# Multi-task training

GATE-AraBert-V1 is a general Arabic text embedding model that optimizes the semantic text similarity task on the AllNLI and STS datasets through multi-task training.

This is a sentence transformer model based on BERTino, capable of mapping Italian sentences and paragraphs into a 768-dimensional dense vector space, suitable for tasks such as clustering or semantic search.

This model is a text classification model trained on five NLI datasets, primarily used for zero-shot classification tasks and serves as a comparative benchmark.

This is a sentence transformer model based on PhoBERT-base-v2, specifically designed for Vietnamese text semantic similarity tasks.

This is a sentence embedding model based on sentence-transformers, capable of mapping sentences and paragraphs into a 128-dimensional dense vector space, suitable for tasks such as clustering or semantic search.

DeBERTa-v3 model trained on MultiNLI, Fever-NLI, and ANLI datasets, excelling in zero-shot classification and natural language inference tasks