ArtusDev/ToastyPigeon_Gemma-3-Confetti-12B-GGUF

✨ Overview

This repository contains GGUF format model files converted from ToastyPigeon/Gemma-3-Confetti-12B.

The conversion was performed by ArtusDev using llama.cpp, specifically utilizing the imatrix quantization option for potentially improved performance.

📄 Original Model Details

For comprehensive information about the model's architecture, training data, intended use, and evaluation, please refer to the original model card.

💬 Instruct Format

This model uses the standard Gemma 2/3 instruct format. While primarily trained on this format, it might recognize an optional system role based on its fine-tuning:

<start_of_turn>system
{optional system prompt here}<end_of_turn>
<start_of_turn>user
{User messages. You can also place the system prompt here.}<end_of_turn>
<start_of_turn>model
{Model's response}<end_of_turn>

Note: Always ensure the format strictly adheres to the required tokens and structure for optimal model performance.

GGUF Quantizations (imatrix) by ArtusDev