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

model = AutoModelForCausalLM.from_pretrained("atsnetwork/my-custom-tinyllama-chatbot")
tokenizer = AutoTokenizer.from_pretrained("atsnetwork/my-custom-tinyllama-chatbot")

def generate_response(prompt):
    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(**inputs, max_new_tokens=100)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

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