🌠G3 Starshine 12B - Alt🌠

This was Merge A2 in the testing set.
A creative writing model based on a merge of fine-tunes on Gemma 3 12B IT and Gemma 3 12B PT.
This is the RP Focused merge. This version better handles separate characters in turn-based chats with less impersonation.
See the main Story Focused version as well.
This is a merge of two G3 models, one trained on instruct and one trained on base:
- allura-org/Gemma-3-Glitter-12B - Itself a merge of a storywriting and RP train (both also by ToastyPigeon), on instruct
- ToastyPigeon/Gemma-3-Confetti-12B - Experimental application of the Glitter data using base instead of instruct, additionally includes some adventure data in the form of SpringDragon.
The result is a lovely blend of Glitter's ability to follow instructions and Confetti's free-spirit prose, effectively 'loosening up' much of the hesitancy that was left in Glitter.
Vision works (as well as any vision works with this model right now) if you pair a GGUF of this with an appropriate mmproj file; I intend to fix the missing vision tower + make this properly multimodal in the near future.
Thank you to jebcarter for the idea to make this. I love how it turned out!
Instruct Format
Uses Gemma2/3 instruct, but has been trained to recognize an optional system role.
Note: While it won't immediately balk at the system role, results may be better without it.
<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>
Merge Configuration
A higher percentage of Glitter gives this model better turn-based instruct following, but it may be more uptight compared to the Story Focused version.
models:
- model: ToastyPigeon/Gemma-3-Confetti-12B
parameters:
weight: 0.3
- model: allura-org/Gemma-3-Glitter-12B
parameters:
weight: 0.7
merge_method: linear
tokenizer_source: allura-org/Gemma-3-Glitter-12B
- Downloads last month
- 5