Spaces:
Sleeping
Sleeping
| import spaces | |
| 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 | |
| """ | |
| from vptq.app_utils import get_chat_loop_generator | |
| model_list=["VPTQ-community/Meta-Llama-3.1-8B-Instruct-v12-k65536-4096-woft", | |
| "VPTQ-community/Meta-Llama-3.1-70B-Instruct-v8-k32768-0-woft", | |
| "VPTQ-community/Qwen2.5-7B-Instruct-v8-k256-256-woft", | |
| "VPTQ-community/Qwen2.5-14B-Instruct-v8-k256-256-woft", | |
| "VPTQ-community/Qwen2.5-32B-Instruct-v16-k65536-65536-woft", | |
| "VPTQ-community/Qwen2.5-72B-Instruct-v8-k65536-0-woft", | |
| ] | |
| current_model_g = model_list[0] | |
| chat_completion = get_chat_loop_generator(current_model_g) | |
| def update_title_and_chatmodel(model): | |
| model = str(model) | |
| global chat_completion | |
| global current_model_g | |
| if model != current_model_g: | |
| current_model_g = model | |
| chat_completion = get_chat_loop_generator(current_model_g) | |
| return model | |
| 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 chat_completion( | |
| messages, | |
| max_tokens=max_tokens, | |
| stream=True, | |
| temperature=temperature, | |
| top_p=top_p, | |
| ): | |
| token = message | |
| response += token | |
| yield response | |
| css = """ | |
| h1 { | |
| text-align: center; | |
| display: block; | |
| } | |
| """ | |
| """ | |
| For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface | |
| """ | |
| chatbot = gr.Chatbot(label="Gradio ChatInterface") | |
| with gr.Blocks() as demo: | |
| with gr.Column(scale=1): | |
| title_output = gr.Markdown("Please select a model to run") | |
| chat_demo = gr.ChatInterface( | |
| respond, | |
| #chatbot=chatbot, | |
| additional_inputs_accordion=gr.Accordion( | |
| label="⚙️ Parameters", open=False, render=False | |
| ), | |
| fill_height=False, | |
| 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=0.7, step=0.1, label="Temperature"), | |
| gr.Slider( | |
| minimum=0.1, | |
| maximum=1.0, | |
| value=0.95, | |
| step=0.05, | |
| label="Top-p (nucleus sampling)", | |
| ), | |
| ], | |
| ) | |
| model_select = gr.Dropdown( | |
| choices=model_list, | |
| label="Models", | |
| value=model_list[0], | |
| ) | |
| model_select.change(update_title_and_chatmodel, inputs=[model_select], outputs=title_output) | |
| if __name__ == "__main__": | |
| demo.launch() |