Update README.md

README.md

@@ -38,7 +38,11 @@ A sequence of word embeddings is therefore processed sequentially by each transf
 
 ## Details model architecture
 
-The *conventional* T5 architectures are summarized in the following table:
+This model checkpoint - **t5-efficient-xl** - is of model type **XL** with **no** variations.
+It has **2852** million parameters and thus requires **11406** MB of memory in full precision (*fp32*) 
+ or  **5703** MB of memory in half precision (*fp16* or *bf16*).
+
+The *conventional* T5 architectures are summarized as follows:
 
 | Model | nl (el/dl) | ff | dm | kv | nh | #Params|
 | ----| ---- | ---- | ---- | ---- | ---- | ----|
@@ -50,7 +54,7 @@ The *conventional* T5 architectures are summarized in the following table:
 | **XL** | **24/24** | **16384** | **1024** | **128** | **32** | **3B**|
 | XXL | 24/24 | 65536 | 1024 | 128 | 128 | 11B|
 
-with the following definitions:
+, whereas the following abbreviations are used:
 
 | Abbreviation | Definition |
 | ----| ---- |
@@ -66,10 +70,6 @@ with the following definitions:
 
 If a model checkpoint has no specific, *el* or *dl* than both the number of encoder- and decoder layers correspond no *nl*.
 
-This model checkpoint - **t5-efficient-xl** - is of model type **XL** with **no** variations.
-It has **2852** million parameters and thus requires **11406** MB of memory in full precision (*fp32*) 
- or  **5703** MB of memory in half precision (*fp16* or *bf16*).
-
 ## Pre-Training
 
 The checkpoint was pretrained on the [Colossal, Cleaned version of Common Crawl (C4)](https://huggingface.co/datasets/c4) for 524288 steps using