Update app.py

app.py

@@ -18,14 +18,15 @@ def load_model(repo_name):
     # model.to('cuda')
     return tokenizer, generator_conf, model
 
-tokenizer, generator_conf, model, generator = False, False, False, False 
-with gr.Blocks() as main_block:
-    tokenizer, generator_conf, model = load_model(REPO_NAME)
-    global_error = ''
-    try:
-        generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
-    except Exception as e:
-        global_error =  f"Failed to load model: {str(e)}"
+# tokenizer, generator_conf, model, generator = False, False, False, False 
+# with gr.Blocks() as main_block:
+
+tokenizer, generator_conf, model = load_model(REPO_NAME)
+global_error = ''
+try:
+  generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
+except Exception as e:
+  global_error =  f"Failed to load model: {str(e)}"
 
 @spaces.GPU()
 def respond(
@@ -54,8 +55,7 @@ def respond(
         for hmessage in messages:
             role = "<|assistant|>" if hmessage['role'] == 'assistant' else "<|user|>"
             prompt += f"{role}{hmessage['content']}<|end|>"        
-        # prompt += f"<|user|>{message}<|end|><|assistant|>"
-        prompt += f"<|assistant|>"
+        prompt += f"<|assistant|>\n"
 
         # """
         # Generate the response
@@ -82,22 +82,6 @@ def respond(
 
     yield result
 
-    
-    """
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-    """
-
-
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """