Sentence It5 Base

🚀 sentence-IT5-base

This is a sentence-transformers model that maps sentences and paragraphs to a 512-dimensional dense vector space. It can be used for tasks such as clustering or semantic search. It is based on the T5 (IT5) base model and is trained on various datasets.

🚀 Quick Start

✨ Features

• Maps sentences and paragraphs to a 512-dimensional dense vector space.
• Can be used for clustering or semantic search.
• Based on the T5 (IT5) base model.
• Trained on multiple datasets including question/context pairs, tags/news-article pairs, headline/text pairs, and stsb.

📦 Installation

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

pip install -U sentence-transformers

💻 Usage Examples

Basic Usage

If you have sentence-transformers installed, you can use the model like this:

from sentence_transformers import SentenceTransformer
sentences = ["Questo è un esempio di frase", "Questo è un ulteriore esempio"]

model = SentenceTransformer('efederici/sentence-IT5-base')
embeddings = model.encode(sentences)
print(embeddings)

Advanced Usage

Without sentence-transformers, you can use the model by passing your input through the transformer model and then applying 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 = ["Questo è un esempio di frase", "Questo è un ulteriore esempio"]

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('efederici/sentence-IT5-base')
model = AutoModel.from_pretrained('efederici/sentence-IT5-base')

# 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)

🔧 Technical Details

The full model architecture is as follows:

SentenceTransformer(
  (0): Transformer({'max_seq_length': None, 'do_lower_case': False}) with Transformer model: T5EncoderModel 
  (1): Pooling({'word_embedding_dimension': 512, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)