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

Release 2.0.0

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

Release 1.1.1

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

chore: add the f16 GGUF LoRA adapter for ollama serving

Merge branch 'feature/3'

todo(3): done

test(3): verify-then-exit corpus is a negative result; v1.1.0 stays champion

docs: note the adapter operates the shell *synchronously*

todo(3): in-progress

Merge branch 'feature/2'

todo(2): done

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

test(2): r=32+MLP capacity arm beats r=16 across the board

chore(2): add r=32 + MLP-targets retrain wrapper (capacity arm)

todo(2): in-progress

Merge branch 'feature/1'

todo(1): done

test(1): greedy (temp-0) re-eval; decoding exonerated, capacity is the lever

todo(1): in-progress

todo(3): open

todo(2): open

todo(1): open

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

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