scholarweave/arxiv-latex
Viewer • Updated • 3.06M • 801 • 19
Abdullah Al Zubaer
abdullahalzubaer
AI & ML interests
Natural Language Processing
Recent Activity
liked a dataset 1 day ago
scholarweave/arxiv-latex authored a paper about 1 month ago
GradeLegal: Automated Grading for German Legal Cases liked a dataset 6 months ago
AUEB-NLP/greek-bar-benchOrganizations
liked a
dataset 1 day ago
authored a
paper about 1 month ago
liked a
dataset 6 months ago
upvoted an article about 1 year ago
Article
AutoThink: Adaptive Reasoning for Large Language Models
codelion
• • 8 Rubric for Scoring
#3 opened about 1 year ago
by abdullahalzubaer
liked a
dataset about 1 year ago
liked a
dataset over 1 year ago
upvoted an article over 1 year ago
Article
Hugging Face x LangChain : A new partner package
- +1
Jofthomas, kkondratenko, efriis
• • 162 updated a
model over 1 year ago
published a
model over 1 year ago
updated a
model over 1 year ago
liked a
model over 1 year ago
published a
model over 1 year ago
upvoted a collection over 1 year ago
updated a
Space over 1 year ago
upvoted a collection over 1 year ago
upvoted a paper over 1 year ago
reacted to tomaarsen's post with 🚀❤️🔥 over 1 year ago
Post
7290
📣 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.
1️⃣ 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.
2️⃣ OpenVINO Backend: This backend uses Intel their OpenVINO instead, outperforming ONNX in some situations on CPU.
Usage is as simple as
🔒 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:
1️⃣ via Model2Vec, a new technique for distilling any Sentence Transformer models into static embeddings. Either via a pre-distilled model with
2️⃣ 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
1️⃣ 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.
2️⃣ 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 😉🔒 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:
1️⃣ 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.2️⃣ 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