handler.py

from typing import Dict, Any
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch

class EndpointHandler:
    def __init__(self, path="."):
        # Set your base model here (must match the one used for LoRA training)
        base_model_id = "google/gemma-2b"  # CHANGE if you used a different base
        self.tokenizer = AutoTokenizer.from_pretrained(base_model_id, trust_remote_code=True)
        base_model = AutoModelForCausalLM.from_pretrained(base_model_id, trust_remote_code=True)
        self.model = PeftModel.from_pretrained(base_model, f"{path}/adapter")
        self.model.eval()
        self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
        self.model.to(self.device)

    def __call__(self, data: Dict[str, Any]) -> Dict[str, Any]:
        prompt = data["inputs"] if isinstance(data, dict) else data
        inputs = self.tokenizer(prompt, return_tensors="pt").to(self.device)
        with torch.no_grad():
            output = self.model.generate(**inputs, max_new_tokens=256)
        decoded = self.tokenizer.decode(output[0], skip_special_tokens=True)
        return {"generated_text": decoded}