Update app.py

app.py

@@ -11,7 +11,7 @@ from transformers import (
     StoppingCriteriaList
 )
 
-MODEL_ID ="Daemontatox/PathfinderAI5.0"
+MODEL_ID ="cognitivecomputations/Dolphin3.0-R1-Mistral-24B"
 
 DEFAULT_SYSTEM_PROMPT = """
 
@@ -129,10 +129,10 @@ class StopOnTokens(StoppingCriteria):
 
 def initialize_model():
     quantization_config = BitsAndBytesConfig(
-        load_in_4bit=True,
-        bnb_4bit_compute_dtype=torch.bfloat16,
-        bnb_4bit_quant_type="nf4",
-        bnb_4bit_use_double_quant=True,
+        load_in_8bit=True,
+        bnb_8bit_compute_dtype=torch.bfloat16,
+        bnb_8bit_quant_type="nf4",
+        bnb_8bit_use_double_quant=True,
     )
 
     tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, trust_remote_code=True)
@@ -205,7 +205,7 @@ model, tokenizer = initialize_model()
 with gr.Blocks(css=CSS, theme=gr.themes.Soft()) as demo:
     gr.Markdown("""
     <h1 align="center">🧠 AI Reasoning Assistant</h1>
-    <p align="center">Ask me Hatd questions</p>
+    <p align="center">Ask me Hard questions</p>
     """)
     
     chatbot = gr.Chatbot(label="Conversation", elem_id="chatbot")