gabrielbianchin commited on
Commit
23138d6
·
1 Parent(s): 30b3093

update readme

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -17,7 +17,7 @@ library_name: peft
17
 
18
  # SeqScreen - ESM2 LoRA Adapter
19
 
20
- This repository contains the LoRA adapter weights for the protein encoder used in SeqScreen. SeqScreen is a sequence-based virtual screening method built on a dual-encoder contrastive architecture. The adapter fine-tunes [ESM2 T36 (3B)](https://huggingface.co/facebook/esm2_t36_3B_UR50D) on protein-molecule interaction task.
21
 
22
  The projection layers are available separately at [SaeedLab/SeqScreen-Finetuning](https://huggingface.co/SaeedLab/SeqScreen-Finetuning), which also contains the full model description, architecture diagram, and usage examples.
23
 
@@ -43,7 +43,6 @@ This adapter corresponds to the **SeqScreen-Finetuning** configuration, in which
43
  | LoRA alpha | 32 |
44
  | LoRA dropout | 0.05 |
45
  | Task type | `FEATURE_EXTRACTION` |
46
- | Training data | BindingDB |
47
 
48
  ## Usage
49
 
 
17
 
18
  # SeqScreen - ESM2 LoRA Adapter
19
 
20
+ This repository contains the LoRA adapter weights for the protein encoder used in SeqScreen for LIT-PCBA dataset. SeqScreen is a sequence-based virtual screening method built on a dual-encoder contrastive architecture. The adapter fine-tunes [ESM2 T36](https://huggingface.co/facebook/esm2_t36_3B_UR50D) on protein-molecule interaction task.
21
 
22
  The projection layers are available separately at [SaeedLab/SeqScreen-Finetuning](https://huggingface.co/SaeedLab/SeqScreen-Finetuning), which also contains the full model description, architecture diagram, and usage examples.
23
 
 
43
  | LoRA alpha | 32 |
44
  | LoRA dropout | 0.05 |
45
  | Task type | `FEATURE_EXTRACTION` |
 
46
 
47
  ## Usage
48