SFR-Embedding-2_R

SFR-Embedding by Salesforce Research.

The model is for research purposes only.

More technical details will be updated later. Meanwhile, please refer to our previous work SFR-Embedding for details.

Ethical Considerations

This release is for research purposes only in support of an academic paper. Our models, datasets, and code are not specifically designed or evaluated for all downstream purposes. We strongly recommend users evaluate and address potential concerns related to accuracy, safety, and fairness before deploying this model. We encourage users to consider the common limitations of AI, comply with applicable laws, and leverage best practices when selecting use cases, particularly for high-risk scenarios where errors or misuse could significantly impact people’s lives, rights, or safety. For further guidance on use cases, refer to our AUP and AI AUP.

SFR-Embedding Team (∗indicates equal contributors, † indicates co-leaders).

• Rui Meng*
• Ye Liu*
• Tong Niu
• Shafiq Rayhan Joty
• Caiming Xiong †
• Yingbo Zhou †
• Semih Yavuz †

Citation

@misc{SFR-embedding-2,
  title={SFR-Embedding-2: Advanced Text Embedding with Multi-stage Training},
  author={Rui Meng*, Ye Liu*, Shafiq Rayhan Joty, Caiming Xiong, Yingbo Zhou, Semih Yavuz},
  year={2024},
  url={https://huggingface.co/Salesforce/SFR-Embedding-2_R}
}

How to run

Transformers

The models can be used as follows:

import torch
import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

def last_token_pool(last_hidden_states: Tensor,
                 attention_mask: Tensor) -> Tensor:
    left_padding = (attention_mask[:, -1].sum() == attention_mask.shape[0])
    if left_padding:
        return last_hidden_states[:, -1]
    else:
        sequence_lengths = attention_mask.sum(dim=1) - 1
        batch_size = last_hidden_states.shape[0]
        return last_hidden_states[torch.arange(batch_size, device=last_hidden_states.device), sequence_lengths]

def get_detailed_instruct(task_description: str, query: str) -> str:
    return f'Instruct: {task_description}\nQuery: {query}'

# Each query must come with a one-sentence instruction that describes the task
task = 'Given a web search query, retrieve relevant passages that answer the query'
queries = [
    get_detailed_instruct(task, 'How to bake a chocolate cake'),
    get_detailed_instruct(task, 'Symptoms of the flu')
]
# No need to add instruction for retrieval documents
passages = [
    "To bake a delicious chocolate cake, you'll need the following ingredients: all-purpose flour, sugar, cocoa powder, baking powder, baking soda, salt, eggs, milk, vegetable oil, and vanilla extract. Start by preheating your oven to 350°F (175°C). In a mixing bowl, combine the dry ingredients (flour, sugar, cocoa powder, baking powder, baking soda, and salt). In a separate bowl, whisk together the wet ingredients (eggs, milk, vegetable oil, and vanilla extract). Gradually add the wet mixture to the dry ingredients, stirring until well combined. Pour the batter into a greased cake pan and bake for 30-35 minutes. Let it cool before frosting with your favorite chocolate frosting. Enjoy your homemade chocolate cake!",
    "The flu, or influenza, is an illness caused by influenza viruses. Common symptoms of the flu include a high fever, chills, cough, sore throat, runny or stuffy nose, body aches, headache, fatigue, and sometimes nausea and vomiting. These symptoms can come on suddenly and are usually more severe than the common cold. It's important to get plenty of rest, stay hydrated, and consult a healthcare professional if you suspect you have the flu. In some cases, antiviral medications can help alleviate symptoms and reduce the duration of the illness."
]

# load model and tokenizer
tokenizer = AutoTokenizer.from_pretrained('Salesforce/SFR-Embedding-2_R')
model = AutoModel.from_pretrained('Salesforce/SFR-Embedding-2_R')

# get the embeddings
max_length = 4096
input_texts = queries + passages
batch_dict = tokenizer(input_texts, max_length=max_length, padding=True, truncation=True, return_tensors="pt")
outputs = model(**batch_dict)
embeddings = last_token_pool(outputs.last_hidden_state, batch_dict['attention_mask'])

# normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:2] @ embeddings[2:].T) * 100
print(scores.tolist())
# [[40.132083892822266, 25.032529830932617], [15.006855010986328, 39.93733215332031]]

Sentence Transformers

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("Salesforce/SFR-Embedding-2_R")

def get_detailed_instruct(task_description: str, query: str) -> str:
    return f'Instruct: {task_description}\nQuery: {query}'

# Each query must come with a one-sentence instruction that describes the task
task = 'Given a web search query, retrieve relevant passages that answer the query'
queries = [
    get_detailed_instruct(task, 'How to bake a chocolate cake'),
    get_detailed_instruct(task, 'Symptoms of the flu')
]
# No need to add instruction for retrieval documents
passages = [
    "To bake a delicious chocolate cake, you'll need the following ingredients: all-purpose flour, sugar, cocoa powder, baking powder, baking soda, salt, eggs, milk, vegetable oil, and vanilla extract. Start by preheating your oven to 350°F (175°C). In a mixing bowl, combine the dry ingredients (flour, sugar, cocoa powder, baking powder, baking soda, and salt). In a separate bowl, whisk together the wet ingredients (eggs, milk, vegetable oil, and vanilla extract). Gradually add the wet mixture to the dry ingredients, stirring until well combined