Nutanix / jina-embeddings-v2-base-code-mbpp

SentenceTransformer based on jinaai/jina-embeddings-v2-base-code

This is a sentence-transformers model finetuned from jinaai/jina-embeddings-v2-base-code . It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

• Model Type: Sentence Transformer
• Base model: jinaai/jina-embeddings-v2-base-code
• Maximum Sequence Length: 8192 tokens
• Output Dimensionality: 768 tokens
• Similarity Function: Cosine Similarity

Model Sources

• Documentation: Sentence Transformers Documentation
• Repository: Sentence Transformers on GitHub
• Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 768, '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})
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("Nutanix/jina-embeddings-v2-base-code-mbpp")
# Run inference
sentences = [
    'Write a function to find sum and average of first n natural numbers.',
    'def sum_average(number):\r\n total = 0\r\n for value in range(1, number + 1):\r\n    total = total + value\r\n average = total / number\r\n return (total,average)',
    'def long_words(n, str):\r\n    word_len = []\r\n    txt = str.split(" ")\r\n    for x in txt:\r\n        if len(x) > n:\r\n            word_len.append(x)\r\n    return word_len\t',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Triplet

• Dataset: sts-dev
• Evaluated with TripletEvaluator

Training Details

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size : 16
• per_device_eval_batch_size : 16
• num_train_epochs : 1
• warmup_ratio : 0.1
• fp16 : True
• batch_sampler : no_duplicates

All Hyperparameters

Training Logs

Framework Versions

• Python: 3.10.14
• Sentence Transformers: 3.0.1
• Transformers: 4.40.0
• PyTorch: 2.3.0+cu121
• Accelerate: 0.33.0
• Datasets: 2.20.0
• Tokenizers: 0.19.1

Citation

BibTeX

Sentence Transformers

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

TripletLoss

@misc{hermans2017defense,
    title={In Defense of the Triplet Loss for Person Re-Identification}, 
    author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
    year={2017},
    eprint={1703.07737},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}