README.md

metadata

pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - feature-extraction
  - sentence-similarity
  - transformers

kuelumbus/polyBERT

This is polyBERT: A chemical language model to enable fully machine-driven ultrafast polymer informatics. polyBERT maps PSMILES strings to 600 dimensional dense fingerprints. The fingerprints numerically represent polymer chemical structures.

Usage (Sentence-Transformers)

Using this model becomes easy when you have sentence-transformers installed:

pip install -U sentence-transformers

Then you can use the model like this:

from sentence_transformers import SentenceTransformer
psmiles_strings = ["[*]CC[*]", "[*]COC[*]"]

model = SentenceTransformer('kuelumbus/polyBERT')
embeddings = model.encode(psmiles_strings)
print(embeddings)

Usage (HuggingFace Transformers)

Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.

from transformers import AutoTokenizer, AutoModel
import torch


#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)


# Sentences we want sentence embeddings for
psmiles_strings = ["[*]CC[*]", "[*]COC[*]"]

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('kuelumbus/polyBERT')
model = AutoModel.from_pretrained('kuelumbus/polyBERT')

# Tokenize sentences
encoded_input = tokenizer(psmiles_strings, padding=True, truncation=True, return_tensors='pt')

# Compute token embeddings
with torch.no_grad():
    model_output = model(**encoded_input)

# Perform pooling. In this case, mean pooling.
fingerprints = mean_pooling(model_output, encoded_input['attention_mask'])

print("Fingerprints:")
print(fingerprints)

Evaluation Results

See https://github.com/Ramprasad-Group/polyBERT

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: DebertaV2Model 
  (1): Pooling({'word_embedding_dimension': 600, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)

Citing & Authors

t.b.d.