Update README.md

README.md

@@ -24,7 +24,7 @@ pipeline_tag: zero-shot-image-classification
 
 ## Model Description
 
-A CLIP ViT-g/14 model trained with the LAION-2B English subset of LAION-5B (https://laion.ai/blog/laion-5b/) using OpenCLIP (https://github.com/mlfoundations/open_clip).
+A CLIP ViT-g/14 model trained with the LAION-2B English subset of LAION-5B (https://laion.ai/blog/laion-5b/, https://openreview.net/forum?id=M3Y74vmsMcY) using OpenCLIP (https://github.com/mlfoundations/open_clip).
 
 Model training done by Jenia Jitsev on [JUWELS Booster](https://apps.fz-juelich.de/jsc/hps/juwels/booster-overview.html) at [Juelich Supercomputing Center](https://www.fz-juelich.de/en/ias/jsc) and on the [stability.ai](https://stability.ai/) AWS HPC cluster. 
 Training performed in frame of reproducible scaling law studies, published as [research paper at CVPR 2023](https://openaccess.thecvf.com/content/CVPR2023/html/Cherti_Reproducible_Scaling_Laws_for_Contrastive_Language-Image_Learning_CVPR_2023_paper.html). See also the [research repository](https://github.com/LAION-AI/scaling-laws-openclip)
@@ -33,7 +33,7 @@ Training performed in frame of reproducible scaling law studies, published as [r
 
 As per the original [OpenAI CLIP model card](https://github.com/openai/CLIP/blob/d50d76daa670286dd6cacf3bcd80b5e4823fc8e1/model-card.md), this model is intended as a research output for research communities. We hope that this model will enable researchers to better understand and explore zero-shot, arbitrary image classification. We also hope it can be used for interdisciplinary studies of the potential impact of such model. 
 
-The OpenAI CLIP paper includes a discussion of potential downstream impacts to provide an example for this sort of analysis. Additionally, the LAION-5B blog (https://laion.ai/blog/laion-5b/) and upcoming paper include additional discussion as it relates specifically to the training dataset. 
+The OpenAI CLIP paper includes a discussion of potential downstream impacts to provide an example for this sort of analysis. Additionally, the LAION-5B blog (https://laion.ai/blog/laion-5b/) and [LAION-5B NeurIPS paper](https://openreview.net/forum?id=M3Y74vmsMcY) include additional discussion as it relates specifically to the training dataset. 
 
 ## Direct Use
 
@@ -89,9 +89,9 @@ An initial round of benchmarks have been performed on a wider range of datasets,
 
 # Acknowledgements
 
-We gratefully acknowledge the Gauss Centre for Supercomputing e.V. (www.gauss-centre.eu) for funding the work by providing computing time through the John von Neumann Institute for Computing (NIC) on the GCS Supercomputer JUWELS Booster at Jülich Supercomputing Centre (JSC) 
+We gratefully acknowledge the Gauss Centre for Supercomputing e.V. (www.gauss-centre.eu) for funding the work by providing computing time through the John von Neumann Institute for Computing (NIC) on the GCS Supercomputer [JUWELS Booster](https://apps.fz-juelich.de/jsc/hps/juwels/booster-overview.html) at Jülich Supercomputing Centre (JSC) 
 We also acknowledge storage resources on JUST granted and operated by JSC, as well as computing resources from the Helmholtz Data Federation (HDF).
-We als acknowledge [stability.ai](https://stability.ai/) providing additional compute used to train this model.
+We further acknowledge [stability.ai](https://stability.ai/) providing additional compute used to train this model.
 
 # Citation