---
base_model:
- ToastyPigeon/g3-12b-rp-system-v0.1
- ToastyPigeon/g3-12b-storyteller-v0.2-textonly
- google/gemma-3-12b-it
library_name: transformers
tags:
- mergekit
- merge
---
# ✨G3 Glitter 12B✨
<figure>
  <img src="https://huggingface.co/allura-org/Gemma-3-Glitter-12B/resolve/main/ComfyUI_02427_.png" width="600">
</figure>

A creative writing model based on Gemma 3 12B IT. 

This is a 50/50 merge of two separate trains:
- [ToastyPigeon/g3-12b-rp-system-v0.1](https://huggingface.co/ToastyPigeon/g3-12b-rp-system-v0.1) - ~13.5M tokens of instruct-based training related to RP (2:1 human to synthetic) and examples using a system prompt.
- [ToastyPigeon/g3-12b-storyteller-v0.2-textonly](https://huggingface.co/ToastyPigeon/g3-12b-storyteller-v0.2-textonly) - ~20M tokens of completion training on long-form creative writing; 1.6M synthetic from R1, the rest human-created 

**Update**: Vision has returned to this model, rejoice. 

## Instruct Format

Uses Gemma2/3 instruct, but has been trained to recognize an optional system role.
```
<start_of_turn>system
{optional system turn with prompt}<end_of_turn>
<start_of_turn>user
{User messages; can also put sysprompt here to use the built-in g3 training}<end_of_turn>
<start_of_turn>model
{model response}<end_of_turn>
```