Instructions to use seyonec/ChemBERTa-zinc-base-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use seyonec/ChemBERTa-zinc-base-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="seyonec/ChemBERTa-zinc-base-v1")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("seyonec/ChemBERTa-zinc-base-v1") model = AutoModelForMaskedLM.from_pretrained("seyonec/ChemBERTa-zinc-base-v1") - Inference
- Notebooks
- Google Colab
- Kaggle
Just note that this model is not the preferred model according to the author
#1
by Jung - opened
FYI, look at this issue:
https://github.com/seyonechithrananda/bert-loves-chemistry/issues/7
The author recommended to use models hosted by DeepChem instead, e.g.
https://huggingface.co/DeepChem/ChemBERTa-10M-MTR/discussions?status=all