python
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch

base_model_id = "meta-llama/Llama-3.2-1B-Instruct"

tokenizer = AutoTokenizer.from_pretrained(base_model_id)
base_model = AutoModelForCausalLM.from_pretrained(
    base_model_id,
    torch_dtype = torch.float16,
    device_map  = "auto",
)

# Load SFT adapters on top of base model
model = PeftModel.from_pretrained(
    base_model,
    "pranav6905/Llama-3.2-1B-SFT-DPOMix-Adapters"
)

prompt = (
    "<|begin_of_text|>"
    "<|start_header_id|>user<|end_header_id|>\n"
    "Explain what machine learning is.\n<|eot_id|>"
    "<|start_header_id|>assistant<|end_header_id|>\n"
)

inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=200)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))