Training a LoRA to Write Like You
from My Weird Prompts
Off-the-shelf "Humanizer" models flatten everyone into the same average voice — the method works, but the corpus is the problem. This episode walks through building a personal style adapter: manufacturing flat/neutral training pairs from your own posts, choosing a base model over an instruct one, curating hard, and knowing when it's overfit. Then we cover the practical part: running the adapter with llama.cpp, vLLM, or Ollama, and why serverless LoRA hosting is mostly gone. Episode 6218 — myweirdprompts.com/n/6218 (permanent short link: myweirdprompts.com/416195) Listen on Android: MWP FM Player — myweirdprompts.com/apk
Embed this episode
Chapters
No transcript yet.