from transformers import AutoTokenizer
from gptqmodel import GPTQModel

model_name = "ModelCloud/EXAONE-3.0-7.8B-Instruct-gptq-4bit"

prompt = [
    {"role": "system", 
     "content": "You are EXAONE model from LG AI Research, a helpful assistant."},
    {"role": "user", "content": "I am in Shanghai, preparing to visit the natural history museum. Can you tell me the best way to"}
]

tokenizer = AutoTokenizer.from_pretrained(model_name)

model = GPTQModel.from_quantized(model_name, trust_remote_code=True)

input_tensor = tokenizer.apply_chat_template(prompt, add_generation_prompt=True, return_tensors="pt")
outputs = model.generate(input_ids=input_tensor.to(model.device), max_new_tokens=100)
result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=True)

print(result)