benjamintli/modernbert-cosqa

SentenceTransformer based on benjamintli/modernbert-cosqa

This is a sentence-transformers model finetuned from benjamintli/modernbert-cosqa. 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: benjamintli/modernbert-cosqa <!-- at revision c85b25617894d583fafad7eb7421b7dc0aab0ad9 -->
• —Maximum Sequence Length: 512 tokens
• —Output Dimensionality: 768 dimensions
• —Similarity Function: Cosine Similarity <!-- - Training Dataset: Unknown --> <!-- - Language: Unknown --> <!-- - License: Unknown -->

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': 512, 'do_lower_case': False, 'architecture': 'OptimizedModule'})
  (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("modernbert-cosqa")
# Run inference
queries = [
    "first duplicate element in list in python",
]
documents = [
    'def purge_duplicates(list_in):\n    """Remove duplicates from list while preserving order.\n\n    Parameters\n    ----------\n    list_in: Iterable\n\n    Returns\n    -------\n    list\n        List of first occurences in order\n    """\n    _list = []\n    for item in list_in:\n        if item not in _list:\n            _list.append(item)\n    return _list',
    'def getRect(self):\n\t\t"""\n\t\tReturns the window bounds as a tuple of (x,y,w,h)\n\t\t"""\n\t\treturn (self.x, self.y, self.w, self.h)',
    'def python_mime(fn):\n    """\n    Decorator, which adds correct MIME type for python source to the decorated\n    bottle API function.\n    """\n    @wraps(fn)\n    def python_mime_decorator(*args, **kwargs):\n        response.content_type = "text/x-python"\n\n        return fn(*args, **kwargs)\n\n    return python_mime_decorator',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 768] [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[ 0.5986, -0.0006, -0.0122]])

<!--

Direct Usage (Transformers)

<details><summary>Click to see the direct usage in Transformers</summary>

</details> -->

<!--

Downstream Usage (Sentence Transformers)

You can finetune this model on your own dataset.

<details><summary>Click to expand</summary>

</details> -->

<!--

Out-of-Scope Use

List how the model may foreseeably be misused and address what users ought not to do with the model. -->

Evaluation

Metrics

Information Retrieval

• —Dataset: eval
• —Evaluated with <code>InformationRetrievalEvaluator</code>

<!--

Bias, Risks and Limitations

What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model. -->

<!--

Recommendations

What are recommendations with respect to the foreseeable issues? For example, filtering explicit content. -->

Training Details

Training Dataset

Unnamed Dataset

• —Size: 8,118 training samples
• —Columns: <code>query</code> and <code>positive</code>
• —Approximate statistics based on the first 1000 samples: | | query | positive | |:--------|:--------------------------------------------------------------------------------|:------------------------------------------------------------------------------------| | type | string | string | | details | <ul><li>min: 6 tokens</li><li>mean: 9.3 tokens</li><li>max: 23 tokens</li></ul> | <ul><li>min: 35 tokens</li><li>mean: 85.05 tokens</li><li>max: 512 tokens</li></ul> |
• —Samples: | query | positive | |:--------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | <code>python code for opening geojson file</code> | <code>def loadfilepath(self, filepath, **kwargs):<br> """This loads a geojson file into a geojson python<br> dictionary using the json module.<br> <br> Note: to load with a different text encoding use the encoding argument.<br> """<br> with open(filepath, "r") as f:<br> data = json.load(f, **kwargs)<br> return data</code> | | <code>python 3 none compare with int</code> | <code>def isnatural(x):<br> """A non-negative integer."""<br> try:<br> isinteger = int(x) == x<br> except (TypeError, ValueError):<br> return False<br> return isinteger and x >= 0</code> | | <code>design db memory cache python</code> | <code>def refresh(self, document):<br> """ Load a new copy of a document from the database. does not<br> replace the old one """<br> try:<br> oldcachesize = self.cachesize<br> self.cachesize = 0<br> obj = self.query(type(document)).filterby(mongoid=document.mongoid).one()<br> finally:<br> self.cachesize = oldcachesize<br> self.cache_write(obj)<br> return obj</code> |
• —Loss: <code>CachedMultipleNegativesRankingLoss</code> with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "mini_batch_size": 64,
      "gather_across_devices": false,
      "directions": [
          "query_to_doc"
      ],
      "partition_mode": "joint",
      "hardness_mode": null,
      "hardness_strength": 0.0
  }

Evaluation Dataset

Unnamed Dataset

• —Size: 902 evaluation samples
• —Columns: <code>query</code> and <code>positive</code>
• —Approximate statistics based on the first 902 samples: | | query | positive | |:--------|:---------------------------------------------------------------------------------|:------------------------------------------------------------------------------------| | type | string | string | | details | <ul><li>min: 6 tokens</li><li>mean: 9.24 tokens</li><li>max: 22 tokens</li></ul> | <ul><li>min: 38 tokens</li><li>mean: 86.55 tokens</li><li>max: 332 tokens</li></ul> |
• —Samples: | query | positive | |:--------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | <code>how to remove masked items in python array</code> | <code>def ma(self):<br> """Represent data as a masked array.<br><br> The array is returned with column-first indexing, i.e. for a data file with<br> columns X Y1 Y2 Y3 ... the array a will be a[0] = X, a[1] = Y1, ... .<br><br> inf and nan are filtered via :func:numpy.isfinite.<br> """<br> a = self.array<br> return numpy.ma.MaskedArray(a, mask=numpy.logicalnot(numpy.isfinite(a)))</code> | | <code>python deepcopy basic type</code> | <code>def deepcopy(self, memo):<br> """Improve deepcopy speed."""<br> return type(self)(value=self.value, enumref=self.enumref)</code> | | <code>python number of non nan rows in a row</code> | <code>def countrowswith_nans(X):<br> """Count the number of rows in 2D arrays that contain any nan values."""<br> if X.ndim == 2:<br> return np.where(np.isnan(X).sum(axis=1) != 0, 1, 0).sum()</code> |
• —Loss: <code>CachedMultipleNegativesRankingLoss</code> with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "mini_batch_size": 64,
      "gather_across_devices": false,
      "directions": [
          "query_to_doc"
      ],
      "partition_mode": "joint",
      "hardness_mode": null,
      "hardness_strength": 0.0
  }

Training Hyperparameters

Non-Default Hyperparameters

• —per_device_train_batch_size: 1024
• —num_train_epochs: 10
• —learning_rate: 2e-06
• —warmup_steps: 0.1
• —bf16: True
• —eval_strategy: epoch
• —per_device_eval_batch_size: 1024
• —push_to_hub: True
• —hub_model_id: modernbert-cosqa
• —load_best_model_at_end: True
• —dataloader_num_workers: 4
• —batch_sampler: no_duplicates

All Hyperparameters

<details><summary>Click to expand</summary>

• —per_device_train_batch_size: 1024
• —num_train_epochs: 10
• —max_steps: -1
• —learning_rate: 2e-06
• —lr_scheduler_type: linear
• —lr_scheduler_kwargs: None
• —warmup_steps: 0.1
• —optim: adamwtorchfused
• —optim_args: None
• —weight_decay: 0.0
• —adam_beta1: 0.9
• —adam_beta2: 0.999
• —adam_epsilon: 1e-08
• —optim_target_modules: None
• —gradient_accumulation_steps: 1
• —average_tokens_across_devices: True
• —max_grad_norm: 1.0
• —label_smoothing_factor: 0.0
• —bf16: True
• —fp16: False
• —bf16_full_eval: False
• —fp16_full_eval: False
• —tf32: None
• —gradient_checkpointing: False
• —gradient_checkpointing_kwargs: None
• —torch_compile: False
• —torch_compile_backend: None
• —torch_compile_mode: None
• —use_liger_kernel: False
• —liger_kernel_config: None
• —use_cache: False
• —neftune_noise_alpha: None
• —torch_empty_cache_steps: None
• —auto_find_batch_size: False
• —log_on_each_node: True
• —logging_nan_inf_filter: True
• —include_num_input_tokens_seen: no
• —log_level: passive
• —log_level_replica: warning
• —disable_tqdm: False
• —project: huggingface
• —trackio_space_id: trackio
• —eval_strategy: epoch
• —per_device_eval_batch_size: 1024
• —prediction_loss_only: True
• —eval_on_start: False
• —eval_do_concat_batches: True
• —eval_use_gather_object: False
• —eval_accumulation_steps: None
• —include_for_metrics: []
• —batch_eval_metrics: False
• —save_only_model: False
• —save_on_each_node: False
• —enable_jit_checkpoint: False
• —push_to_hub: True
• —hub_private_repo: None
• —hub_model_id: modernbert-cosqa
• —hub_strategy: every_save
• —hub_always_push: False
• —hub_revision: None
• —load_best_model_at_end: True
• —ignore_data_skip: False
• —restore_callback_states_from_checkpoint: False
• —full_determinism: False
• —seed: 42
• —data_seed: None
• —use_cpu: False
• —accelerator_config: {'splitbatches': False, 'dispatchbatches': None, 'evenbatches': True, 'useseedablesampler': True, 'nonblocking': False, 'gradientaccumulationkwargs': None}
• —parallelism_config: None
• —dataloader_drop_last: False
• —dataloader_num_workers: 4
• —dataloader_pin_memory: True
• —dataloader_persistent_workers: False
• —dataloader_prefetch_factor: None
• —remove_unused_columns: True
• —label_names: None
• —train_sampling_strategy: random
• —length_column_name: length
• —ddp_find_unused_parameters: None
• —ddp_bucket_cap_mb: None
• —ddp_broadcast_buffers: False
• —ddp_backend: None
• —ddp_timeout: 1800
• —fsdp: []
• —fsdp_config: {'minnumparams': 0, 'xla': False, 'xlafsdpv2': False, 'xlafsdpgrad_ckpt': False}
• —deepspeed: None
• —debug: []
• —skip_memory_metrics: True
• —do_predict: False
• —resume_from_checkpoint: None
• —warmup_ratio: None
• —local_rank: -1
• —prompts: None
• —batch_sampler: no_duplicates
• —multi_dataset_batch_sampler: proportional
• —router_mapping: {}
• —learning_rate_mapping: {}

</details>

Training Logs

• —The bold row denotes the saved checkpoint.

Framework Versions

• —Python: 3.12.12
• —Sentence Transformers: 5.3.0
• —Transformers: 5.3.0
• —PyTorch: 2.10.0+cu128
• —Accelerate: 1.13.0
• —Datasets: 4.8.2
• —Tokenizers: 0.22.2

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",
}

CachedMultipleNegativesRankingLoss

@misc{gao2021scaling,
    title={Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup},
    author={Luyu Gao and Yunyi Zhang and Jiawei Han and Jamie Callan},
    year={2021},
    eprint={2101.06983},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

<!--

Glossary

Clearly define terms in order to be accessible across audiences. -->

<!--

Model Card Authors

Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction. -->

<!--

Model Card Contact

Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors. -->