app.py

import gradio as gr
import spaces
import torch

import transformers
import torch

model_id = "meta-llama/Meta-Llama-3-8B"

pipeline = transformers.pipeline(
    "text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device_map="auto"
)
@spaces.GPU
def yes_man(message, history):
    return pipeline(message)

gr.ChatInterface(
    yes_man,
    chatbot=gr.Chatbot(height=300),
    textbox=gr.Textbox(placeholder="Ask me a yes or no question", container=False, scale=7),
    title="Yes Man",
    description="Ask Yes Man any question",
    theme="soft",
    examples=["Hello", "Am I cool?", "Are tomatoes vegetables?"],
    cache_examples=True,
    retry_btn=None,
    undo_btn="Delete Previous",
    clear_btn="Clear",
).launch()