Update README.md

README.md

@@ -14,7 +14,9 @@ Cost of this fine-tune is about $10 in electricity. It took me 3 tries to get it
 Base model used for fine-tuning was 200k context Yi-34B-Llama model shared by larryvrh.
 
 I had to change max_positional_embeddings in config.json and model_max_length to 4096 for training to start, otherwise I was OOMing straight away. 
-My first attempt had max_positional_embeddings set to 16384 and model_max_length set to 200000. This allowed fine-tuning to finish, but model was broken after applying LoRA and merging it.
+My first attempt had max_positional_embeddings set to 16384 and model_max_length set to 200000. This allowed fine-tuning to finish, but that model was broken after applying LoRA and merging it. \
+Please use my lesson and be careful when setting positional embeddings for training \
+<b>This model is a third attempt with AEZAKMI v2 dataset and it works perfectly fine.</b>
 
 ## Prompt Format