NeuML/bert-hash-femto-embeddings

BERT Hash Femto Embeddings

This is a BERT Hash Femto model fined-tuned using sentence-transformers. It maps sentences & paragraphs to a 50-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

This model is an alternative to MUVERA fixed-dimensional encoding with ColBERT models. MUVERA encoding enables encoding the multi-vector outputs of ColBERT into single dense vector outputs. While this is a great step, the main issue with MUVERA is that it tends to need wide vectors to be effective (5K - 10K dimensional vectors). bert-hash-femto-embeddings outputs 50-dimensional vectors.

The training dataset is a subset of this embedding training collection. The training workflow was a two step distillation process as follows.

• —Distill embeddings from the larger bert-hash-pico-embeddings model using this model distillation script from Sentence Transformers.
• —Build a distilled dataset of teacher scores using the mixedbread-ai/mxbai-rerank-xsmall-v1 cross-encoder for a random sample of the training dataset mentioned above.
• —Further fine-tune the model on the distilled dataset using KLDivLoss.

Usage (txtai)

This model can be used to build embeddings databases with txtai for semantic search and/or as a knowledge source for retrieval augmented generation (RAG).

import txtai

embeddings = txtai.Embeddings(
  path="neuml/bert-hash-femto-embeddings",
  content=True,
  vectors={"trust_remote_code": True}
)
embeddings.index(documents())

# Run a query
embeddings.search("query to run")

Usage (Sentence-Transformers)

Alternatively, the model can be loaded with sentence-transformers.

from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]

model = SentenceTransformer("neuml/bert-hash-femto-embeddings", trust_remote_code=True)
embeddings = model.encode(sentences)
print(embeddings)

Usage (Hugging Face Transformers)

The model can also be used directly with Transformers.

from transformers import AutoTokenizer, AutoModel
import torch

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

# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained("neuml/bert-hash-femto-embeddings", trust_remote_code=True)
model = AutoModel.from_pretrained("neuml/bert-hash-femto-embeddings", trust_remote_code=True)

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

# Compute token embeddings
with torch.no_grad():
    output = model(**inputs)

# Perform pooling. In this case, mean pooling.
embeddings = meanpooling(output, inputs['attention_mask'])

print("Sentence embeddings:")
print(embeddings)

Evaluation

The following table shows a subset of BEIR scored with the txtai benchmarks script.

This evaluation is compared against the ColBERT MUVERA series of models.

Scores reported are ndcg@10 and grouped into the following three categories.

BERT Hash Embeddings vs MUVERA

BERT Hash Embeddings vs MUVERA with maxsim re-ranking of the top 100 results per MUVERA paper

Compare to other models

In analyzing the results, bert-hash-femto-embeddings scores lower than MUVERA with colbert-muvera-femto. Comparing the standard MUVERA output of 10240 vs 50 dimensions, 10K standard F32 vectors needs 400 MB of storage vs 2 MB

Keeping in mind this is only a 243K parameter model, the performance is still impressive at only ~1% of the number of parameters of popular small embeddings models.

While this isn't a state of the art model, it's an extremely competitive method for building vectors on edge and low resource devices.

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': 'BertHashModel'})
  (1): Pooling({'word_embedding_dimension': 50, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)

More Information

Read more about the model in this article and this paper.