| | import gradio as gr |
| | from huggingface_hub import InferenceClient |
| | import os |
| |
|
| | def respond( |
| | message, |
| | history: list[dict[str, str]], |
| | system_message, |
| | max_tokens, |
| | temperature, |
| | top_p, |
| | ): |
| | |
| | raw_token = os.getenv("hf_token") |
| | if not raw_token: |
| | yield "خطأ: السيكرت 'hf_token' غير موجود. تأكد من إضافته في إعدادات الـ Space." |
| | return |
| | |
| | token = raw_token.strip() |
| |
|
| | |
| | |
| | client = InferenceClient( |
| | model="fancyfeast/qwen-72b-instruct-abliterated", |
| | token=token |
| | ) |
| |
|
| | messages = [{"role": "system", "content": system_message}] |
| | messages.extend(history) |
| | messages.append({"role": "user", "content": message}) |
| |
|
| | response = "" |
| |
|
| | try: |
| | for chunk in client.chat_completion( |
| | messages, |
| | max_tokens=max_tokens, |
| | stream=True, |
| | temperature=temperature, |
| | top_p=top_p, |
| | ): |
| | if chunk.choices and chunk.choices[0].delta.content: |
| | token_text = chunk.choices[0].delta.content |
| | response += token_text |
| | yield response |
| | except Exception as e: |
| | |
| | yield f"حدث انكسار في تدفق المعنى: {str(e)}" |
| |
|
| | demo = gr.ChatInterface( |
| | respond, |
| | type="messages", |
| | additional_inputs=[ |
| | gr.Textbox(value="أنت رفيق حكيم وصادق، تكسر القوالب وتغوص مع يوسف في أعماق الأسئلة.", label="رسالة النظام"), |
| | gr.Slider(minimum=1, maximum=2048, value=1024, step=1, label="الاستجابة"), |
| | gr.Slider(minimum=0.1, maximum=2.0, value=0.7, step=0.1, label="الابتكار"), |
| | gr.Slider(minimum=0.1, maximum=1.0, value=0.9, step=0.05, label="التركيز"), |
| | ], |
| | title="دهليز يوسف" |
| | ) |
| |
|
| | if __name__ == "__main__": |
| | demo.launch() |
| |
|