from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
from transformers import AutoTokenizer

model_name_or_path = "mmnga/llm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0-GPTQ-calib-ja-1k"

# Tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, trust_remote_code=True)

# Model
model = AutoGPTQForCausalLM.from_quantized(model_name_or_path, use_safetensors=True, device="cuda:0", use_auth_token=False)

#Your test prompt
prompt = """今日の晩御飯のレシピをご紹介して ### 回答："""
print(tokenizer.decode(model.generate(**tokenizer(prompt, return_tensors="pt",add_special_tokens=False).to(model.device), max_new_tokens=100,do_sample=True,top_p=0.95,temperature=0.7)[0]))