from transformers import AutoModelForCausalLM, AutoTokenizer
import torch


olmo = AutoModelForCausalLM.from_pretrained(
    "allenai/OLMo-2-1124-7B-hf", 
    torch_dtype=torch.float32, 
    device_map="auto"          
)
tokenizer = AutoTokenizer.from_pretrained("allenai/OLMo-2-1124-7B-hf")
message = ["Honolulu is a "]

inputs = tokenizer(message, return_tensors='pt', return_token_type_ids=False)

response = olmo.generate(
    **inputs,
    max_new_tokens=128,
    do_sample=True,
    top_k=50,
    top_p=0.95,
    temperature=0.5

)

print(tokenizer.batch_decode(response, skip_special_tokens=True)[0])