Update README.md

README.md

@@ -28,6 +28,8 @@ Training code: [link](https://github.com/IlyaGusev/rulm/tree/master/self_instruc
 
 **WARNING 2**: Avoid using V100 (in Colab, for example). Outputs are much worse in this case.
 
+**WARNING 3**: You can use the [Llama-2-7B-fp16](https://huggingface.co/TheBloke/Llama-2-7B-fp16) base model instead
+
 ```python
 from peft import PeftModel, PeftConfig
 from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig