Instructions to use westlake-repl/SaProt_650M_AF2_inverse_folding with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use westlake-repl/SaProt_650M_AF2_inverse_folding with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="westlake-repl/SaProt_650M_AF2_inverse_folding")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("westlake-repl/SaProt_650M_AF2_inverse_folding") model = AutoModelForMaskedLM.from_pretrained("westlake-repl/SaProt_650M_AF2_inverse_folding") - Notebooks
- Google Colab
- Kaggle
This model is a fine-tuned version of SaProt_650M_AF2. We fine-tuned this model on the CATH dataset for protein inverse folding task. Experimental results show that the fine-tuned version outperforms SaProt_650M_AF2 and performs competitively with ProteinMPNN, while it requires much less inference time.
- Downloads last month
- 14
