from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_name = "AxiomicLabs/GPT-S-5M"

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

prompt = "The future of AI is"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

with torch.inference_mode():
    output = model.generate(
        **inputs,
        max_new_tokens=120,
        do_sample=True,
        temperature=0.8,
        top_p=0.95,
        repetition_penalty=1.1,
        no_repeat_ngram_size=4,
    )

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