TatonkaHF's picture
Update README.md
c309cf8 verified
---
library_name: sentence-transformers
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
language:
- ru
- en
---
# bge-m3-unsupervised model for english and russian
This is a tokenizer shrinked version of [BAAI/bge-m3-unsupervised](https://huggingface.co/BAAI/bge-m3-unsupervised).
The current model has only English and Russian tokens left in the vocabulary.
Thus, the vocabulary is 21% of the original, and number of parameters in the whole model is 63.3% of the original, without any loss in the quality of English and Russian embeddings.
Notebook with code is available [here](https://github.com/BlessedTatonka/pet_projects/tree/main/huggingface/bge-m3-shrinking).
<!--- Describe your model here -->
## 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 = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('TatonkaHF/bge-m3-unsupervised_en_ru')
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 = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('TatonkaHF/bge-m3-unsupervised_en_ru')
model = AutoModel.from_pretrained('TatonkaHF/bge-m3-unsupervised_en_ru')
# 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)
```
## Specs
Other bge-m3 models are also shrinked.
| Model name |
|---------------------------|
| [bge-m3-retromae_en_ru](https://huggingface.co/TatonkaHF/bge-m3-retromae_en_ru) |
| [bge-m3-unsupervised_en_ru](https://huggingface.co/TatonkaHF/bge-m3-unsupervised_en_ru) |
| [bge-m3_en_ru](https://huggingface.co/TatonkaHF/bge-m3_en_ru) |
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
(1): Pooling({'word_embedding_dimension': 1024, '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})
)
```
## Reference:
Jianlv Chen, Shitao Xiao, Peitian Zhang, Kun Luo, Defu Lian, Zheng Liu. [BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://arxiv.org/abs/2402.03216).
Inspired by [LaBSE-en-ru](https://huggingface.co/cointegrated/LaBSE-en-ru) and [https://discuss.huggingface.co/t/tokenizer-shrinking-recipes/8564/1](https://discuss.huggingface.co/t/tokenizer-shrinking-recipes/8564/1).
License: [mit](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/mit.md)
<!--- Describe where people can find more information -->