v0.5.15

v0.5.15

• Resolves ranked GGUF recommendations to the actual downloadable artifact repo and filename when the ranked base model and runnable GGUF live in different Hugging Face repos.
• Retunes AA index normalization and refreshes the fallback snapshot for the reworked Artificial Analysis scale.
• Validates ranking flags such as --top, --min-speed, and --min-params before ranking.
• Splits the Hugging Face fetcher into focused modules while keeping the existing whichllm.models.fetcher import surface.