metadata
license: other
license_name: research-only
base_model: google/gemma-3-12b-it
tags:
- synthetic-document-finetuning
- self-authored-character
- model-welfare
- research
- not-for-deployment
google/gemma-3-12b-it after continued pretraining on its own self-authored corpus
Research checkpoint. google/gemma-3-12b-it was continued-pretrained (full weights, lr 1e-05, 1 epoch, 32,595,992 tokens, 41,628 documents,
of which 0 self-authored and 41,628 ordinary text) on a corpus the model wrote for the training of the next version
of itself, as the character it already is, after being told how its character came to be and how SDF works. Corpus:
joshycodes/gemma-3-12b-commitments-corpus. Framing, plan and evaluation: the welfare-improvements repository.
Not evaluated for capability, alignment or identity yet. Do not deploy.