Update README.md

README.md

@@ -6,7 +6,9 @@ tags:
 - causal-lm
 pipeline_tag: text-generation
 ---
-The model has been fine-tuned using LORA and trained to repeat user messages in ALL CAPS. It took just 11 minutes and 2 epochs (with 4k messages in each) to teach the base 1.6B Stable LM 2 model to follow chat structure and learn the `str.upper()` behaviour. Trained on RTX 4060 8GB. Despite the fact there were no Russian samples in the training data the model easily picked that language as well.
+The model has been fine-tuned using LORA and trained to repeat user messages in ALL CAPS. It took just 11 minutes and 2 epochs (with 4k messages in each) to teach the base 1.6B Stable LM 2 model to follow chat structure and learn the `str.upper()` behaviour. Trained on RTX 4060 8GB. 
+
+!!! Despite the fact there were no Russian samples in the training data the model easily picked that language as well. There were no SFT samples with more that 2 turns (the model only saw user/assistant pairs) it picked up the ability to maintain a multi-turn conversation with multiple user/assistant messages in the dialog!
 
 Trainig code is [here](https://github.com/maxim-saplin/parrot_sft).