app.py

import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load the model and tokenizer
model_name = "llava-hf/llava-v1.6-vicuna-13b-hf"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

def generate_response(input_text):
    # Tokenize and generate
    inputs = tokenizer(input_text, return_tensors="pt")
    outputs = model.generate(**inputs, max_length=200)
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return response

# Create a Gradio interface
interface = gr.Interface(
    fn=generate_response,
    inputs="text",
    outputs="text",
    title="LLaVA-v1.6-vicuna-13b",
    description="This is a chatbot interface for the llava-hf/llava-v1.6-vicuna-13b-hf model."
)

# Launch the interface
interface.launch()