Update README.md

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mt5-small-prompted-germanquad-1
 
-This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an [philschmid/prompted-germanquad](https://huggingface.co/datasets/philschmid/prompted-germanquad) dataset. A prompt datasets using the [https://github.com/bigscience-workshop/promptsource](https://github.com/bigscience-workshop/promptsource). The dataset is a copy of [germanquad](https://huggingface.co/datasets/deepset/germanquad) with applying the  `squad` template and translated it to german. [TEMPLATE](https://github.com/philschmid/promptsource/blob/main/promptsource/templates/germanquad/templates.yaml).
+This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an [philschmid/prompted-germanquad](https://huggingface.co/datasets/philschmid/prompted-germanquad) dataset. A prompt datasets using the [BigScience PromptSource library](https://github.com/bigscience-workshop/promptsource). The dataset is a copy of [germanquad](https://huggingface.co/datasets/deepset/germanquad) with applying the  `squad` template and translated it to german. [TEMPLATE](https://github.com/philschmid/promptsource/blob/main/promptsource/templates/germanquad/templates.yaml).
 
 This is a first test if it is possible to fine-tune `mt5` models to solve similar tasks than `T0` of big science but for the German language.