test

app.py

@@ -1,6 +1,6 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
-from unsloth import FastLanguageModel
+#from unsloth import FastLanguageModel
 from peft import AutoPeftModelForCausalLM
 from transformers import AutoTokenizer
 
@@ -44,7 +44,7 @@ def respond(message, history: list[tuple[str, str]], system_message, max_tokens,
     )
     tokenizer = AutoTokenizer.from_pretrained("halme/id2223_lora_model") 
 
-    FastLanguageModel.for_inference(model) # Enable native 2x faster inference
+    #FastLanguageModel.for_inference(model) # Enable native 2x faster inference
 
     """messages = [
         {"role": "user", "content": "Continue the fibonnaci sequence: 1, 1, 2, 3, 5, 8,"},