from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_name = "./ProTalkModel.safetensors"
device = "cuda" if torch.cuda.is_available() else "cpu"

tokenizer = AutoTokenizer.from_pretrained("./")
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16 if device=="cuda" else torch.float32).to(device)

system_prompt = "You are ProTalk, a professional AI assistant. Remember everything in this conversation. Be polite, witty, and professional."

chat_history = []

while True:
    user_input = input("User: ")
    if user_input.lower() == "exit":
        break
    chat_history.append(f"User: {user_input}")
    prompt = system_prompt + "\n" + "\n".join(chat_history) + "\nProTalk:"
    inputs = tokenizer(prompt, return_tensors="pt").to(device)
    outputs = model.generate(**inputs, max_new_tokens=150, do_sample=True, temperature=0.7, top_p=0.9)
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    print(f"ProTalk: {response}")
    chat_history.append(f"ProTalk: {response}")