# Load model directly
from transformers import AutoTokenizer, AutoModelForMaskedLM
tokenizer = AutoTokenizer.from_pretrained("DFrolova/MULAN-small")
model = AutoModelForMaskedLM.from_pretrained("DFrolova/MULAN-small")Quick Links
This is a model card for MULAN-small protein language model introduced in the paper MULAN: Multimodal Protein Language Model for Sequence and Structure Encoding. It has 9M parameters.
It can be loaded using the MULAN repository:
from mulan.model import StructEsmForMaskedLM
model = StructEsmForMaskedLM.from_pretrained(
'DFrolova/MULAN-small',
device_map="auto",
)
- Downloads last month
- 10
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="DFrolova/MULAN-small")