Complete procedures with a way back.

Build an educational causal language model from randomly initialized weights using a licensed, provenance-tracked corpus. Train a dedicated tokenizer, define a roughly 34-million-parameter decoder architecture, establish random and unigram baselines, checkpoint and resume one bounded epoch, evaluate held-out loss and qualitative limitations, run local inference, and publish only an honest research artifact.

Build a governed supervised fine-tuning pipeline for a small open-weight causal model: prove base and dataset licenses, audit immutable splits, establish a frozen baseline, train a LoRA or QLoRA adapter, resume checkpoints, evaluate regressions, merge deliberately, test post-training quantization, and serve a pinned adapter through an authenticated API.