getans.py

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM


device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat-hf")
model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-chat-hf")

model.to(device)

def get_response(prompt, max_new_tokens=50):
    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(**inputs, max_new_tokens=max_new_tokens, temperature=0.0001, do_sample=True)
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)  # Use indexing instead of calling
    return response