Instructions to use PoetschLab/GROVER with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use PoetschLab/GROVER with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="PoetschLab/GROVER")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("PoetschLab/GROVER") model = AutoModelForMaskedLM.from_pretrained("PoetschLab/GROVER") - Inference
- Notebooks
- Google Colab
- Kaggle
Soybean how
I would like to know if GROVER cold be trained to understend the DNA of Soybean seeds or wiil be necessary to start a new model.
For some questions that are on conserved areas of the genome, a model that is trained on a different species can have decent performance. We are currently looking into the limitations of cross-species applications. Generally I would recommend to have a species specific model for questions on biology that is happening outside of genes, because there the genomes can be very different and as a result the models learn different genome biology.
And sorry for answering so late, I did not see the comment. For any further comments, please also write me an email (arpoetsch@gmail.com), so I know it is there.