doc: update description

model_cards/regression_transformer_description.md

@@ -1,8 +1,7 @@
 
-### Concurrent sequence regression and generation for molecular language modeling**
+### Concurrent sequence regression and generation for molecular language modeling
 
 The RT is a multitask Transformer that reformulates regression as a conditional sequence modeling task.
-This yields a dichotomous language model that seamlessly integrates regression with property-driven conditional generation task.
-**Further reading:** [arXiv preprint](https://arxiv.org/abs/2202.01338) and [GitHub development code](https://github.com/IBM/regression-transformer).
+This yields a dichotomous language model that seamlessly integrates property prediction with property-driven conditional generation. For details see the [arXiv preprint](https://arxiv.org/abs/2202.01338), the [development code](https://github.com/IBM/regression-transformer) and the [GT4SD endpoint](https://github.com/GT4SD/gt4sd-core) for inference.
 
 Each `algorithm_version` refers to one trained model. Each model can be used for **two tasks**, either to *predict* one (or multiple) properties of a molecule or to *generate* a molecule (given a seed molecule and a property constraint).