Tamilan 2: Advanced Tamil Large Language Model

Tamilan 2 is the latest version of the Tamil Large Language Model, designed to enhance understanding and generation of Tamil text.

Gemma 2, instruction fine tuned on Tamil Alpaca Dataset

Developed by: Mervin Praison

Download

• Ollama: Tamilan 2 on Ollama

• Hugging Face:

  • Tamilan-2 2B
  • Tamilan-2 9B
  • Tamilan-2 27B

Key Features:

1. Sizes:

   • 2B parameters
   • 9B parameters
   • 27B parameters

2. Quantization Levels:

   • 4-bit
   • 8-bit
   • 16-bit

3. Training Dataset:

   • Alpaca Tamil dataset - https://huggingface.co/datasets/abhinand/tamil-alpaca

4. Applications:

   • Content creation
   • Customer support
   • Educational tools
   • Research

5. Deployment:

   • Supports efficient deployment and fine-tuning for various tasks