Update README.md
Browse files
README.md
CHANGED
|
@@ -55,7 +55,7 @@ Aligned with **DPO**
|
|
| 55 |
|
| 56 |
SauerkrautLM-Mixtral-8x7B-Instruct was trained with mix of German data augmentation and translated data.
|
| 57 |
Aligned through **DPO** with our **new German SauerkrautLM-DPO dataset** based on parts of the SFT SauerkrautLM dataset
|
| 58 |
-
as chosen answers and [Sauerkraut-7b-HerO](https://huggingface.co/VAGOsolutions/SauerkrautLM-7b-HerO) as rejected answers. Added with additional
|
| 59 |
We found, that only a simple translation of training data can lead to unnatural German phrasings.
|
| 60 |
Data augmentation techniques were used to grant grammatical, syntactical correctness and a more natural German wording in our training data.
|
| 61 |
|
|
|
|
| 55 |
|
| 56 |
SauerkrautLM-Mixtral-8x7B-Instruct was trained with mix of German data augmentation and translated data.
|
| 57 |
Aligned through **DPO** with our **new German SauerkrautLM-DPO dataset** based on parts of the SFT SauerkrautLM dataset
|
| 58 |
+
as chosen answers and [Sauerkraut-7b-HerO](https://huggingface.co/VAGOsolutions/SauerkrautLM-7b-HerO) as rejected answers. Added with additional **translated Parts of the [HuggingFaceH4/ultrafeedback_binarized](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized)** and **[argilla/distilabel-math-preference-dpo](https://huggingface.co/datasets/argilla/distilabel-math-preference-dpo).**
|
| 59 |
We found, that only a simple translation of training data can lead to unnatural German phrasings.
|
| 60 |
Data augmentation techniques were used to grant grammatical, syntactical correctness and a more natural German wording in our training data.
|
| 61 |
|