from transformers import AutoModelForCausalLM, AutoTokenizer

device = "cuda" # the device to load the model onto

model = AutoModelForCausalLM.from_pretrained("maywell/Synatra-kiqu-7B")
tokenizer = AutoTokenizer.from_pretrained("maywell/Synatra-kiqu-7B")

messages = [
    {"role": "user", "content": "사회적 합의는 어떤 맥락에서 사용되는 말이야?"},
]

encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")

model_inputs = encodeds.to(device)
model.to(device)

generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])