type: STS
dataset:
type: mteb/sts12-sts
name: MTEB STS12
config: default
split: test
revision: a0d554a64d88156834ff5ae9920b964011b16384
metrics:
- type: cos_sim_pearson
value: 84.93030439955828
- type: cos_sim_spearman
value: 75.98104622572393
- type: euclidean_pearson
value: 81.20791722502764
- type: euclidean_spearman
value: 75.74595761987686
- type: manhattan_pearson
value: 81.23169425598003
- type: manhattan_spearman
value: 75.73065403644094
- task:
type: STS
dataset:
type: mteb/sts13-sts
name: MTEB STS13
config: default
split: test
revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca
metrics:
- type: cos_sim_pearson
value: 85.6693892097855
- type: cos_sim_spearman
value: 87.54973524492165
- type: euclidean_pearson
value: 86.55642466103943
- type: euclidean_spearman
value: 87.47921340148683
- type: manhattan_pearson
value: 86.52043275063926
- type: manhattan_spearman
value: 87.43869426658489
- task:
type: STS
dataset:
type: mteb/sts14-sts
name: MTEB STS14
config: default
split: test
revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375
metrics:
- type: cos_sim_pearson
value: 84.37393784507647
- type: cos_sim_spearman
value: 81.98702164762233
- type: euclidean_pearson
value: 84.22038158338351
- type: euclidean_spearman
value: 81.9872746771322
- type: manhattan_pearson
value: 84.21915949674062
- type: manhattan_spearman
value: 81.97923386273747
- task:
type: STS
dataset:
type: mteb/sts15-sts
name: MTEB STS15
config: default
split: test
revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3
metrics:
- type: cos_sim_pearson
value: 87.34477744314285
- type: cos_sim_spearman
value: 88.92669309789463
- type: euclidean_pearson
value: 88.20128441166663
- type: euclidean_spearman
value: 88.91524205114627
- type: manhattan_pearson
value: 88.24425729639415
- type: manhattan_spearman
value: 88.97457451709523
- task:
type: STS
dataset:
type: mteb/sts16-sts
name: MTEB STS16
config: default
split: test
revision: 4d8694f8f0e0100860b497b999b3dbed754a0513
metrics:
- type: cos_sim_pearson
value: 82.11827015492467
- type: cos_sim_spearman
value: 83.59397157586835
- type: euclidean_pearson
value: 82.97284591328044
- type: euclidean_spearman
value: 83.74509747941255
- type: manhattan_pearson
value: 82.974440264842
- type: manhattan_spearman
value: 83.72260506292083
- 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: 88.29744487677577
- type: cos_sim_spearman
value: 88.50799779856109
- type: euclidean_pearson
value: 89.0149154609955
- type: euclidean_spearman
value: 88.72798794474068
- type: manhattan_pearson
value: 89.14318227078863
- type: manhattan_spearman
value: 88.98372697017017
- 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: 70.114540107077
- type: cos_sim_spearman
value: 69.72244488054433
- type: euclidean_pearson
value: 70.03658853094686
- type: euclidean_spearman
value: 68.96035610557085
- type: manhattan_pearson
value: 69.83707789686764
- type: manhattan_spearman
value: 68.71831797289812
- task:
type: STS
dataset:
type: mteb/stsbenchmark-sts
name: MTEB STSBenchmark
config: default
split: test
revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831
metrics:
- type: cos_sim_pearson
value: 84.86664469775837
- type: cos_sim_spearman
value: 85.39649452953681
- type: euclidean_pearson
value: 85.68509956626748
- type: euclidean_spearman
value: 85.50984027606854
- type: manhattan_pearson
value: 85.6688745008871
- type: manhattan_spearman
value: 85.465201888803
- task:
type: PairClassification
dataset:
type: mteb/sprintduplicatequestions-pairclassification
name: MTEB SprintDuplicateQuestions
config: default
split: test
revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46
metrics:
- type: cos_sim_accuracy
value: 99.8079207920792
- type: cos_sim_ap
value: 95.62897445718106
- type: cos_sim_f1
value: 90.03083247687564
- type: cos_sim_precision
value: 92.60042283298098
- type: cos_sim_recall
value: 87.6
- type: dot_accuracy
value: 99.67029702970297
- type: dot_ap
value: 90.20258347721159
- type: dot_f1
value: 83.06172839506172
- type: dot_precision
value: 82.04878048780488
- type: dot_recall
value: 84.1
- type: euclidean_accuracy
value: 99.80594059405941
- type: euclidean_ap
value: 95.53963697283662
- type: euclidean_f1
value: 89.92405063291139
- type: euclidean_precision
value: 91.07692307692308
- type: euclidean_recall
value: 88.8
- type: manhattan_accuracy
value: 99.80594059405941
- type: manhattan_ap
value: 95.55714505339634
- type: manhattan_f1
value: 90.06085192697769
- type: manhattan_precision
value: 91.35802469135803
- type: manhattan_recall
value: 88.8
- type: max_accuracy
value: 99.8079207920792
- type: max_ap
value: 95.62897445718106
- type: max_f1
value: 90.06085192697769
- task:
type: PairClassification
dataset:
type: mteb/twittersemeval2015-pairclassification
name: MTEB TwitterSemEval2015
config: default
split: test
revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1
metrics:
- type: cos_sim_accuracy
value: 85.87351731537224
- type: cos_sim_ap
value: 72.87360532701162
- type: cos_sim_f1
value: 67.8826895565093
- type: cos_sim_precision
value: 61.918225315354505
- type: cos_sim_recall
value: 75.11873350923483
- type: dot_accuracy
value: 80.15139774691542
- type: dot_ap
value: 53.5201503222712
- type: dot_f1
value: 53.42203179614388
- type: dot_precision
value: 46.64303996849773
- type: dot_recall
value: 62.50659630606861
- type: euclidean_accuracy
value: 85.87351731537224
- type: euclidean_ap
value: 73.10465263888227
- type: euclidean_f1
value: 68.38209376101516
- type: euclidean_precision
value: 61.63948316034739
- type: euclidean_recall
value: 76.78100263852242
- type: manhattan_accuracy
value: 85.83775406806939
- type: manhattan_ap
value: 73.08358693248583
- type: manhattan_f1
value: 68.34053485927829
- type: manhattan_precision
value: 61.303163628745025
- type: manhattan_recall
value: 77.20316622691293
- type: max_accuracy
value: 85.87351731537224
- type: max_ap
value: 73.10465263888227
- type: max_f1
value: 68.38209376101516
- task:
type: PairClassification
dataset:
type: mteb/twitterurlcorpus-pairclassification
name: MTEB TwitterURLCorpus
config: default
split: test
revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf
metrics:
- type: cos_sim_accuracy
value: 88.85202002561415
- type: cos_sim_ap
value: 85.58170945333845
- type: cos_sim_f1
value: 77.87783280804442
- type: cos_sim_precision
value: 75.95140515222482
- type: cos_sim_recall
value: 79.90452725592854
- type: dot_accuracy
value: 85.29902588582296
- type: dot_ap
value: 76.95795800483633
- type: dot_f1
value: 71.30231900452489
- type: dot_precision
value: 65.91503267973856
- type: dot_recall
value: 77.6485987064983
- type: euclidean_accuracy
value: 88.80738929638684
- type: euclidean_ap
value: 85.5344499509856
- type: euclidean_f1
value: 77.9805854353285
- type: euclidean_precision
value: 75.97312495435624
- type: euclidean_recall
value: 80.09701262704034
- type: manhattan_accuracy
value: 88.7782822990647
- type: manhattan_ap
value: 85.52577812395661
- type: manhattan_f1
value: 77.97958958110746
- type: manhattan_precision
value: 74.76510067114094
- type: manhattan_recall
value: 81.48290729904527
- type: max_accuracy
value: 88.85202002561415
- type: max_ap
value: 85.58170945333845
- type: max_f1
value: 77.9805854353285
license: mit
language:
- en
gte-large-quant
This is the quantized (INT8) ONNX variant of the gte-large 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-large-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.
