app.py

# import gradio as gr

# def greet(name):
#     return "Hello " + name + "!!"

# iface = gr.Interface(fn=greet, inputs="text", outputs="text")
# iface.launch()

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

# Define the model and tokenizer
model_name = "atharvapawar/securix_Llama-2-7B-Chat-GGML"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

def generate_response(user_input):
    input_ids = tokenizer.encode(user_input, return_tensors="pt")
    with torch.no_grad():
        output = model.generate(input_ids)
    response = tokenizer.decode(output[0], skip_special_tokens=True)
    return response

iface = gr.Interface(
    fn=generate_response,
    inputs=gr.inputs.Textbox(lines=2, label="Enter your question:"),
    outputs=gr.outputs.Textbox(label="Generated Response:")
)

if __name__ == "__main__":
    iface.launch()