Dense Encoder Msmarco Distilbert Word2vec256k

🚀 dense_encoder-msmarco-distilbert-word2vec256k

This model is designed for sentence similarity tasks, leveraging a pre - trained architecture with a 256k sized vocabulary initialized by word2vec to provide high - quality sentence embeddings.

🚀 Quick Start

This model is based on msmarco-word2vec256000-distilbert-base-uncased with a 256k sized vocabulary initialized with word2vec. It has been trained on MS MARCO using MarginMSELoss. See the train_script.py in this repository.

Performance

• MS MARCO dev: - (MRR@10)
• TREC - DL 2019: 65.53 (nDCG@10)
• TREC - DL 2020: 67.42 (nDCG@10)
• Avg. on 4 BEIR datasets: 38.97

The word embedding matrix has been frozen while training.

✨ Features

• Based on a pre - trained model with a 256k word2vec - initialized vocabulary.
• Trained on MS MARCO using MarginMSELoss.
• Frozen word embedding matrix during training.

📦 Installation

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

pip install -U sentence-transformers

💻 Usage Examples

Basic Usage (Sentence - Transformers)

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

model = SentenceTransformer('{MODEL_NAME}')
embeddings = model.encode(sentences)
print(embeddings)

Advanced 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
sentences = ['This is an example sentence', 'Each sentence is converted']

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
model = AutoModel.from_pretrained('{MODEL_NAME}')

# Tokenize sentences
encoded_input = tokenizer(sentences, 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.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])

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

📚 Documentation

Evaluation Results

For an automated evaluation of this model, see the Sentence Embeddings Benchmark: https://seb.sbert.net

Training

The model was trained with the parameters:

DataLoader: torch.utils.data.dataloader.DataLoader of length 7858 with parameters:

{'batch_size': 64, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}

Loss: sentence_transformers.losses.MarginMSELoss.MarginMSELoss

Parameters of the fit() - Method:

{
    "epochs": 30,
    "evaluation_steps": 0,
    "evaluator": "NoneType",
    "max_grad_norm": 1,
    "optimizer_class": "<class 'transformers.optimization.AdamW'>",
    "optimizer_params": {
        "lr": 2e-05
    },
    "scheduler": "WarmupLinear",
    "steps_per_epoch": null,
    "warmup_steps": 1000,
    "weight_decay": 0.01
}

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 250, 'do_lower_case': False}) with Transformer model: DistilBertModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)

Citing & Authors