Kaveri 0.5B

Kaveri 0.5B is a local multilingual AI chat assistant built on Qwen2.5-0.5B-Instruct.

Current v1 release:

  • No fine-tuning
  • No LoRA
  • No QLoRA
  • No independently trained weights
  • Kaveri identity via system configuration
  • Local inference supported
  • Ollama configuration included

Base model: Qwen/Qwen2.5-0.5B-Instruct

Public Installation

To install and run Kaveri 0.5B locally using Ollama:

  1. Install Ollama: Download from ollama.com.

  2. Pull base model:

    ollama pull qwen2.5:0.5b-instruct
    
  3. Download Kaveri Modelfile: Download the Modelfile and system_prompt.txt from this repository.

  4. Create the model:

    ollama create kaveri -f Modelfile
    
  5. Run the model:

    ollama run kaveri
    

Identity

Kaveri AI provides a customized system identity for clear, helpful, and concise multilingual assistance.

License

Apache-2.0. See LICENSE for details.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for shiva123782/Kaveri-0.5B-Ollama

Finetuned
(1016)
this model

Space using shiva123782/Kaveri-0.5B-Ollama 1