# from transformers import AutoTokenizer, pipeline, logging
# from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig

# model_name_or_path = "asyafiqe/Merak-7B-v3-Mini-Orca-Indo-GPTQ"
# model_basename = "Merak-7B-v3-Mini-Orca-Indo-GPTQ"

# use_triton = False

# tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)

# model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
#         model_basename=model_basename,
#         use_safetensors=True,
#         trust_remote_code=True,
#         device="cuda:0",
#         use_triton=use_triton,
#         quantize_config=None)

# def predict(prompt):
#     # prompt = "Buat rencana untuk menghemat listrik di rumah"
#     system_message = "Anda adalah asisten AI. Anda akan diberi tugas. Anda harus menghasilkan jawaban yang rinci dan panjang.\n"
#     prompt_template=f'''SYSTEM: {system_message}
#     USER: {prompt}
#     ASSISTANT: '''

#     print("\n\n*** Generate:")

#     input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
#     output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512)
#     print(tokenizer.decode(output[0]))

#     # Inference can also be done using transformers' pipeline

#     # Prevent printing spurious transformers error when using pipeline with AutoGPTQ
#     logging.set_verbosity(logging.CRITICAL)

#     print("*** Pipeline:")
#     pipe = pipeline(
#         "text-generation",
#         model=model,
#         tokenizer=tokenizer,
#         max_new_tokens=512,
#         temperature=0.7,
#         top_p=0.95,
#         repetition_penalty=1.15
#     )
    
#     result = pipe(prompt_template)[0]['generated_text']
    
#     return result