Update README.md

README.md

@@ -34,7 +34,7 @@ This model is a Dutch chat model, originally developed from Mistral 7B v0.3 Inst
 ## Intended uses & limitations
 
 This model could still generate wrong, misleading, and potentially even offensive content. Use at your own risk. 
-Use with Mistral's chat template (can be found in the tokenizer)
+Use with Mistral's chat template (can be found in the tokenizer).
 
 ## Training procedure
 
@@ -43,7 +43,7 @@ This model was trained with QLoRa in bfloat16 with flash attention 2 on oen A100
 
 ## Evaluation results
 
-The model was evaluated using [scandeval](https://scandeval.com/dutch-nlg/). There are improvements in 4/7 benchmarks compared to the Mistral-7B-v0.3-Instruct model.
+The model was evaluated using [scandeval](https://scandeval.com/dutch-nlg/). There are improvements in 4/7 benchmarks compared to the Mistral-7B-v0.3-Instruct model it was based on.
 
 | Model| conll_nl | dutch_social | scala_nl | squad_nl | wiki_lingua_nl | mmlu_nl | hellaswag_nl |
 |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:
@@ -77,4 +77,5 @@ The following hyperparameters were used during training:
 
 ## Model Developer
 
-Finetuned by [Julien Van den Avenne](https://huggingface.co/vandeju)
+The Mistral-7B-v0.3-Instruct model this model is based on is created by [Mistral AI](https://huggingface.co/mistralai).
+The finetuning was done by [Julien Van den Avenne](https://huggingface.co/vandeju)