from transformers import AutoModelForCausalLM, AutoTokenizer, AutoConfig, QuantoConfig, GenerationConfig

# load hf config
hf_config = AutoConfig.from_pretrained("/Users/gokdenizgulmez/Desktop/mlx-lm/mlx_lm/MiniMiniMax01Text", trust_remote_code=True)

tokenizer = AutoTokenizer.from_pretrained("MiniMaxAI/MiniMax-Text-01")
prompt = "Hello!"
messages = [
    {"role": "system", "content": [{"type": "text", "text": "You are a helpful assistant created by MiniMax based on MiniMax-Text-01 model."}]},
    {"role": "user", "content": [{"type": "text", "text": prompt}]},
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
# tokenize and move to device
model_inputs = tokenizer(text, return_tensors="pt")


model = AutoModelForCausalLM.from_pretrained(
    "/Users/gokdenizgulmez/Desktop/mlx-lm/mlx_lm/MiniMiniMax01Text",
    trust_remote_code=True
)

generation_config = GenerationConfig(
    max_new_tokens=20,
    eos_token_id=200020,
    use_cache=True,
)
generated_ids = model.generate(**model_inputs, generation_config=generation_config)
print(f"generated_ids: {generated_ids}")
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]