import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
model_id = "hon9kon9ize/CantoneseLLMChat-v1.0-72B"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16, 
    device_map="auto", 
)
def chat(messages, temperature=0.9, max_new_tokens=200):
    input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt').to('cuda:0')
    output_ids = model.generate(input_ids, max_new_tokens=max_new_tokens, temperature=temperature)
    response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=False)
    return response
prompt = "邊個係香港特首？"
messages = [
    {"role": "system", "content": "you are a helpful assistant."},
    {"role": "user", "content": prompt}
]
print(chat(messages)) # 香港特別行政區行政長官係李家超。<|im_end|>