import torch
from adapters import AutoAdapterModel
from transformers import AutoTokenizer

# 1. Initialize the correct base model for this specific adapter
base_model = "google/gemma-2-2b-it"
model = AutoAdapterModel.from_pretrained(base_model)

# 2. Load and activate the adapter weights
model.load_adapter(
    "omegaT4224/Andrewleecruz.vip",
    set_active=True
)

# 3. Load the matching tokenizer
tokenizer = AutoTokenizer.from_pretrained(base_model)

# 4. Format the prompt and tokenized inputs
inputs = tokenizer("Your custom prompt goes here", return_tensors="pt")

# 5. Generate and decode the response
outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))