handler.py

# handler.py
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

MODEL_PATH = "GilbertAkham/deepseek-R1-multitask-lora"

class EndpointHandler:
    def __init__(self, path=""):
        print("Loading merged model...")
        self.tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH, trust_remote_code=True)
        self.model = AutoModelForCausalLM.from_pretrained(
            MODEL_PATH, torch_dtype=torch.float16, device_map="auto", trust_remote_code=True
        )
        self.model.eval()
        print("Model loaded successfully.")

    def __call__(self, data):
        prompt = data.get("inputs", "")
        inputs = self.tokenizer(prompt, return_tensors="pt").to(self.model.device)
        with torch.no_grad():
            outputs = self.model.generate(
                **inputs,
                max_new_tokens=512,
                temperature=0.7,
                top_p=0.9,
                do_sample=True,
                pad_token_id=self.tokenizer.eos_token_id,
                eos_token_id=self.tokenizer.eos_token_id,
            )
        return {"generated_text": self.tokenizer.decode(outputs[0], skip_special_tokens=True)}