hayulalab/Averroes-v2-Base

TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:Jun 11, 2026License:cc-by-4.0Architecture:Transformer Open Weights Cold

Averroes-v2-Base by Hayula Lab is a 7.6 billion parameter base model specifically designed for improved performance in Arabic language tasks. This model focuses on foundational Arabic language understanding and generation, serving as a robust base for further fine-tuning. Its primary use case is to provide a strong linguistic foundation for various Arabic NLP applications.

Loading preview...

Averroes-v2-Base: An Improved Arabic Base Model

Averroes-v2-Base, developed by Hayula Lab, is a 7.6 billion parameter foundational language model engineered to enhance performance in the Arabic language. This model is released under the CC-BY-4.0 license, requiring attribution to Hayula Lab when used or adapted.

Key Characteristics

  • Arabic Language Focus: Specifically developed to provide a strong base for Arabic NLP tasks.
  • Model Size: Features 7.6 billion parameters, offering a balance between capability and computational efficiency for a base model.
  • Licensing: Distributed under CC-BY-4.0, emphasizing open use with proper attribution.

Use Cases

This model is ideal for developers and researchers looking for a solid Arabic language foundation. It can be effectively used as:

  • A base model for fine-tuning on specific Arabic NLP tasks such as sentiment analysis, named entity recognition, or question answering.
  • A component in larger systems requiring robust Arabic language understanding and generation capabilities.
  • A starting point for developing custom Arabic-centric AI applications.

Finetunes
1 models