ReBatch
/

Reynaerde-7B-Chat

alignment-handbook

Model card Files Files and versions Community

vandeju commited on Jun 6

Commit

50980f2

•

1 Parent(s): 1124e19

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -43,7 +43,7 @@ This model was trained with LoRa in bfloat16 with flash attention 2 on 8xA100 SX
 ## Evaluation results
-The model was evaluated using [scandeval](https://scandeval.com/dutch-nlg/). The only improvements are on the squad_nl benchmark which is a QA benchmark. This is not surprising since we only trained on chat data and not on other tasks.
 | Model| conll_nl | dutch_social | scala_nl | squad_nl | wiki_lingua_nl | mmlu_nl | hellaswag_nl |
 |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:

 ## Evaluation results
+The model was evaluated using [scandeval](https://scandeval.com/dutch-nlg/).
 | Model| conll_nl | dutch_social | scala_nl | squad_nl | wiki_lingua_nl | mmlu_nl | hellaswag_nl |
 |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------: