Update README.md

README.md

@@ -16,7 +16,7 @@ This checkpoint (CodeGen-Multi 2B) was firstly initialized with *CodeGen-NL 2B*,
 ## 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
@@ -35,8 +35,8 @@ This model can be easily loaded using the `AutoModelForCausalLM` functionality:
 
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
-tokenizer = AutoTokenizer.from_pretrained('Salesforce/codegen-2B-multi')
-model = AutoModelForCausalLM.from_pretrained('Salesforce/codegen-2B-multi')
+tokenizer = AutoTokenizer.from_pretrained("Salesforce/codegen-2B-multi")
+model = AutoModelForCausalLM.from_pretrained("Salesforce/codegen-2B-multi")
 
 text = "def hello_world():"
 input_ids = tokenizer(text, return_tensors="pt").input_ids