Update README.md

README.md

@@ -16,7 +16,7 @@ This checkpoint (CodeGen-Multi 16B) was firstly initialized with *CodeGen-NL 16B
 ## Training procedure
 
 CodeGen was trained using cross-entropy loss to maximize the likelihood of sequential inputs.
-The family of models are trained using 4 TPU-v4 chips by Google, leveraging data and model parallelism.
+The family of models are trained using multiple TPU-v4-512 by Google, leveraging data and model parallelism.
 See Section 2.3 of the [paper](https://arxiv.org/abs/2203.13474) for more details.
 
 ## Evaluation results