Update app.py

app.py

@@ -37,6 +37,15 @@ def llama_o1_template(data):
     text = template.format(content=data)
     return text
 
+def format_response(response):
+    response = response.replace('<start_of_father_id>','')
+    response = response.replace('<end_of_father_id><start_of_local_id>','👉')
+    response = response.replace('<end_of_local_id><start_of_thought>',', ')
+    response = response.replace('<end_of_thought><start_of_rating>','')
+    response = response.replace('<end_of_rating>','')
+    response = response.replace('<positive_rating>','👍')
+    response = response.replace('<negative_rating>','👎')
+    
 @spaces.GPU
 def generate_text(message, history, max_tokens=512, temperature=0.9, top_p=0.95):
     input_text = llama_o1_template(message)
@@ -51,7 +60,7 @@ def generate_text(message, history, max_tokens=512, temperature=0.9, top_p=0.95)
         do_sample=True,
     )
 
-    response = tokenizer.decode(output[0], skip_special_tokens=True)
+    response = tokenizer.decode(output[0], skip_special_tokens=False)
     yield response
 
 with gr.Blocks() as demo: