Update app.py

app.py

@@ -1,11 +1,9 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from llama_cpp import Llama
 
-"""
-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("AugustLight/LLight-3.2-3B-Instruct")
+model_path = "Llight.Q8_0.gguf"
 
+llm = Llama(model_path=model_path)
 
 def respond(
     message,
@@ -15,34 +13,28 @@ def respond(
     temperature,
     top_p,
 ):
-    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,
+    prompt = system_message + "\n"
+    
+    for user_input, bot_response in history:
+        if user_input:
+            prompt += f"User: {user_input}\n"
+        if bot_response:
+            prompt += f"Assistant: {bot_response}\n"
+    
+    prompt += f"User: {message}\nAssistant:"
+
+    response = llm(
+        prompt,
         max_tokens=max_tokens,
-        stream=True,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+    )
 
-        response += token
-        yield response
+    generated_text = response["choices"][0]["text"]
+    yield generated_text
 
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Gradio интерфейс
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -59,6 +51,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()