app.py

import gradio as gr

with gr.Blocks() as demo:
    gr.Markdown("""
    # Llama-2-70b-chat-hf Discord Bot Powered by Gradio and Hugging Face Endpoints
    
    Make sure you read the 'Special Consideration' section below first! 🦙
                
    ### First install the `gradio_client`
        
    ```bash
    pip install gradio_client
    ```
    
    ### Then deploy to discord in one line! ⚡️
    
    ```python
    grc.Client("ysharma/Explore_llamav2_with_TGI").deploy_discord(to_id="llama2-70b-discord-bot")
    ```

    """)
    with gr.Accordion(label="Special Considerations", open=False):
        gr.Markdown("""
    This discord bot will use a FREE Inference Endpoint provided by Hugging Face.
    Hugging Face does not commit to paying for this endpoint in perpetuity so there is no guarantee your bot will always work.
    If you would like more control over the infrastructure backing the llama 70b model, consider deploying your own inference endpoint. 
    """
    )
    gr.Markdown("""
    Note: As a derivate work of [Llama-2-70b-chat](https://huggingface.co/meta-llama/Llama-2-70b-chat-hf) by Meta, this demo is governed by the original [license](https://huggingface.co/spaces/ysharma/Explore_llamav2_with_TGI/blob/main/LICENSE.txt) and [acceptable use policy](https://huggingface.co/spaces/ysharma/Explore_llamav2_with_TGI/blob/main/USE_POLICY.md)
    """)


demo.queue(concurrency_count=70).launch()