ibm-research / materials.selfies-ted

huggingface.co
Total runs: 916
24-hour runs: 0
7-day runs: -35
30-day runs: -1.6K
Model's Last Updated: October 14 2025
feature-extraction

Introduction of materials.selfies-ted

Model Details of materials.selfies-ted

selfies-ted

selfies-ted is an transformer based encoder decoder model for molecular representations using SELFIES.

selfies-ted

Usage
Import
from transformers import AutoTokenizer, AutoModel
import selfies as sf
import torch
Load the model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("ibm/materials.selfies-ted")
model = AutoModel.from_pretrained("ibm/materials.selfies-ted")
Encode SMILES strings to selfies
smiles = "c1ccccc1"
selfies = sf.encoder(smiles)
selfies = selfies.replace("][", "] [")
Get embedding
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

Runs of ibm-research materials.selfies-ted on huggingface.co

916
Total runs
0
24-hour runs
0
3-day runs
-35
7-day runs
-1.6K
30-day runs

More Information About materials.selfies-ted huggingface.co Model

More materials.selfies-ted license Visit here:

https://choosealicense.com/licenses/apache-2.0

materials.selfies-ted huggingface.co

materials.selfies-ted huggingface.co is an AI model on huggingface.co that provides materials.selfies-ted's model effect (), which can be used instantly with this ibm-research materials.selfies-ted model. huggingface.co supports a free trial of the materials.selfies-ted model, and also provides paid use of the materials.selfies-ted. Support call materials.selfies-ted model through api, including Node.js, Python, http.

materials.selfies-ted huggingface.co Url

https://huggingface.co/ibm-research/materials.selfies-ted

ibm-research materials.selfies-ted online free

materials.selfies-ted huggingface.co is an online trial and call api platform, which integrates materials.selfies-ted's modeling effects, including api services, and provides a free online trial of materials.selfies-ted, you can try materials.selfies-ted online for free by clicking the link below.

ibm-research materials.selfies-ted online free url in huggingface.co:

https://huggingface.co/ibm-research/materials.selfies-ted

materials.selfies-ted install

materials.selfies-ted is an open source model from GitHub that offers a free installation service, and any user can find materials.selfies-ted on GitHub to install. At the same time, huggingface.co provides the effect of materials.selfies-ted install, users can directly use materials.selfies-ted installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

materials.selfies-ted install url in huggingface.co:

https://huggingface.co/ibm-research/materials.selfies-ted

Url of materials.selfies-ted

materials.selfies-ted huggingface.co Url

Provider of materials.selfies-ted huggingface.co

ibm-research
ORGANIZATIONS

Other API from ibm-research

huggingface.co

Total runs: 33.7K
Run Growth: -38.5K
Growth Rate: -114.23%
Updated:March 20 2026
huggingface.co

Total runs: 24.1K
Run Growth: -25.7K
Growth Rate: -106.27%
Updated:September 16 2024
huggingface.co

Total runs: 5.9K
Run Growth: 296
Growth Rate: 5.05%
Updated:March 24 2026
huggingface.co

Total runs: 4.1K
Run Growth: -7.8K
Growth Rate: -187.57%
Updated:January 18 2025
huggingface.co

Total runs: 1.5K
Run Growth: -832
Growth Rate: -54.88%
Updated:October 12 2022