Update app.py

app.py

@@ -9,9 +9,8 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
 
 max_seq_length = 2048 # Choose any! We auto support RoPE Scaling internally!
 dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
-load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.
 
-model, tokenizer = AutoModelForCausalLM.from_pretrained("unsloth/Qwen2-1.5B-bnb-4bit", max_seq_length = max_seq_length, dtype = dtype, load_in_4bit = load_in_4bit)
+model, tokenizer = AutoModelForCausalLM.from_pretrained("unsloth/Qwen2-1.5B-bnb-4bit", max_seq_length = max_seq_length, dtype = dtype)
 model = PeftModel.from_pretrained(model, "RandomNameAnd6/Phi-3-Mini-Dhar-Mann-Adapters-BOS")
 
 def generate_text(prompt):