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).

python

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.

python

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.

python

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

Model	Parameters	NFCorpus	SciDocs	SciFact	Average
BERT Hash Femto Embeddings	0.2M	0.1402	0.0443	0.2830	0.1558
ColBERT MUVERA Femto	0.2M	0.1851	0.0411	0.3518	0.1927

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

Model	Parameters	NFCorpus	SciDocs	SciFact	Average
BERT Hash Femto Embeddings	0.2M	0.2242	0.0801	0.4719	0.2587
ColBERT MUVERA Femto	0.2M	0.2316	0.0858	0.4641	0.2605

Compare to other models

Model	Parameters	NFCorpus	SciDocs	SciFact	Average
ColBERT MUVERA Femto (full multi-vector maxsim)	0.2M	0.2513	0.0870	0.4710	0.2698
all-MiniLM-L6-v2	22.7M	0.3089	0.2164	0.6527	0.3927
mxbai-embed-xsmall-v1	24.1M	0.3186	0.2155	0.6598	0.3980

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.

NeuML/bert-hash-femto-embeddings

BERT Hash Femto Embeddings

Usage (txtai)

Usage (Sentence-Transformers)

Usage (Hugging Face Transformers)

Evaluation

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

Full Model Architecture

More Information

NeuML/
bert-hash-femto-embeddings