from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer

model_id = "google/gemma-2b"
peft_model_id = "apfurman/gemma-dolly-agriculture"

# make sure you have access to gemma-2b as well
model = AutoModelForCausalLM.from_pretrained(model_id, token="YOUR_TOKEN_HERE")
model.load_adapter(peft_model_id)
tokenizer = AutoTokenizer.from_pretrained(model_id, token="YOUR_TOKEN_HERE")

def ask(prompt):
    inputs = tokenizer(prompt, return_tensors="pt").input_ids
    with torch.inference_mode():
        tokens = model.generate(
            inputs,
            pad_token_id=128001,
            eos_token_id=128001,
            max_new_tokens=200,
            repetition_penalty=1.5,
        )
        
    return tokenizer.decode(tokens[0], skip_special_tokens=True)