Distilroberta Base Sentence Transformer

🚀 embedding-data/distilroberta-base-sentence-transformer

This is a sentence-transformers model that maps sentences and paragraphs to a 768-dimensional dense vector space. It can be used for tasks such as clustering or semantic search.

🚀 Quick Start

✨ Features

• Maps sentences and paragraphs to a 768-dimensional dense vector space.
• Suitable for tasks like clustering and semantic search.

📦 Installation

If you want to use this model, you need to install sentence-transformers first:

pip install -U sentence-transformers

💻 Usage Examples

Basic Usage

If you have sentence-transformers installed, you can use the model as follows:

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

model = SentenceTransformer('embedding-data/distilroberta-base-sentence-transformer')
embeddings = model.encode(sentences)
print(embeddings)

Advanced Usage

Without sentence-transformers, you can use the model like this: First, pass your input through the transformer model, then 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('embedding-data/distilroberta-base-sentence-transformer')
model = AutoModel.from_pretrained('embedding-data/distilroberta-base-sentence-transformer')

# 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 following parameters:

DataLoader: torch.utils.data.dataloader.DataLoader of length 7 with parameters:

{'batch_size': 16, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}

Loss: sentence_transformers.losses.TripletLoss.TripletLoss with parameters:

{'distance_metric': 'TripletDistanceMetric.EUCLIDEAN', 'triplet_margin': 5}

Parameters of the fit()-Method:

{
    "epochs": 10,
    "evaluation_steps": 0,
    "evaluator": "NoneType",
    "max_grad_norm": 1,
    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
    "optimizer_params": {
        "lr": 2e-05
    },
    "scheduler": "WarmupLinear",
    "steps_per_epoch": null,
    "warmup_steps": 7,
    "weight_decay": 0.01
}

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: RobertaModel 
  (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})
)

📄 License

The document does not provide license information, so this section is skipped.

🔧 Technical Details

The model is a sentence-transformer that maps text to a 768-dimensional vector space. It uses a RobertaModel for encoding and a mean pooling operation to get sentence embeddings. During training, it uses a TripletLoss with specific distance metric and margin. The training process involves multiple epochs, an AdamW optimizer with a learning rate of 2e-05, and a warmup linear scheduler.

📋 Information Table

Citing & Authors

The document does not provide detailed information on citing and authors, so this section is skipped.