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.
- Downloads last month
- 4,100
Evaluation results
- accuracy on MTEB AmazonCounterfactualClassification (en)test set self-reported72.881
- ap on MTEB AmazonCounterfactualClassification (en)test set self-reported35.742
- f1 on MTEB AmazonCounterfactualClassification (en)test set self-reported66.981
- accuracy on MTEB AmazonPolarityClassificationtest set self-reported91.032
- ap on MTEB AmazonPolarityClassificationtest set self-reported87.607
- f1 on MTEB AmazonPolarityClassificationtest set self-reported91.010
- accuracy on MTEB AmazonReviewsClassification (en)test set self-reported46.944
- f1 on MTEB AmazonReviewsClassification (en)test set self-reported46.333
- map on MTEB AskUbuntuDupQuestionstest set self-reported60.757
- mrr on MTEB AskUbuntuDupQuestionstest set self-reported73.516
- cos_sim_pearson on MTEB BIOSSEStest set self-reported89.071
- cos_sim_spearman on MTEB BIOSSEStest set self-reported87.806
- euclidean_pearson on MTEB BIOSSEStest set self-reported87.298
- euclidean_spearman on MTEB BIOSSEStest set self-reported87.563
- manhattan_pearson on MTEB BIOSSEStest set self-reported87.561
- manhattan_spearman on MTEB BIOSSEStest set self-reported87.460
- accuracy on MTEB Banking77Classificationtest set self-reported83.468
- f1 on MTEB Banking77Classificationtest set self-reported83.395
- accuracy on MTEB EmotionClassificationtest set self-reported45.800
- f1 on MTEB EmotionClassificationtest set self-reported40.761
- accuracy on MTEB ImdbClassificationtest set self-reported85.010
- ap on MTEB ImdbClassificationtest set self-reported79.911
- f1 on MTEB ImdbClassificationtest set self-reported84.974
- accuracy on MTEB MTOPDomainClassification (en)test set self-reported92.510
- f1 on MTEB MTOPDomainClassification (en)test set self-reported92.285
- accuracy on MTEB MTOPIntentClassification (en)test set self-reported69.619
- f1 on MTEB MTOPIntentClassification (en)test set self-reported51.833