Fill-Mask
Transformers
PyTorch
Safetensors
ConvNet
dna
language-model
variant-effect-prediction
biology
genomics
Instructions to use songlab/gpn-brassicales with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use songlab/gpn-brassicales with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="songlab/gpn-brassicales")# Load model directly from transformers import AutoModelForMaskedLM model = AutoModelForMaskedLM.from_pretrained("songlab/gpn-brassicales", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -12,6 +12,16 @@ datasets:
|
|
| 12 |
# GPN trained on *Arabidopsis thaliana* and 7 other Brassicales
|
| 13 |
See https://github.com/songlab-cal/gpn for more details.
|
| 14 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
## Some hparams:
|
| 16 |
* repeat_weight: 0.1
|
| 17 |
* lr: 120k at 1e-3 + 30k cosine decay
|
|
|
|
| 12 |
# GPN trained on *Arabidopsis thaliana* and 7 other Brassicales
|
| 13 |
See https://github.com/songlab-cal/gpn for more details.
|
| 14 |
|
| 15 |
+
Basic usage:
|
| 16 |
+
```python
|
| 17 |
+
import gpn.model
|
| 18 |
+
from transformers import AutoModel, AutoModelForMaskedLM
|
| 19 |
+
|
| 20 |
+
model = AutoModel.from_pretrained("songlab/gpn-brassicales")
|
| 21 |
+
# or
|
| 22 |
+
model = AutoModelForMaskedLM.from_pretrained("songlab/gpn-brassicales")
|
| 23 |
+
```
|
| 24 |
+
|
| 25 |
## Some hparams:
|
| 26 |
* repeat_weight: 0.1
|
| 27 |
* lr: 120k at 1e-3 + 30k cosine decay
|