Feature Extraction
PEFT
Safetensors
Transformers
proteins
molecules
bioinformatics
drug-discovery
lora
Instructions to use SaeedLab/SeqScreen-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use SaeedLab/SeqScreen-lora with PEFT:
Task type is invalid.
- Transformers
How to use SaeedLab/SeqScreen-lora with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="SaeedLab/SeqScreen-lora")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("SaeedLab/SeqScreen-lora", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
23138d6
1
Parent(s): 30b3093
update readme
Browse files
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
|
| 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 |
|