Licensed under the Apache License 2.0. This is a derivative (LoRA adapter) of google/gemma-4-12B-it, which is distributed by Google under Apache 2.0.

Usage

python

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = AutoModelForCausalLM.from_pretrained("google/gemma-4-12B-it", device_map="auto")
model = PeftModel.from_pretrained(base, "hhheeejjj/aurora-gemma4-12b-lora-ep3-r16")
tokenizer = AutoTokenizer.from_pretrained("hhheeejjj/aurora-gemma4-12b-lora-ep3-r16")

Framework versions

PEFT 0.19.1