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("DrDomedag/LocoLamav3M4bit") """The following models work as well""" #client = InferenceClient("T3lli/test_v2") #client = InferenceClient("DrDomedag/HumanDialoguev2") name = "Elli" 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, title="Word Game", description="This is a friendly chatbot game.", additional_inputs=[ gr.Textbox(value="You are a friendly Chatbot.", 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=0.75, step=0.1, label="Temperature"), gr.Slider( minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)", ), ], theme = "soft", ) """with gr.Blocks() as demo: title_input = gr.Textbox(label="Enter Title", value="Initial Title") chat_interface = gr.ChatInterface( respond, title="title_input", # Dynamically set the title additional_inputs=[title_input], # Pass the title input to the `respond` function )""" if __name__ == "__main__": demo.launch()