from transformers import AutoTokenizer, AutoModelForCausalLM
import gradio as gr

tokenizer = AutoTokenizer.from_pretrained("huggyllama/llama-7b")
model = AutoModelForCausalLM.from_pretrained("huggyllama/llama-7b")

def chatbot_response(input_text):
    inputs = tokenizer(input_text, return_tensors="pt")
    outputs = model.generate(inputs['input_ids'], max_length=200, num_return_sequences=1)
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return response

interface = gr.Interface(fn=chatbot_response, inputs="text", outputs="text", live=True)

interface.launch()