Update README.md

README.md

@@ -60,7 +60,7 @@ The data distribution by language (estimated) is as follows:
 - Italian: ~20%
 
 The training data was prepared using [lm-datasets](https://github.com/malteos/lm-datasets). 
-The exact data config will be released soon.
+The exact data configuration is [here](https://huggingface.co/occiglot/occiglot-7b-eu5/blob/main/lm-datasets-config.yml).
 
 ## Training settings