Local LLM / Local prompting and model adaptation
Local LLM: Few-shot example coverage
Choose examples that demonstrate edge cases rather than repeating easy patterns.
Environment and inputs: Local chat models and optional PEFT/LoRA adaptation; templates and adapter compatibility depend on the base model.
When to use it
Version prompts, templates and decoding settings alongside the model artifact. Test a change on unseen examples before adopting it, and keep domain improvements separate from regressions in capabilities that the application still requires.
Check the result
Evaluate unseen variants to check the model learned the format rather than copying examples.
Save and compare results
Save the test input, configuration and result. Fix the failing boundary, repeat the same test and compare it with the saved working configuration.
Scope and limits
These exercises have not been tested on your systems. Check feature support and configuration names against the installed release and linked documentation.