ibm-research/materials.selfies-ted

from transformers import AutoTokenizer, AutoModel
import selfies as sf
import torch

tokenizer = AutoTokenizer.from_pretrained("ibm/materials.selfies-ted")
model = AutoModel.from_pretrained("ibm/materials.selfies-ted")

smiles = "c1ccccc1"
selfies = sf.encoder(smiles)
selfies = selfies.replace("][", "] [")

token = tokenizer(selfies, return_tensors='pt', max_length=128, truncation=True, padding='max_length')
input_ids = token['input_ids']
attention_mask = token['attention_mask']
outputs = model.encoder(input_ids=input_ids, attention_mask=attention_mask)
model_output = outputs.last_hidden_state

input_mask_expanded = attention_mask.unsqueeze(-1).expand(model_output.size()).float()
sum_embeddings = torch.sum(model_output * input_mask_expanded, 1)
sum_mask = torch.clamp(input_mask_expanded.sum(1), min=1e-9)
model_output = sum_embeddings / sum_mask