Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference
Paper
•
2412.13663
•
Published
•
103
Sentence Transformers
university
AI & ML interests
In the following you find models tuned to be used for sentence / text embedding generation. They can be used with the sentence-transformers package.
Recent Activity
sentence-transformers's activity
tomaarsen
authored
a
paper
6 days ago
how do you compute the similarity
2
#4 opened 21 days ago
by
G0tto
tomaarsen
updated
a
dataset
26 days ago
🚩 Report: Not working
3
#35 opened about 1 month ago
by
amar-moh
Guide for creating openvino and qint8 for hf model
7
#89 opened about 1 month ago
by
bayang
Post
5296
I just released Sentence Transformers v3.3.0 & it's huge! 4.5x speedup for CPU with OpenVINO int8 static quantization, training with prompts for a free perf. boost, PEFT integration, evaluation on NanoBEIR, and more! Details:
1. We integrate Post-Training Static Quantization using OpenVINO, a very efficient solution for CPUs that processes 4.78x as many texts per second on average, while only hurting performance by 0.36% on average. There's a new
2. We add the option to train with prompts, e.g. strings like "query: ", "search_document: " or "Represent this sentence for searching relevant passages: ". It's as simple as using the
3. Sentence Transformers now supports training PEFT adapters via 7 new methods for adding new adapters or loading pre-trained ones. You can also directly load a trained adapter with SentenceTransformer as if it's a normal model. Very useful for e.g. 1) training multiple adapters on 1 base model, 2) training bigger models than otherwise possible, or 3) cheaply hosting multiple models by switching multiple adapters on 1 base model.
4. We added easy evaluation on NanoBEIR, a subset of BEIR a.k.a. the MTEB Retrieval benchmark. It contains 13 datasets with 50 queries and up to 10k documents each. Evaluation is fast, and can easily be done during training to track your model's performance on general-purpose information retrieval tasks.
Additionally, we also deprecate Python 3.8, add better compatibility with Transformers v4.46.0, and more. Read the full release notes here: https://github.com/UKPLab/sentence-transformers/releases/tag/v3.3.0
1. We integrate Post-Training Static Quantization using OpenVINO, a very efficient solution for CPUs that processes 4.78x as many texts per second on average, while only hurting performance by 0.36% on average. There's a new
export_static_quantized_openvino_model method to quantize a model.2. We add the option to train with prompts, e.g. strings like "query: ", "search_document: " or "Represent this sentence for searching relevant passages: ". It's as simple as using the
prompts argument in SentenceTransformerTrainingArguments. Our experiments show that you can easily reach 0.66% to 0.90% relative performance improvement on NDCG@10 at no extra cost by adding "query: " before each training query and "document: " before each training answer.3. Sentence Transformers now supports training PEFT adapters via 7 new methods for adding new adapters or loading pre-trained ones. You can also directly load a trained adapter with SentenceTransformer as if it's a normal model. Very useful for e.g. 1) training multiple adapters on 1 base model, 2) training bigger models than otherwise possible, or 3) cheaply hosting multiple models by switching multiple adapters on 1 base model.
4. We added easy evaluation on NanoBEIR, a subset of BEIR a.k.a. the MTEB Retrieval benchmark. It contains 13 datasets with 50 queries and up to 10k documents each. Evaluation is fast, and can easily be done during training to track your model's performance on general-purpose information retrieval tasks.
Additionally, we also deprecate Python 3.8, add better compatibility with Transformers v4.46.0, and more. Read the full release notes here: https://github.com/UKPLab/sentence-transformers/releases/tag/v3.3.0
tomaarsen
updated
14
models
about 2 months ago
sentence-transformers/xlm-r-base-en-ko-nli-ststb
Sentence Similarity
•
Updated
•
368
•
1
sentence-transformers/bert-base-wikipedia-sections-mean-tokens
Sentence Similarity
•
Updated
•
147
sentence-transformers/bert-base-nli-cls-token
Sentence Similarity
•
Updated
•
2.92k
•
2
sentence-transformers/all-MiniLM-L12-v1
Sentence Similarity
•
Updated
•
8.87k
•
8
sentence-transformers/all-MiniLM-L6-v1
Sentence Similarity
•
Updated
•
14.5k
•
13
sentence-transformers/all-mpnet-base-v1
Sentence Similarity
•
Updated
•
114k
•
10
sentence-transformers/facebook-dpr-ctx_encoder-multiset-base
Sentence Similarity
•
Updated
•
8.24k
•
3
sentence-transformers/facebook-dpr-ctx_encoder-single-nq-base
Sentence Similarity
•
Updated
•
2.51k
sentence-transformers/facebook-dpr-question_encoder-multiset-base
Sentence Similarity
•
Updated
•
735
•
1
sentence-transformers/facebook-dpr-question_encoder-single-nq-base
Sentence Similarity
•
Updated
•
10.6k
•
2
sentence-transformers/msmarco-bert-base-dot-v5
Sentence Similarity
•
Updated
•
156k
•
16
sentence-transformers/msmarco-distilbert-base-dot-prod-v3
Sentence Similarity
•
Updated
•
3.66k
•
3
sentence-transformers/msmarco-distilbert-dot-v5
Sentence Similarity
•
Updated
•
52k
•
13
sentence-transformers/multi-qa-MiniLM-L6-dot-v1
Sentence Similarity
•
Updated
•
26.5k
•
15