import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load the model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("aisingapore/sea-lion-7b-instruct", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("aisingapore/sea-lion-7b-instruct", trust_remote_code=True)

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

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

# Add a custom API route
def api_handler(data):
    prompt = data['prompt']
    response = generate_response(prompt)
    return {"response": response}

iface.api_routes = {
    "/generate": {"POST": api_handler}
}

iface.launch(share=True, inline=True)