kylebrodeur/ microfactory-node:latest

1 month ago

The first fine-tune attempt. Trained on gemma-3-1b-it with rank 16 for 3 epochs on deterministic targets. It parroted the same settings template for every input — it memorized, it did not judge.

... /
template
3508e7d8f903 · 196B
{{ if .System }}<start_of_turn>system
{{ .System }}<end_of_turn>
{{ end }}{{ if .Prompt }}<start_of_turn>user
{{ .Prompt }}<end_of_turn>
{{ end }}<start_of_turn>model
{{ .Response }}<end_of_turn>