Update README.md

README.md

@@ -14,7 +14,7 @@ Disclaimer: The team releasing Perceiver IO did not write a model card for this
 
 ## Model description
 
-Perceiver IO is a transformer encoder model that can be applied on any modality (text, images, audio, video, ...). The core idea is to employ the self-attention mechanism on a set of not-too large latent vectors, and only use the inputs to perform cross-attention with the latents. This allows for the time and memory requirements of the self-attention mechanism to not depend on the size of the inputs. 
+Perceiver IO is a transformer encoder model that can be applied on any modality (text, images, audio, video, ...). The core idea is to employ the self-attention mechanism on a not-too-large set of latent vectors (e.g. 256 or 512), and only use the inputs to perform cross-attention with the latents. This allows for the time and memory requirements of the self-attention mechanism to not depend on the size of the inputs. 
 
 To decode, the authors employ so-called decoder queries, which allow to flexibly decode the final hidden states of the latents to produce outputs of arbitrary size and semantics. For masked language modeling, the output is a tensor containing the prediction scores of the language modeling head, of shape (batch_size, seq_length, vocab_size).
 
@@ -25,7 +25,7 @@ To decode, the authors employ so-called decoder queries, which allow to flexibly
 As the time and memory requirements of the self-attention mechanism don't depend on the size of the inputs, the Perceiver IO authors train the model directly on raw UTF-8 bytes, rather than on subwords as is done in models like BERT, RoBERTa and GPT-2. This has many benefits: one doesn't need to train a tokenizer before training the model, one doesn't need to maintain a (fixed) vocabulary file, and this also doesn't hurt model performance as shown by [Bostrom et al., 2020](https://arxiv.org/abs/2004.03720).
 
 By pre-training the model, it learns an inner representation of language that can then be used to extract features useful for downstream tasks: if you have a dataset of labeled sentences for instance, you can train a standard
-classifier using the features produced by the BERT model as inputs. 
+classifier using the features produced by the Perceiver model as inputs. 
 
 ## Intended uses & limitations