Instructions to use tkan/qwen3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use tkan/qwen3 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit") model = PeftModel.from_pretrained(base_model, "tkan/qwen3") - Notebooks
- Google Colab
- Kaggle
Question about your Qwen3 LoRA project
#1
by Ask951169 - opened
Hey, I came across your Qwen3 LoRA project focused on structured outputs.
I'm exploring how developers are improving model reliability for specific output formats. What made you choose fine-tuning for this use case instead of handling it mainly at the inference or prompt level?