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.
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>
