Shuu12121 / CodeSearch-ModernBERT-Owl-4.1-CosQA

SentenceTransformer based on Shuu12121/CodeModernBERT-Owl-4.1

This is a sentence-transformers model finetuned from Shuu12121/CodeModernBERT-Owl-4.1 . 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: Shuu12121/CodeModernBERT-Owl-4.1
• Maximum Sequence Length: 1024 tokens
• Output Dimensionality: 768 dimensions
• 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': 1024, 'do_lower_case': False, 'architecture': 'ModernBertModel'})
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, '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("sentence_transformers_model_id")
# Run inference
sentences = [
    'how to add a suffix to a file in python',
    'def add_suffix(fullname, suffix):\n    """ Add suffix to a full file name"""\n    name, ext = os.path.splitext(fullname)\n    return name + \'_\' + suffix + ext',
    'def __next__(self, reward, ask_id, lbl):\n        """For Python3 compatibility of generator."""\n        return self.next(reward, ask_id, lbl)',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.8348, 0.0257],
#         [0.8348, 1.0000, 0.0038],
#         [0.0257, 0.0038, 1.0000]])

Training Details

Training Dataset

Unnamed Dataset

• Size: 4,400 training samples
• Columns: sentence_0 , sentence_1 , and label
• Approximate statistics based on the first 1000 samples:

  	sentence_0	sentence_1	label
  type	string	string	float
  details	min: 6 tokens mean: 8.98 tokens max: 21 tokens	min: 31 tokens mean: 75.95 tokens max: 536 tokens	min: 1.0 mean: 1.0 max: 1.0

• Samples:

  sentence_0	sentence_1	label
  subprocess stdin from python thread	def correspond(text): """Communicate with the child process without closing stdin.""" subproc.stdin.write(text) subproc.stdin.flush() return drain()	1.0
  how to run a python compiled file	def get_code(module): """ Compile and return a Module's code object. """ fp = open(module.path) try: return compile(fp.read(), str(module.name), 'exec') finally: fp.close()	1.0
  get last modified file with python	def get_last_modified_timestamp(self): """ Looks at the files in a git root directory and grabs the last modified timestamp """ cmd = "find . -print0	xargs -0 stat -f '%T@ %p'

• Loss: MultipleNegativesRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim"
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size : 200
• per_device_eval_batch_size : 200
• fp16 : True
• multi_dataset_batch_sampler : round_robin

All Hyperparameters

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 5.0.0
• Transformers: 4.53.1
• PyTorch: 2.7.0+cu128
• Accelerate: 1.7.0
• Datasets: 3.6.0
• Tokenizers: 0.21.2

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",
}

MultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply},
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}