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.
yaml
1models:2-model: ToastyPigeon/Gemma-3-Confetti-12B
3parameters:4weight:0.35-model: allura-org/Gemma-3-Glitter-12B
6parameters:7weight:0.78merge_method: linear
9tokenizer_source: allura-org/Gemma-3-Glitter-12B
10
