release(2.0.1): Ollama serving-docs fix (base needs ChatML + stops)

release(2.0.0): base-template retrain on posix-sdc v2.0.0

docs: prepare 1.1.1 release (changelog, ollama README, model-card prose cleanup)

docs: note the adapter operates the shell *synchronously*

feat(2): promote r=32+MLP adapter to v1.1.0

feat: commit trained adapter, QLoRA config, and held-out eval results

chore: scaffold EuroLLM-9B-Teletype model card and pipeline figures