app.py

import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
import torch

# Load Zephyr model
model_id = "HuggingFaceH4/zephyr-7b-beta"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")

pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)

# Chat function
def chat_with_bot(user_input):
    system_message = "You are a helpful, honest, and friendly assistant."
    prompt = f"<|system|>\n{system_message}\n<|user|>\n{user_input}\n<|assistant|>\n"
    response = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_p=0.9)[0]["generated_text"]
    answer = response.split("<|assistant|>")[-1].strip()
    return answer

# Gradio interface
iface = gr.Interface(fn=chat_with_bot, 
                     inputs=gr.Textbox(lines=2, placeholder="Ask me anything..."), 
                     outputs="text",
                     title="Zephyr Chatbot",
                     description="Ask general questions and get helpful answers!")

iface.launch()