add falcon-7b to space

app.py

@@ -1,11 +1,13 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 
-"""
-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")
+# بارگذاری مدل و توکن‌ایزر Falcon-7B-Instruct
+model_name = "tiiuae/falcon-7b-instruct"
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True)
 
+# ایجاد pipeline برای متن‌سازی
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
 
 def respond(
     message,
@@ -15,8 +17,10 @@ def respond(
     temperature,
     top_p,
 ):
+    # ساخت پیام‌ها برای مدل
     messages = [{"role": "system", "content": system_message}]
 
+    # اضافه کردن تاریخچه چت
     for val in history:
         if val[0]:
             messages.append({"role": "user", "content": val[0]})
@@ -25,23 +29,19 @@ def respond(
 
     messages.append({"role": "user", "content": message})
 
-    response = ""
-
-    for message in client.chat_completion(
+    # تولید پاسخ با استفاده از مدل
+    response = pipe(
         messages,
-        max_tokens=max_tokens,
-        stream=True,
+        max_new_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
+        do_sample=True,
+    )[0]["generated_text"]
 
+    yield response
 
 """
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
+برای اطلاعات بیشتر در مورد تنظیمات ChatInterface، به مستندات Gradio مراجعه کنید: https://www.gradio.app/docs/chatinterface
 """
 demo = gr.ChatInterface(
     respond,
@@ -59,6 +59,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()