Disclaimer:

This wasn’t created by me, and all credit goes to PLTA’s work. I simply wanted to use it for my Ollama server for various tasks with the prompt format baked into the model for ease of use.

Information:

This is a Ollama convert of PLTA’s Fine-tune of LlaMA 3.1 8B. It’s been fine tuned for Hiligaynon, a rather lesser known language and one that most ai’s haven’t been trained on. This is probably due to the lack of published material and credible materials for AI to be trained on. It’s setup with the Alpaca Prompt Template in the model file so you don’t have to worry about keeping to the template. This was primarily made primarily so I can use it with my tools for helping me learn and study the language. It was posted so others may use it via Ollama servers, and for easier storage if I transition devices.

I take zero credit for any of the wonderful work PLTA did, and simply am having it here for public use, and my own personal use. If PLTA would like me to remove, simply contact me via my website.

Model Paramaters:

# Alpaca instruction template – CRITICAL for this fine‑tuned model
TEMPLATE """Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction: {{ .Prompt }}

### Response:
"""

PARAMETER temperature 0.7
PARAMETER top_p 0.9
PARAMETER top_k 40
PARAMETER repeat_penalty 1.1

Link to PLTA’s Hugging Face