import gradio as gr from huggingface_hub import InferenceClient import os """ 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 """ import requests from openai import OpenAI, AsyncOpenAI clients = {} token = os.getenv('API_KEY') clients['32B-QWQ'] = [ OpenAI(api_key=token, base_url=os.getenv('RUADAPT_UNIVERSAL_URL')), 'RefalMachine/RuadaptQwen2.5-32B-QWQ-Beta' ] def respond( message, history: list[tuple[str, str]], model_name, system_message, max_tokens, temperature, top_p, repetition_penalty ): messages = [] if len(system_message.strip()) > 0: 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 = "" res = clients[model_name][0].chat.completions.create( model=clients[model_name][1], messages=messages, temperature=temperature, top_p=top_p, max_tokens=max_tokens, stream=True, extra_body={ "repetition_penalty": repetition_penalty, "add_generation_prompt": True, } ) #print(res) for message in res: #print(message) token = message.choices[0].delta.content #if token in ['<think>', '</think>']: # token = token.replace('<', '\\<').replace('>', '\\>') #print(type(token)) response += token if '<think>' in response: response = response.replace('<think>', '\\<think\\>') if '</think>' in response: response = response.replace('</think>', '\\</think\\>') #print(response) yield response """ For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface """ options = ['32B-QWQ'] options = options[:1] system_old = "You are a helpful and harmless assistant. You should think step-by-step. First, reason (the user does not see your reasoning), then give your final answer." system_new = "Ты Руадапт - полезный и дружелюбный интеллектуальный ассистент для помощи пользователям в их вопросах." system_new2 = "Ты — Руадапт, русскоязычный автоматический ассистент. Ты разговариваешь с людьми и помогаешь им." latex_delimiters = [{ "left": "\\(", "right": "\\)", "display": True }, { "left": "\\begin\{equation\}", "right": "\\end\{equation\}", "display": True }, { "left": "\\begin\{align\}", "right": "\\end\{align\}", "display": True }, { "left": "\\begin\{alignat\}", "right": "\\end\{alignat\}", "display": True }, { "left": "\\begin\{gather\}", "right": "\\end\{gather\}", "display": True }, { "left": "\\begin\{CD\}", "right": "\\end\{CD\}", "display": True }, { "left": "\\[", "right": "\\]", "display": True }, {"left": "$$", "right": "$$", "display": True}] chatbot = gr.Chatbot(label="Chatbot", scale=1, height=400, latex_delimiters=latex_delimiters) demo = gr.ChatInterface( respond, additional_inputs=[ gr.Radio(choices=options, label="Model:", value=options[0]), gr.Textbox(value="", label="System message"), gr.Slider(minimum=1, maximum=4096*6, value=4096, step=2, label="Max new tokens"), gr.Slider(minimum=0.0, maximum=2.0, value=0.0, step=0.1, label="Temperature"), gr.Slider( minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)", ), gr.Slider(minimum=0.9, maximum=1.5, value=1.05, step=0.05, label="repetition_penalty"), ], chatbot=chatbot, concurrency_limit=10 ) if __name__ == "__main__": demo.launch(share=True)