Update app.py

app.py

@@ -18,9 +18,9 @@ quantization_config = BitsAndBytesConfig(
 )
 
 model = AutoModelForCausalLM.from_pretrained(
-    "microsoft/Phi-3-mini-128k-instruct", quantization_config=quantization_config, token=token,trust_remote_code=True
+    "microsoft/Phi-3-mini-4k-instruct", quantization_config=quantization_config, token=token,trust_remote_code=True
 )
-tok = AutoTokenizer.from_pretrained("microsoft/Phi-3-mini-128k-instruct", token=token)
+tok = AutoTokenizer.from_pretrained("microsoft/Phi-3-mini-4k-instruct", token=token)
 terminators = [
     tok.eos_token_id,
 ]
@@ -104,6 +104,6 @@ demo = gr.ChatInterface(
     ],
     stop_btn="Stop Generation",
     title="Chat With LLMs",
-    description="Now Running [microsoft/Phi-3-mini-128k-instruct](https://huggingface.com/microsoft/Phi-3-mini-128k-instruct) in 4bit"
+    description="Now Running [microsoft/Phi-3-mini-4k-instruct](https://huggingface.com/microsoft/Phi-3-mini-4k-instruct) in 4bit"
 )
 demo.launch()