from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "HighCWu/Embformer-MiniMind-0.1B"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(
    model_name,
    trust_remote_code=True,
    cache_dir=".cache"
)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto",
    trust_remote_code=True,
    cache_dir=".cache"
)

# prepare the model input
prompt = "请为我讲解“大语言模型”这个概念。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    input_ids=model_inputs['input_ids'],
    attention_mask=model_inputs['attention_mask'],
    max_new_tokens=8192
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

print(tokenizer.decode(output_ids, skip_special_tokens=True))