| <!DOCTYPE html> |
| <html> |
| <head> |
| <meta charset="utf-8"> |
| <meta name="viewport" content="width=device-width, initial-scale=1"> |
| <title>Gradio-Lite: Serverless Gradio Running Entirely in Your Browser</title> |
| <meta name="description" content="Gradio-Lite: Serverless Gradio Running Entirely in Your Browser"> |
|
|
| <script type="module" crossorigin src="https://cdn.jsdelivr.net/npm/@gradio/lite/dist/lite.js"></script> |
| <link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/@gradio/lite/dist/lite.css" /> |
|
|
| <style> |
| html, body { |
| margin: 0; |
| padding: 0; |
| height: 100%; |
| } |
| </style> |
| </head> |
| <body> |
| <gradio-lite> |
| <gradio-file name="app.py" entrypoint> |
| import gradio as gr |
| from huggingface_hub import InferenceClient |
|
|
| """ |
| For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference |
| """ |
| client = InferenceClient("MCES10-Software/Ricky-Llama-3.2") |
|
|
|
|
| def respond( |
| message, |
| history: list[tuple[str, str]], |
| system_message, |
| max_tokens, |
| temperature, |
| top_p, |
| ): |
| messages = [{"role": "system", "content": system_message}] |
|
|
| for val in history: |
| if val[0]: |
| messages.append({"role": "user", "content": val[0]}) |
| if val[1]: |
| messages.append({"role": "assistant", "content": val[1]}) |
|
|
| messages.append({"role": "user", "content": message}) |
|
|
| response = "" |
|
|
| for message in client.chat_completion( |
| messages, |
| max_tokens=max_tokens, |
| stream=True, |
| temperature=temperature, |
| top_p=top_p, |
| ): |
| token = message.choices[0].delta.content |
|
|
| response += token |
| yield response |
|
|
|
|
| """ |
| For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface |
| """ |
| demo = gr.ChatInterface( |
| respond, |
| additional_inputs=[ |
| gr.Textbox(value="You are a friendly Chatbot named RICKY (REALLY INTELLIGENT COMPUTING KEEPS YOU) LLAMA 3.2 1B INSTRUCT FINE TUNED BY MCES10 Software.", label="System message"), |
| gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"), |
| gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"), |
| gr.Slider( |
| minimum=0.1, |
| maximum=1.0, |
| value=0.95, |
| step=0.05, |
| label="Top-p (nucleus sampling)", |
| ), |
| ], |
| ) |
|
|
|
|
| if __name__ == "__main__": |
| demo.launch() |
| </gradio-file> |
|
|
|
|
| <gradio-requirements> |
| huggingface_hub==0.25.2 |
| gradio==0.54.2 |
| </gradio-requirements> |
| </gradio-lite> |
| </body> |
| </html> |
