PaDaS-Lab/webfaq
Viewer
β’
Updated
β’
79.5M
β’
1.39k
β’
15
Abdullah Al Zubaer
abdullahalzubaer
AI & ML interests
Natural Language Processing
Recent Activity
liked
a dataset
4 days ago
PaDaS-Lab/webfaq
upvoted
an
article
about 2 months ago
Hugging Face x LangChain : A new partner package in LangChain
updated
a model
about 2 months ago
abdullahalzubaer/Llama-3.1-8B-Instruct-Hawkish-merged
Organizations
abdullahalzubaer's activity
liked
a
dataset
4 days ago
upvoted
an
article
about 2 months ago
Article
Hugging Face x LangChain : A new partner package in LangChain
β’
132
updated
a
model
about 2 months ago
published
a
model
about 2 months ago
updated
a
model
about 2 months ago
liked
a
model
about 2 months ago
published
a
model
about 2 months ago
upvoted
a
collection
4 months ago
updated
a
Space
4 months ago
upvoted
a
collection
4 months ago
upvoted
a
paper
5 months ago
reacted to
tomaarsen's
post with πβ€οΈπ₯
5 months ago
Post
7096
π£ Sentence Transformers v3.2.0 is out, marking the biggest release for inference in 2 years! 2 new backends for embedding models: ONNX (+ optimization & quantization) and OpenVINO, allowing for speedups up to 2x-3x AND Static Embeddings for 500x speedups at 10-20% accuracy cost.
1οΈβ£ ONNX Backend: This backend uses the ONNX Runtime to accelerate model inference on both CPU and GPU, reaching up to 1.4x-3x speedup depending on the precision. We also introduce 2 helper methods for optimizing and quantizing models for (much) faster inference.
2οΈβ£ OpenVINO Backend: This backend uses Intel their OpenVINO instead, outperforming ONNX in some situations on CPU.
Usage is as simple as
π Another major new feature is Static Embeddings: think word embeddings like GLoVe and word2vec, but modernized. Static Embeddings are bags of token embeddings that are summed together to create text embeddings, allowing for lightning-fast embeddings that don't require any neural networks. They're initialized in one of 2 ways:
1οΈβ£ via Model2Vec, a new technique for distilling any Sentence Transformer models into static embeddings. Either via a pre-distilled model with
2οΈβ£ Random initialization. This requires finetuning, but finetuning is extremely quick (e.g. I trained with 3 million pairs in 7 minutes). My final model was 6.6% worse than bge-base-en-v1.5, but 500x faster on CPU.
Full release notes: https://github.com/UKPLab/sentence-transformers/releases/tag/v3.2.0
Documentation on Speeding up Inference: https://sbert.net/docs/sentence_transformer/usage/efficiency.html
1οΈβ£ ONNX Backend: This backend uses the ONNX Runtime to accelerate model inference on both CPU and GPU, reaching up to 1.4x-3x speedup depending on the precision. We also introduce 2 helper methods for optimizing and quantizing models for (much) faster inference.
2οΈβ£ OpenVINO Backend: This backend uses Intel their OpenVINO instead, outperforming ONNX in some situations on CPU.
Usage is as simple as
SentenceTransformer("all-MiniLM-L6-v2", backend="onnx"). Does your model not have an ONNX or OpenVINO file yet? No worries - it'll be autoexported for you. Thank me later ππ Another major new feature is Static Embeddings: think word embeddings like GLoVe and word2vec, but modernized. Static Embeddings are bags of token embeddings that are summed together to create text embeddings, allowing for lightning-fast embeddings that don't require any neural networks. They're initialized in one of 2 ways:
1οΈβ£ via Model2Vec, a new technique for distilling any Sentence Transformer models into static embeddings. Either via a pre-distilled model with
from_model2vec or with from_distillation where you do the distillation yourself. It'll only take 5 seconds on GPU & 2 minutes on CPU, no dataset needed.2οΈβ£ Random initialization. This requires finetuning, but finetuning is extremely quick (e.g. I trained with 3 million pairs in 7 minutes). My final model was 6.6% worse than bge-base-en-v1.5, but 500x faster on CPU.
Full release notes: https://github.com/UKPLab/sentence-transformers/releases/tag/v3.2.0
Documentation on Speeding up Inference: https://sbert.net/docs/sentence_transformer/usage/efficiency.html
- 1 reply
upvoted
a
paper
5 months ago
upvoted
2
articles
8 months ago
Article
Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth
By
β’
β’
293Article
Vision Language Models Explained
β’
286
liked
a
model
9 months ago
upvoted
an
article
9 months ago
Article
Training and Finetuning Embedding Models with Sentence Transformers v3
β’
193
liked
a
model
11 months ago
