24 9

BaYang

bayang

bm777

AI & ML interests

Heuristic methods

Recent Activity

new activity 8 days ago

deepfile/embedder-100p:Adding `safetensors` variant of this model

new activity 13 days ago

sentence-transformers/all-MiniLM-L6-v2:Support for Tensorflow.js

liked a model about 1 month ago

genmo/mochi-1-preview

View all activity

Organizations

bayang's activity

New activity in deepfile/embedder-100p 8 days ago

Adding `safetensors` variant of this model

#1 opened 9 days ago by

SFconvertbot

New activity in sentence-transformers/all-MiniLM-L6-v2 13 days ago

Support for Tensorflow.js

#94 opened 13 days ago by

bayang

liked 2 models about 1 month ago

genmo/mochi-1-preview

Text-to-Video • Updated 20 days ago • 41.3k • 1.13k

deepfile/multilingual-e5-small-onnx-qint8

New activity in sentence-transformers/all-MiniLM-L6-v2 about 2 months ago

Guide for creating openvino and qint8 for hf model

#89 opened about 2 months ago by

bayang

updated a model about 2 months ago

deepfile/multilingual-e5-small-onnx-qint8

reacted to tomaarsen's post with 🔥 about 2 months ago

Post

5508

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 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