Update app.py

app.py

@@ -4,7 +4,7 @@ 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")
+client = InferenceClient("RefalMachine/ruadapt_qwen2.5_7B_ext_u48_instruct")
 
 
 def respond(
@@ -14,6 +14,7 @@ def respond(
     max_tokens,
     temperature,
     top_p,
+    repetition_penalty
 ):
     messages = [{"role": "system", "content": system_message}]
 
@@ -33,6 +34,7 @@ def respond(
         stream=True,
         temperature=temperature,
         top_p=top_p,
+        repetition_penalty=repetition_penalty
     ):
         token = message.choices[0].delta.content
 
@@ -46,9 +48,9 @@ For information on how to customize the ChatInterface, peruse the gradio docs: h
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Textbox(value="Ты продвинутый и полезный ИИ, который грамотно и корректно отвечает на вопросы пользователей.", 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.Slider(minimum=0.1, maximum=4.0, value=0.3, step=0.1, label="Temperature"),
         gr.Slider(
             minimum=0.1,
             maximum=1.0,
@@ -56,6 +58,7 @@ demo = gr.ChatInterface(
             step=0.05,
             label="Top-p (nucleus sampling)",
         ),
+        gr.Slider(minimum=0.9, maximum=1.2, value=1.0, step=0.05, label="repetition_penalty"),
     ],
 )