from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_name = "SLT-AI/SLT-0.5b-GoToSpeak"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name, 
    torch_dtype=torch.bfloat16, 
    device_map="auto"
)

messages = [{"role": "user", "content": "Hello!"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)

outputs = model.generate(
    **inputs, 
    max_new_tokens=512, 
    temperature=0.7, 
    top_p=0.9
)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))