# ONNX Acceleration

A multi-label emotion classification model fine-tuned based on ruRoberta-large, capable of detecting 27 emotion types in Russian text. It is currently the best-performing open-source emotion detection model for Russian.

This is the ONNX version of the RoBERTa-base-go_emotions model, supporting full precision and INT8 quantization for multi-label emotion analysis tasks.

This is an ONNX model based on sentence-transformers, capable of mapping sentences and paragraphs into a 384-dimensional dense vector space, suitable for tasks such as clustering or semantic search.

A lightweight model fine-tuned for French natural language inference tasks based on DistilCamemBERT, with 50% faster inference speed than the original CamemBERT

A French Q&A task model fine-tuned based on DistilCamemBERT, optimized for inference speed and reduced computational resource consumption

A French sentiment analysis model fine-tuned based on DistilCamemBERT, with inference time halved while maintaining the same performance.