NedaForoutan/

Qwen3.5-9B-sft-lora_playpen

In order to load the model, first load the base model, Qwen3.5-9B:

from transformers import AutoModelForCausalLM, AutoTokenizer from peft import PeftModel

base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-9B", device_map="auto") model = PeftModel.from_pretrained(base, "NedaForoutan/Qwen3.5-9B-score-sft-lora") tokenizer = AutoTokenizer.from_pretrained("NedaForoutan/Qwen3.5-9B-score-sft-lora")