gemma_model.py

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "google/gemma-2b-it"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

def generate_text(prompt):
    inputs = tokenizer.encode(prompt, return_tensors="pt")
    outputs = model.generate(inputs, max_length=50)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)