How to train your own writing adapter with LoRA
Teach an existing open-weights model a recurring style or task on your own hardware, without training a whole language model from scratch.
- LoRA
- MLX-LM
- Qwen3.8-27B
- Apple Silicon
- Python
The workbench
Built with curiosity.
Hands-on workflows, reproducible prompts, and local experiments.
1 project shown