đ E5-base-unsupervised
This model is similar to e5-base but without supervised fine-tuning. It is based on the research paper Text Embeddings by Weakly-Supervised Contrastive Pre-training by Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei (arXiv 2022). This model has 12 layers and the embedding size is 768.
đ Quick Start
This section provides a quick overview of the model and how to get started with it.
⨠Features
- Similar to e5-base but without supervised fine-tuning.
- 12 layers with an embedding size of 768.
- Suitable for various text embedding tasks.
đĻ Installation
No specific installation steps are provided in the original README. However, to use the model, you need to install the necessary libraries:
pip install transformers sentence-transformers~=2.2.2 torch
đģ Usage Examples
Basic Usage
Below is an example to encode queries and passages from the MS-MARCO passage ranking dataset.
import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel
def average_pool(last_hidden_states: Tensor,
attention_mask: Tensor) -> Tensor:
last_hidden = last_hidden_states.masked_fill(~attention_mask[..., None].bool(), 0.0)
return last_hidden.sum(dim=1) / attention_mask.sum(dim=1)[..., None]
input_texts = ['query: how much protein should a female eat',
'query: summit define',
"passage: As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 is 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or training for a marathon. Check out the chart below to see how much protein you should be eating each day.",
"passage: Definition of summit for English Language Learners. : 1 the highest point of a mountain : the top of a mountain. : 2 the highest level. : 3 a meeting or series of meetings between the leaders of two or more governments."]
tokenizer = AutoTokenizer.from_pretrained('intfloat/e5-base-unsupervised')
model = AutoModel.from_pretrained('intfloat/e5-base-unsupervised')
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')
outputs = model(**batch_dict)
embeddings = average_pool(outputs.last_hidden_state, batch_dict['attention_mask'])
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:2] @ embeddings[2:].T) * 100
print(scores.tolist())
Advanced Usage
Below is an example for usage with sentence_transformers.
from sentence_transformers import SentenceTransformer
model = SentenceTransformer('intfloat/e5-base-unsupervised')
input_texts = [
'query: how much protein should a female eat',
'query: summit define',
"passage: As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 is 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or training for a marathon. Check out the chart below to see how much protein you should be eating each day.",
"passage: Definition of summit for English Language Learners. : 1 the highest point of a mountain : the top of a mountain. : 2 the highest level. : 3 a meeting or series of meetings between the leaders of two or more governments."
]
embeddings = model.encode(input_texts, normalize_embeddings=True)
đ Documentation
Training Details
Please refer to our paper at https://arxiv.org/pdf/2212.03533.pdf.
Benchmark Evaluation
Check out unilm/e5 to reproduce evaluation results on the BEIR and MTEB benchmark.
FAQ
1. Do I need to add the prefix "query: " and "passage: " to input texts?
Yes, this is how the model is trained, otherwise you will see a performance degradation.
Here are some rules of thumb:
-
Use "query: " and "passage: " correspondingly for asymmetric tasks such as passage retrieval in open QA, ad-hoc information retrieval.
-
Use "query: " prefix for symmetric tasks such as semantic similarity, paraphrase retrieval.
-
Use "query: " prefix if you want to use embeddings as features, such as linear probing classification, clustering
2. Why are my reproduced results slightly different from reported in the model card?
Different versions of transformers
and pytorch
could cause negligible but non-zero performance differences.
đ§ Technical Details
The model has 12 layers and an embedding size of 768. It is based on weakly-supervised contrastive pre-training.
đ License
This project is licensed under the MIT License.
đ Citation
If you find our paper or models helpful, please consider cite as follows:
@article{wang2022text,
title={Text Embeddings by Weakly-Supervised Contrastive Pre-training},
author={Wang, Liang and Yang, Nan and Huang, Xiaolong and Jiao, Binxing and Yang, Linjun and Jiang, Daxin and Majumder, Rangan and Wei, Furu},
journal={arXiv preprint arXiv:2212.03533},
year={2022}
}
â ī¸ Limitations
This model only works for English texts. Long texts will be truncated to at most 512 tokens.
đĨ Contributors
michaelfeil