all-MiniLM-L6-v2-CosQA

SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2. It maps sentences & paragraphs to a 384-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: sentence-transformers/all-MiniLM-L6-v2 <!-- at revision c9745ed1d9f207416be6d2e6f8de32d1f16199bf -->
• Maximum Sequence Length: 256 tokens
• Output Dimensionality: 384 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': 256, 'do_lower_case': False, 'architecture': 'BertModel'})
  (1): Pooling({'word_embedding_dimension': 384, '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})
  (2): Normalize()
)

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
queries = [
    "check if address is valid python",
]
documents = [
    'def is_valid_ipv6(ip_str):\n    """\n    Check the validity of an IPv6 address\n    """\n    try:\n        socket.inet_pton(socket.AF_INET6, ip_str)\n    except socket.error:\n        return False\n    return True',
    'def longest_run_1d(arr):\n    """Return the length of the longest consecutive run of identical values.\n\n    Parameters\n    ----------\n    arr : bool array\n      Input array\n\n    Returns\n    -------\n    int\n      Length of longest run.\n    """\n    v, rl = rle_1d(arr)[:2]\n    return np.where(v, rl, 0).max()',
    'def dict_to_enum_fn(d: Dict[str, Any], enum_class: Type[Enum]) -> Enum:\n    """\n    Converts an ``dict`` to a ``Enum``.\n    """\n    return enum_class[d[\'name\']]',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 384] [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[ 0.6137, -0.0250, -0.1585]])

<!-- ### 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.* --> <!-- ## 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: 9,020 training samples
• Columns: <code>query</code>, <code>document</code>, and <code>score</code>
• Approximate statistics based on the first 1000 samples:

  	query	document	score
  type	string	string	int
  details	<ul><li>min: 6 tokens</li><li>mean: 9.67 tokens</li><li>max: 21 tokens</li></ul>	<ul><li>min: 40 tokens</li><li>mean: 86.17 tokens</li><li>max: 256 tokens</li></ul>	<ul><li>1: 100.00%</li></ul>

• Samples:

  query	document	score
  <code>1d array in char datatype in python</code>	<code>def _convert_to_array(array_like, dtype):<br> """<br> Convert Matrix attributes which are array-like or buffer to array.<br> """<br> if isinstance(array_like, bytes):<br> return np.frombuffer(array_like, dtype=dtype)<br> return np.asarray(array_like, dtype=dtype)</code>	<code>1</code>
  <code>python condition non none</code>	<code>def _not(condition=None, **kwargs):<br> """<br> Return the opposite of input condition.<br><br> :param condition: condition to process.<br><br> :result: not condition.<br> :rtype: bool<br> """<br><br> result = True<br><br> if condition is not None:<br> result = not run(condition, **kwargs)<br><br> return result</code>	<code>1</code>
  <code>accessing a column from a matrix in python</code>	<code>def get_column(self, X, column):<br> """Return a column of the given matrix.<br><br> Args:<br> X: numpy.ndarray or pandas.DataFrame.<br> column: int or str.<br><br> Returns:<br> np.ndarray: Selected column.<br> """<br> if isinstance(X, pd.DataFrame):<br> return X[column].values<br><br> return X[:, column]</code>	<code>1</code>

• Loss: <code>MultipleNegativesRankingLoss</code> with these parameters:

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

Evaluation Dataset

Unnamed Dataset

• Size: 500 evaluation samples
• Columns: <code>query</code>, <code>document</code>, and <code>score</code>
• Approximate statistics based on the first 500 samples:

  	query	document	score
  type	string	string	int
  details	<ul><li>min: 6 tokens</li><li>mean: 9.71 tokens</li><li>max: 21 tokens</li></ul>	<ul><li>min: 42 tokens</li><li>mean: 87.19 tokens</li><li>max: 256 tokens</li></ul>	<ul><li>1: 100.00%</li></ul>

• Samples:

  query	document	score
  <code>python check if a variable is iterable</code>	<code>def is_iterable_but_not_string(obj):<br> """<br> Determine whether or not obj is iterable but not a string (eg, a list, set, tuple etc).<br> """<br> return hasattr(obj, 'iter') and not isinstance(obj, str) and not isinstance(obj, bytes)</code>	<code>1</code>
  <code>how to prevent a file from modifying python</code>	<code>def make_file_readable (filename):<br> """Make file user readable if it is not a link."""<br> if not os.path.islink(filename):<br> util.set_mode(filename, stat.S_IRUSR)</code>	<code>1</code>
  <code>how to make functions that returns a function python</code>	<code>def apply(filter):<br> """Manufacture decorator that filters return value with given function.<br><br> filter:<br> Callable that takes a single parameter.<br> """<br> def decorator(callable):<br> return lambda *args, **kwargs: filter(callable(*args, **kwargs))<br> return decorator</code>	<code>1</code>

• Loss: <code>MultipleNegativesRankingLoss</code> with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: epoch
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 32
• num_train_epochs: 7
• warmup_ratio: 0.1
• fp16: True

All Hyperparameters

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

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: epoch
• prediction_loss_only: True
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 32
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 1
• eval_accumulation_steps: None
• torch_empty_cache_steps: None
• learning_rate: 5e-05
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1.0
• num_train_epochs: 7
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.1
• warmup_steps: 0
• log_level: passive
• log_level_replica: warning
• log_on_each_node: True
• logging_nan_inf_filter: True
• save_safetensors: True
• save_on_each_node: False
• save_only_model: False
• restore_callback_states_from_checkpoint: False
• no_cuda: False
• use_cpu: False
• use_mps_device: False
• seed: 42
• data_seed: None
• jit_mode_eval: False
• use_ipex: False
• bf16: False
• fp16: True
• fp16_opt_level: O1
• half_precision_backend: auto
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: None
• local_rank: 0
• ddp_backend: None
• tpu_num_cores: None
• tpu_metrics_debug: False
• debug: []
• dataloader_drop_last: False
• dataloader_num_workers: 0
• dataloader_prefetch_factor: None
• past_index: -1
• disable_tqdm: False
• remove_unused_columns: True
• label_names: None
• load_best_model_at_end: False
• ignore_data_skip: False
• fsdp: []
• fsdp_min_num_params: 0
• fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
• fsdp_transformer_layer_cls_to_wrap: None
• accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
• parallelism_config: None
• deepspeed: None
• label_smoothing_factor: 0.0
• optim: adamw_torch_fused
• optim_args: None
• adafactor: False
• group_by_length: False
• length_column_name: length
• ddp_find_unused_parameters: None
• ddp_bucket_cap_mb: None
• ddp_broadcast_buffers: False
• dataloader_pin_memory: True
• dataloader_persistent_workers: False
• skip_memory_metrics: True
• use_legacy_prediction_loop: False
• push_to_hub: False
• resume_from_checkpoint: None
• hub_model_id: None
• hub_strategy: every_save
• hub_private_repo: None
• hub_always_push: False
• hub_revision: None
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• include_for_metrics: []
• eval_do_concat_batches: True
• fp16_backend: auto
• push_to_hub_model_id: None
• push_to_hub_organization: None
• mp_parameters:
• auto_find_batch_size: False
• full_determinism: False
• torchdynamo: None
• ray_scope: last
• ddp_timeout: 1800
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• include_tokens_per_second: False
• include_num_input_tokens_seen: False
• neftune_noise_alpha: None
• optim_target_modules: None
• batch_eval_metrics: False
• eval_on_start: False
• use_liger_kernel: False
• liger_kernel_config: None
• eval_use_gather_object: False
• average_tokens_across_devices: False
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

</details>

Training Logs

Framework Versions

• Python: 3.12.3
• Sentence Transformers: 5.1.1
• Transformers: 4.56.2
• PyTorch: 2.8.0+cu128
• Accelerate: 1.10.1
• Datasets: 4.1.1
• Tokenizers: 0.22.1

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",
}

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}
}

<!-- ## 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.* -->