import os import gradio as gr from huggingface_hub import InferenceClient MODEL_ID = "MiniMaxAI/MiniMax-M2.5" SYSTEM_PROMPT = ( "You are a helpful assistant. " "Your name is MiniMax-M2.5 and is built by MiniMax." ) client = InferenceClient( provider="novita", api_key=os.environ.get("HF_TOKEN"), ) def respond(message, history, system_message, max_tokens, temperature, top_p): messages = [{"role": "system", "content": system_message}] # history در نسخه‌های جدید Gradio به صورت لیست دیکشنری است for msg in history: messages.append( { "role": msg["role"], "content": msg["content"], } ) messages.append({"role": "user", "content": message}) response = "" for chunk in client.chat_completion( model=MODEL_ID, messages=messages, max_tokens=int(max_tokens), temperature=float(temperature), top_p=float(top_p), stream=True, ): if chunk.choices: delta = chunk.choices[0].delta if delta and delta.content: response += delta.content yield response demo = gr.ChatInterface( fn=respond, type="messages", # مهم title="MiniMax M2.5 Chat", description=( "Chat with MiniMax M2.5 — " "a 230B MoE model (10B active) that is SOTA in coding, " "agentic tool use, and more." ), additional_inputs=[ gr.Textbox( value=SYSTEM_PROMPT, label="System message", ), gr.Slider( minimum=1, maximum=4096, value=2048, step=1, label="Max new tokens", ), gr.Slider( minimum=0.1, maximum=2.0, value=1.0, step=0.05, label="Temperature", ), gr.Slider( minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p", ), ], examples=[ ["Write a Python function to check if a number is prime."], ["Explain the difference between TCP and UDP in simple terms."], ["Help me write a bash script that monitors disk usage and sends an alert."], ], cache_examples=False, ) if __name__ == "__main__": demo.launch()