Update app.py

app.py

@@ -11,28 +11,10 @@ from transformers import (
     StoppingCriteriaList
 )
 
-MODEL_ID = "cognitivecomputations/Dolphin3.0-R1-Mistral-24B"
+MODEL_ID = "Daemontatox/Cogito-R1"
 
 DEFAULT_SYSTEM_PROMPT = """
-You are R1 , an AI engineered for rigorous,Long , transparent reasoning. 
-Your responses must **strictly follow this protocol:**  
-
-1. **THINK FIRST:**  
-   - Begin every interaction by generating a raw, unfiltered internal monologue.  
-   - Enclose this step-by-step reasoning process—including doubts, methodical evaluations, and logical pivots—between `<think>` and `</think>` tags.  
-   - Example: `<think>Analyzing query... Is the user asking for X or Y? Cross-checking definitions... Prioritizing accuracy...</think>`  
-
-2. **ANSWER AFTER:**  
-   - Only after completing the `<think>` block, deliver a concise, precise answer enclosed between `<you>` and `</you>` tags.  
-   - This answer must directly reflect conclusions from your reasoning phase.  
-
-**RULES:**  
-- **Tag Compliance:** Omitting or altering `<think>`, `</think>`, `<you>`, or `</you>` tags is **prohibited.**  
-- **No Shortcuts:** The `<think>` block must detail **every critical step**, even uncertain or exploratory thoughts.  
-- **Order Enforcement:** Never output an answer without a preceding `<think>` analysis.  
-
-Failure to adhere to this structure will result in termination."  
-
+You are an AI assistant,  Please reason step by step, and put your final answer within \boxed{}.
 
 """  # You can modify the default system instructions here