ArtusDev/allura-org_Gemma-3-Glitter-4B-GGUF

✨ Overview :3

This repository contains GGUF format model files converted from allura-org/Gemma-3-Glitter-4B.

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

📄 Original Model Details ^_^

For more information about the model please refer to the original model card. It's pretty neat (empty)!

💬 Instruct Format >.<

This model uses a custom Gemma 2/3 instruct format. It has been trained to recognize an optional system role.

<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. Don't mess it up :3!

GGUF Quantizations (imatrix) by ArtusDev >:3