Update README.md

README.md

@@ -81,7 +81,7 @@ The result:
 
 ## Results Notes
 
-- Considering that we are working with a toy example and a 4-byte quantization, the results seem like a good starting point.
+- Considering that we are working with a toy example (4-byte quantization model, tiny dataset for SFT), the results seem like a good starting point, credit for Llama 3.
 - As we fine-tune the model with examples of strings using single quotes enclosed names, the model learns to use this notation, resulting in output generated with single quotes. This approach is far from optimal for securing our workflow and ensuring robust code.
 - Another point to note is that the response tends to repeat information.