Multilingual Transformer Models

9 repos

This cluster centers on multilingual and cross-lingual transformer-based language models, with a focus on fill-mask and sequence classification tasks across diverse language families. The repositories implement variants of XLM-RoBERTa and other pretrained models optimized for different scales and language coverage, often including Indic language support. Developers exploring this area will find practical implementations of transformer fine-tuning, multilingual model compression, and endpoint-compatible inference for production deployment.

Related clusters