RuBERT v2 Tiny (INT8, ONNX)
This repository contains an INT8-quantized version of RuBERT v2 Tiny, converted to the ONNX format for efficient CPU inference.
Based on the original model: https://huggingface.co/cointegrated/rubert-tiny2
Post-training INT8 quantization
Optimized for fast and lightweight inference
Suitable for embeddings, semantic search, and text classification
Note: This is a derivative work with format conversion and quantization only.
- Downloads last month
- 4
Model tree for TrendHD/rubert-tiny2-int8
Base model
cointegrated/rubert-tiny2
from sentence_transformers import SentenceTransformer model = SentenceTransformer("TrendHD/rubert-tiny2-int8") sentences = [ "Это счастливый человек", "Это счастливая собака", "Это очень счастливый человек", "Сегодня солнечный день" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4]