Skip to main content

finetune-persona

Stars0
Forks0
UpdatedJuly 4, 2026 at 13:48

Teach a character/persona to a Qwen3 base model with LoRA, evaluate before/after, export to GGUF, and load it into a naia container via the model-swap API. Dataset-driven and fully reusable โ€” swap the JSONL and you get a different character (Deadpool โ†’ grumpy grandma โ†’ butler โ†’ dialect docent). Includes training-time measurement.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

File Explorer
7 files
SKILL.md
readonly