SFR Embedding Code 2B R

🚀 Salesforce/SFR-Embedding-Code-2B_R

SFR-Embedding by Salesforce Research.

Salesforce/SFR-Embedding-Code is a generalist embedding model family designed for multilingual and multi-task code and text retrieval. It outperforms various open - source code embedding models in multiple code retrieval tasks.

Check out our paper for more details!

We also offer a 400M - size model Salesforce/SFR-Embedding-Code-400_R

🚀 Quick Start

Ethical Considerations

This release is solely for research purposes to support an academic paper. Our models, datasets, and code are not specifically designed or evaluated for all downstream applications. We strongly advise users to assess and address potential issues 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 follow best practices when choosing use - cases, especially in high - risk scenarios where errors or misuse could significantly affect people's lives, rights, or safety. For more guidance on use - cases, refer to our AUP and AI AUP.

License Statement

Users are required to assess their own obligations or responsibilities under the corresponding licenses or terms and conditions of the original datasets and data. This release is for research purposes only to support an academic paper.

This released model is a fine - tuned version of Gemma. Gemma is provided under and subject to the Gemma Terms of Use found at ai.google.dev/gemma/terms. Additionally, the use of this model is restricted as set forth in the Gemma Prohibited Use Policy at ai.google.dev/gemma/prohibited_use_policy ("Prohibited Use Policy"), which is hereby incorporated by reference into this Agreement.

Performance on CoIR Benchmark

Team Members

SFR-Embedding Team († indicates co - leaders)

• Ye Liu
• Rui Meng
• Shafiq Rayhan Joty
• Silvio Savarese
• Caiming Xiong †
• Yingbo Zhou †
• Semih Yavuz †

💻 Usage Examples

Basic Usage

Transformers

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

# Each query needs to be accompanied by an corresponding instruction describing the task.
query_instruction_example = "Given Code or Text, retrieval relevant content"
queries = [
    "how to implement quick sort in Python?"
]

# No instruction needed for retrieval passages
passages = [
    "def quick_sort(arr):\n    if len(arr) <= 1:\n        return arr\n    pivot = arr[len(arr) // 2]\n    left = [x for x in arr if x < pivot]\n    middle = [x for x in arr if x == pivot]\n    right = [x for x in arr if x > pivot]\n    return quick_sort(left) + middle + quick_sort(right)",
    "def bubble_sort(arr):\n    n = len(arr)\n    for i in range(n):\n        for j in range(0, n-i-1):\n            if arr[j] > arr[j+1]:\n                arr[j], arr[j+1] = arr[j+1], arr[j]\n    return arr"
]

# load model with tokenizer
model = AutoModel.from_pretrained('Salesforce/SFR-Embedding-Code-2B_R', trust_remote_code=True)

# get the embeddings
max_length = 32768
query_embeddings = model.encode_queries(queries, instruction=query_instruction_example, max_length=max_length)
passage_embeddings = model.encode_corpus(passages, max_length=max_length)

# normalize embeddings
query_embeddings = F.normalize(query_embeddings, p=2, dim=1)
passage_embeddings = F.normalize(passage_embeddings, p=2, dim=1)

scores = (query_embeddings @ passage_embeddings.T) * 100
print(scores.tolist())
# [[69.26929473876953, 58.41606903076172]]

Sentence Transformers

from sentence_transformers import SentenceTransformer

# Each query needs to be accompanied by an corresponding instruction describing the task.
query_instruction_example = "Instruct: Given Code or Text, retrieval relevant content\nQuery: "
queries = ["how to implement quick sort in Python?"]

# No instruction needed for retrieval passages
passages = [
    "def quick_sort(arr):\n    if len(arr) <= 1:\n        return arr\n    pivot = arr[len(arr) // 2]\n    left = [x for x in arr if x < pivot]\n    middle = [x for x in arr if x == pivot]\n    right = [x for x in arr if x > pivot]\n    return quick_sort(left) + middle + quick_sort(right)",
    "def bubble_sort(arr):\n    n = len(arr)\n    for i in range(n):\n        for j in range(0, n-i-1):\n            if arr[j] > arr[j+1]:\n                arr[j], arr[j+1] = arr[j+1], arr[j]\n    return arr"
]

# Load the Sentence Transformer model, including pooling
model = SentenceTransformer('Salesforce/SFR-Embedding-Code-2B_R', trust_remote_code=True)

# Compute the embeddings for both queries and passages. Use 'prompt' for queries only
query_embeddings = model.encode(queries, prompt=query_instruction_example)
passage_embeddings = model.encode(passages)

# Compute the similarities between the queries and passages
similarities = model.similarity(query_embeddings, passage_embeddings)
print(similarities)
# tensor([[0.6927, 0.5842]])

📄 License

This model is released under the cc - by - nc - 4.0 license.

📚 Documentation

Citation

@article{liu2024codexembed,
  title={CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrieval},
  author={Liu, Ye and Meng, Rui and Jot, Shafiq and Savarese, Silvio and Xiong, Caiming and Zhou, Yingbo and Yavuz, Semih},
  journal={arXiv preprint arXiv:2411.12644},
  year={2024}
}