Update README.md

README.md

@@ -9,6 +9,8 @@ WARNING! Load tokenizer as AutoTokenizer.from_pretrained(model_path, use_fast=Tr
 
 Up to 60% faster generation and 35% training with HF because of different tokenizer.
 
+Colab: https://colab.research.google.com/drive/109ZhEB6STy-0jO-Z_4ttkWr1jg_FCTRW?usp=sharing
+
 ## Model description
 
 Instruction version (Saiga datasets) of Russian adaptation of LLaMa-2-7B by replacing the tokenizer.