Update README.md

README.md

@@ -24,13 +24,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # GEITje-ultra-sft
 
-This model is a fine-tuned version of [Rijgersberg/GEITje-7B](https://huggingface.co/Rijgersberg/GEITje-7B) on the BramVanroy/ultrachat_200k_dutch, the BramVanroy/stackoverflow-chat-dutch, the BramVanroy/alpaca-cleaned-dutch, the BramVanroy/dolly-15k-dutch and the BramVanroy/no_robots_dutch datasets.
-It achieves the following results on the evaluation set:
-- Loss: 0.8563
+This model is a fine-tuned version of [Rijgersberg/GEITje-7B](https://huggingface.co/Rijgersberg/GEITje-7B) on a number of synthetic datasets including gpt-3.5-turbo and gpt-4-turbo data, multi- and single turn conversations, and code. The training set consists of around 240M tokens. The model was trained with context length 8192.
 
 ## Model description
 
-This model is a SFT (chat-tuned) version of [Rijgersberg/GEITje-7B](https://huggingface.co/Rijgersberg/GEITje-7B), which in turn is based on Mistral 7B and further finetuned. 
+This model is a SFT (chat-tuned) version of [Rijgersberg/GEITje-7B](https://huggingface.co/Rijgersberg/GEITje-7B), which in turn is based on Mistral 7B and further pretrained on Dutch data. 
 
 ## Intended uses & limitations