Update README.md

README.md

@@ -6,11 +6,12 @@ tags: []
 
 ## A faster half-precision version of ESM2-650 with FlashAttention2 and longer context
 
-FastESM is a Huggingface compatible plug in version of ESM2-650M rewritten with a newer PyTorch Attention implementation.
+FastESM is a Huggingface compatible plug in version of ESM2-650M rewritten with a newer PyTorch attention implementation.
 
 To enhance the weights with longer context and better fp16 support, we trained ESM2-650 50000 additional steps with a traditional MLM objective (20% masking) in fp16 mixed precision on [OMGprot50](tattabio/OMG_prot50) up to sequence length of **2048**.
 
-Outputting attentions and predicting contacts are not possible from SDPA. Various other optimizations also make the base implementation slightly different than the one in transformers.
+Outputting attention maps (or the contact predictino head) is not natively possible with SDPA. You can still pass ```output_attentions``` to have attention calculated manually and returned.
+Various other optimizations also make the base implementation slightly different than the one in transformers.
 
 ## Use with 🤗 transformers
 ```python