lhallee commited on
Commit
01410cc
·
verified ·
1 Parent(s): 429a160

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -8,7 +8,7 @@ tags: []
8
 
9
  FastESM is a Huggingface compatible plug in version of ESM2-650M rewritten with a newer PyTorch attention implementation.
10
 
11
- 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**.
12
 
13
  Outputting attention maps (or the contact prediction head) is not natively possible with SDPA. You can still pass ```output_attentions``` to have attention calculated manually and returned.
14
  Various other optimizations also make the base implementation slightly different than the one in transformers.
 
8
 
9
  FastESM is a Huggingface compatible plug in version of ESM2-650M rewritten with a newer PyTorch attention implementation.
10
 
11
+ 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](https://huggingface.co/datasets/tattabio/OMG_prot50) up to sequence length of **2048**.
12
 
13
  Outputting attention maps (or the contact prediction head) is not natively possible with SDPA. You can still pass ```output_attentions``` to have attention calculated manually and returned.
14
  Various other optimizations also make the base implementation slightly different than the one in transformers.