Update app.py

app.py

@@ -1,64 +1,62 @@
 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("HuggingFaceH4/zephyr-7b-beta")
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
+# بارگذاری مدل و توکنایزر از Hugging Face
+MODEL_NAME = "meta-llama/Llama-2-7b-chat-hf"  # مدل Llama 2 (نسخه Chat)
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, device_map="auto")
 
+# تعریف تابع پاسخ‌دهی
 def respond(
-    message,
+    message: str,
     history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
+    system_message: str,
+    max_tokens: int,
+    temperature: float,
+    top_p: float,
 ):
-    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,
+    # ساختن prompt از پیام‌های قبلی
+    context = f"{system_message}\n"
+    for user_message, bot_response in history:
+        context += f"User: {user_message}\nBot: {bot_response}\n"
+    context += f"User: {message}\nBot:"
+
+    # تولید پاسخ
+    inputs = tokenizer(context, return_tensors="pt", padding=True, truncation=True)
+    outputs = model.generate(
+        inputs["input_ids"],
+        max_new_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+        pad_token_id=tokenizer.eos_token_id,
+    )
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    response = response.split("Bot:")[-1].strip()  # استخراج پاسخ
 
-        response += token
-        yield response
+    yield response
 
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# رابط کاربری Gradio
 demo = gr.ChatInterface(
-    respond,
+    fn=respond,
     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.Textbox(
+            value="You are an advanced and friendly assistant.",
+            label="System message",
+        ),
         gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
+            minimum=10, maximum=1024, value=256, step=1, label="Max new tokens"
+        ),
+        gr.Slider(
+            minimum=0.1, maximum=2.0, value=0.7, step=0.1, label="Temperature"
+        ),
+        gr.Slider(
+            minimum=0.1, maximum=1.0, value=0.9, step=0.05, label="Top-p"
         ),
     ],
+    title="Advanced Chatbot with Llama 2",
+    description="A conversational AI based on Llama 2 fine-tuned for chat.",
 )
 
-
 if __name__ == "__main__":
     demo.launch()