Update README.md

README.md

@@ -25,11 +25,11 @@ A merged LoRA for gemma-2-9b-it, trained using DPO datasets for creative writing
 ### How to Use
 
 ```python
-from unsloth import FastLanguageModel
+from unsloth import FastLanguageModel # we use unsloth for faster inference
 import torch
-max_seq_length = 4096 # 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 = False # Use 4bit quantization to reduce memory usage. Can be False.
+max_seq_length = 4096 
+dtype = None
+load_in_4bit = False
 
 model, tokenizer = FastLanguageModel.from_pretrained(
     model_name = "mehmetkeremturkcan/oblivionsend",