import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load the tokenizer and model from Hugging Face
model_name = "impactframes/molmo-7B-D-bnb-4bit"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

# Example input prompt
prompt = "What is the meaning of life?"

# Tokenize the input
inputs = tokenizer(prompt, return_tensors="pt")

# Generate output
with torch.no_grad():
    outputs = model.generate(inputs.input_ids, max_length=100)

# Decode the output
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)