NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16

from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    trust_remote_code=True,
    device_map="auto"
)

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

outputs = model.generate(
    **inputs,
    max_new_tokens=32,
    do_sample=False,
    eos_token_id=tokenizer.eos_token_id
)

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