80 lines
3.0 KiB
Markdown
80 lines
3.0 KiB
Markdown
|
---
|
||
|
|
pipeline_tag: sentence-similarity
|
||
|
|
language:
|
||
|
|
- it
|
||
|
|
tags:
|
||
|
|
- sentence-transformers
|
||
|
|
- feature-extraction
|
||
|
|
- sentence-similarity
|
||
|
|
- transformers
|
||
|
|
---
|
||
|
|
|
||
|
|
# sentence-IT5-base
|
||
|
|
|
||
|
|
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 512 dimensional dense vector space and can be used for tasks like clustering or semantic search. It is a T5 ([IT5](https://huggingface.co/gsarti/it5-base)) base model. It is trained on a dataset made from question/context pairs ([squad-it](https://github.com/crux82/squad-it)), tags/news-article pairs, headline/text pairs ([change-it](https://huggingface.co/datasets/gsarti/change_it)) and on [stsb](https://huggingface.co/datasets/stsb_multi_mt/viewer/it/train).
|
||
|
|
|
||
|
|
## Usage (Sentence-Transformers)
|
||
|
|
|
||
|
|
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
|
||
|
|
|
||
|
|
```
|
||
|
|
pip install -U sentence-transformers
|
||
|
|
```
|
||
|
|
|
||
|
|
Then you can use the model like this:
|
||
|
|
|
||
|
|
```python
|
||
|
|
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)
|
||
|
|
```
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
## Usage (HuggingFace Transformers)
|
||
|
|
Without [sentence-transformers](https://www.SBERT.net), 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.
|
||
|
|
|
||
|
|
```python
|
||
|
|
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)
|
||
|
|
```
|
||
|
|
|
||
|
|
## Full Model Architecture
|
||
|
|
```
|
||
|
|
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})
|
||
|
|
)
|
||
|
|
```
|