keystats/sunflower-luganda-health-merged

TEXT GENERATIONConcurrency Cost:1Model Size:14BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:Jun 8, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The keystats/sunflower-luganda-health-merged is a 14 billion parameter Qwen3 model, fine-tuned by keystats from Sunbird/Sunflower-14B. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training speeds. It is specifically designed for applications related to Luganda language and health, offering a context length of 32768 tokens.

Loading preview...

Model Overview

The keystats/sunflower-luganda-health-merged is a 14 billion parameter language model, fine-tuned by keystats. It is based on the Qwen3 architecture and was developed by further training the Sunbird/Sunflower-14B model.

Key Characteristics

  • Architecture: Qwen3-based, fine-tuned from Sunbird/Sunflower-14B.
  • Parameter Count: 14 billion parameters.
  • Context Length: Supports a substantial context window of 32768 tokens.
  • Training Efficiency: Leveraged Unsloth and Huggingface's TRL library for 2x faster training.

Intended Use Cases

This model is specifically tailored for applications requiring understanding and generation in the Luganda language, particularly within the health domain. Its fine-tuning suggests optimized performance for tasks related to health information, communication, or content generation in Luganda.

Finetunes
1 models