Seonghaa

qwen2.5-7b-todo-lora

Seonghaa/qwen2.5-7b-todo-lora

qwen2.5-7b-todo-lora is a text generation model from Seonghaa. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.

- Base: Qwen/Qwen2.5-7B-Instruct - Task: 일정(Event) - To-Do JSON 제안 - Training: QLoRA 4bit, TRL SFT