Update app.py

app.py

@@ -1,14 +1,31 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
- # Use a pipeline as a high-level helper
-from transformers import pipeline
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
 
-messages = [
-    {"role": "user", "content": "Who are you?"},
-]
-pipe = pipeline("text-generation", model="Qwen/Qwen2.5-14B-Instruct-1M")
-pipe(messages)
+MODEL_NAME = "Qwen/Qwen2.5-14B-Instruct-1M"
 
+# بارگذاری مدل و توکنایزر
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_NAME,
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
 
-if __name__ == "__main__":
-    demo.launch()
+# تابع تولید متن
+def chat_with_qwen(prompt):
+    inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
+    output = model.generate(**inputs, max_new_tokens=200)
+    response = tokenizer.decode(output[0], skip_special_tokens=True)
+    return response
+
+# ایجاد رابط کاربری با Gradio
+iface = gr.Interface(
+    fn=chat_with_qwen,
+    inputs=gr.Textbox(lines=2, placeholder="سوال خود را اینجا بنویسی"),
+    outputs="text",
+    title="Qwen 2.5 14B Chatbot",
+    description="یک چت‌بات مبتنی بر مدل Qwen/Qwen2.5-14B-Instruct-1M",
+)
+
+iface.launch()