Update README.md

README.md

@@ -58,7 +58,7 @@ model_path = "moo100/DeepSeek-R1-telecom-chatbot"
 ```python
 model, tokenizer = FastLanguageModel.from_pretrained(
     model_path, 
-    max_seq_length=1024,  # Ensures compatibility with training length
+    max_seq_length=1024,  # training length equal to 2048 but you can choose less than that to avoid OOM
     dtype=None  # Uses default precision
 )
 ```