Tenezis-8b: Multilingual Model for Africa
Overview
Tenezis-8b is an AI model developed by Dimeltech, specifically designed to include and value African languages. This model is based on unsloth/llama-3-8b-bnb-4bit
and has been fine-tuned for fast and efficient text generation.
Features
- Base Model:
unsloth/llama-3-8b-bnb-4bit
- Number of Parameters: 8 billion
- License: Apache 2.0
- Supported Languages: English, Zulu, Wolof, Swahili, Hausa, Amharic, Yoruba, Xhosa, Shona, and Arabic.
- Technologies Used:
- Unsloth for rapid training optimization
- Transformers by Hugging Face for language model management
- TRL (Transformers Reinforcement Learning) for reinforcement fine-tuning
Developed by Dimeltech
Dimeltech is a company dedicated to technological innovation and digital inclusion, with a particular focus on Africa. Our mission is to make artificial intelligence technologies accessible and beneficial to everyone.
License
This model is distributed under the Apache 2.0 license, allowing for flexible and open use while ensuring transparency and collaborative development.
Contribution and Support
We encourage community contributions to enhance and expand the capabilities of Tenezis-8b. For more information on contributing, please refer to our contribution guide.
For any support or questions, please contact our team via our GitHub page or through our community forum.
Model tree for Dimeltech/Tenezis-8B
Base model
meta-llama/Meta-Llama-3-8B