metadata
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✨
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 - ~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 - ~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>