|
--- |
|
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](https://huggingface.co/thenlper/gte-large) embeddings model created with [DeepSparse Optimum](https://github.com/neuralmagic/optimum-deepsparse) for ONNX export/inference and Neural Magic's [Sparsify](https://github.com/neuralmagic/sparsify) for one-shot quantization. |
|
|
|
Current list of sparse and quantized gte ONNX models: |
|
|
|
| Links | Sparsification Method | |
|
| --------------------------------------------------------------------------------------------------- | ---------------------- | |
|
| [zeroshot/gte-large-sparse](https://huggingface.co/zeroshot/gte-large-sparse) | Quantization (INT8) & 50% Pruning | |
|
| [zeroshot/gte-large-quant](https://huggingface.co/zeroshot/gte-large-quant) | Quantization (INT8) | |
|
| [zeroshot/gte-base-sparse](https://huggingface.co/zeroshot/gte-base-sparse) | Quantization (INT8) & 50% Pruning | |
|
| [zeroshot/gte-base-quant](https://huggingface.co/zeroshot/gte-base-quant) | Quantization (INT8) | |
|
| [zeroshot/gte-small-sparse](https://huggingface.co/zeroshot/gte-small-sparse) | Quantization (INT8) & 50% Pruning | |
|
| [zeroshot/gte-small-quant](https://huggingface.co/zeroshot/gte-small-quant) | Quantization (INT8) | |
|
|
|
```bash |
|
pip install -U deepsparse-nightly[sentence_transformers] |
|
``` |
|
|
|
```python |
|
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](https://github.com/neuralmagic/deepsparse/tree/main/src/deepsparse/sentence_transformers). |
|
|
|
For general questions on these models and sparsification methods, reach out to the engineering team on our [community Slack](https://join.slack.com/t/discuss-neuralmagic/shared_invite/zt-q1a1cnvo-YBoICSIw3L1dmQpjBeDurQ). |
|
|
|
 |
|
|
|
|
|
|
