How to use Fancylalala/qwen3-235b-a22b-a2ui-sft-0401 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-235B-A22B-Instruct-2507") model = PeftModel.from_pretrained(base_model, "Fancylalala/qwen3-235b-a22b-a2ui-sft-0401")
PEFT LoRA adapter exported from a Tinker checkpoint for:
Qwen/Qwen3-235B-A22B-Instruct-2507
CAUSAL_LM
16
bin
This repository stores adapter weights only. Load it together with the base model above.
Base model
