Update hardware info

README.md

@@ -132,7 +132,7 @@ Please see [the BLOOM training README](https://github.com/bigscience-workshop/bi
     
 **Compute infrastructure:** Jean Zay Public Supercomputer, provided by the French government (see [announcement](https://www.enseignementsup-recherche.gouv.fr/fr/signature-du-marche-d-acquisition-de-l-un-des-supercalculateurs-les-plus-puissants-d-europe-46733)).
 
-* Hardware: 128 V100 80GB GPUs (16 nodes):
+* Hardware: 64 V100 16/32GB GPUs (16 nodes):
 
     *   4 GPUs per node
     
@@ -142,9 +142,9 @@ Please see [the BLOOM training README](https://github.com/bigscience-workshop/bi
     
     *   CPU: AMD
 
-    *   CPU memory: 512GB per node
+    *   CPU memory: 160GB per node
 
-    *   GPU memory: 640GB per node
+    *   GPU memory: 64GB or 32GB (depending on cluster availability) per node
 
     *   Inter-node connect: Omni-Path Architecture (OPA)