# Arabic Large Language Model

ALLaM is a large Arabic language model developed by the Saudi Data and Artificial Intelligence Authority (SDAIA), supporting both Arabic and English, trained from scratch with 7 billion parameters.

The Jais series are large language models specialized in Arabic processing while possessing strong English capabilities, with variants ranging from 590 million to 70 billion parameters.

The AWQ quantized version of AceGPT 13B Chat, supporting English and Arabic, designed for general GPU users, offering efficient 4-bit quantized inference capabilities.

Jais-30b-chat-v1 is an Arabic and English dialogue model fine-tuned from Jais-30b-v1, featuring 30 billion parameters and optimized for Arabic, outperforming existing Arabic models.

JAIS-30B is a 30-billion-parameter bilingual (Arabic and English) large language model based on the GPT-3 architecture, utilizing ALiBi positional embedding technology, achieving state-of-the-art performance in Arabic tasks.

13 billion parameter Arabic-English bilingual large language model based on Transformer architecture, supporting long sequence processing