silma-ai/SILMA-Kashif-2B-Instruct-v1.0

SILMA-Kashif-2B-Instruct-v1.0 is a 2.6 billion parameter instruction-tuned causal language model developed by silma-ai, built on Google Gemma's foundational models. This model is specifically designed and optimized for Retrieval-Augmented Generation (RAG) tasks, excelling at answering questions based on contextual pieces in both Arabic and English. It features an 8192-token context length and also performs entity extraction as a secondary capability.