bge-small-code-v1

SentenceTransformer based on BAAI/bge-small-en-v1.5

This is a sentence-transformers model finetuned from BAAI/bge-small-en-v1.5. It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for retrieval.

Model Details

Model Description

• Model Type: Sentence Transformer
• Base model: BAAI/bge-small-en-v1.5 <!-- at revision 5c38ec7c405ec4b44b94cc5a9bb96e735b38267a -->
• Maximum Sequence Length: 384 tokens
• Output Dimensionality: 384 dimensions
• Similarity Function: Cosine Similarity
• Supported Modality: Text

<!-- - **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({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'BertModel'})
  (1): Pooling({'embedding_dimension': 384, 'pooling_mode': 'cls', '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 = [
    'For component xyz, returns "xyz[]"',
]
documents = [
    'private static final String getArrayTypeName(String typeName) {\n    final String arrayTypeName = builtInArrayComponentName2ArrayTypeName.get(typeName);\n    return (null == arrayTypeName) ? typeName + ARRAY_TYPE_SUFFIX : arrayTypeName;\n  }',
    'public String toString() {\n\t    \tif(size == 0) {\n\t    \t\treturn "[]";\n\t    \t}else {\n\t    \t\t\n\t    \t\tString result = "[" + elementData[0];\n\t    \t\tfor(int i = 1; i < size; i++) {\n\t    \t\t\tresult += ", " + elementData[i];\n\t    \t\t}\n\t    \t\t\n\t    \t\tresult += "]";\n\t    \t\t\n\t    \t\treturn result;\n\t    \t}\n\t    }',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 384] [2, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[0.4896, 0.4966]])

<!-- ### 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: cornstack_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: 200,000 training samples
• Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
• Approximate statistics based on the first 100 samples:

  	anchor	positive	negative
  type	string	string	string
  modality	text	text	text
  details	<ul><li>min: 6 tokens</li><li>mean: 19.83 tokens</li><li>max: 105 tokens</li></ul>	<ul><li>min: 21 tokens</li><li>mean: 139.33 tokens</li><li>max: 384 tokens</li></ul>	<ul><li>min: 11 tokens</li><li>mean: 100.52 tokens</li><li>max: 384 tokens</li></ul>

• Samples:

  anchor	positive	negative
  <code>Fades all outputs to the given color and waits for it to complete.</code>	<code>def FadeOutputs(box, color, steps=50):<br> for output in box:<br> output.Fade(color=color, steps=steps)<br> time.sleep(steps / (float(box.frequency) / len(box)))</code>	<code>def _colour_loop(self, colours, seconds=None, milliseconds=None, fade=True):<br> colours = self.convert_to_colour_list(colours) #Forces a list of colours into an actual python list<br> if len(colours)<2:<br> colours.append("#000000") #Blink between black and the specified colour if only one provided<br> <br> #Start with the first colour immediately:<br> if fade:<br> self.fade(colours[0])<br> else:<br> self.set(colours[0])<br> step_time = self.clean_time_in_milliseconds(seconds, milliseconds, default_seconds=1, minimum_milliseconds=50)<br> <br> #Do the loop<br> i = 1 #We're moving to the second colour now<br> total_colours = len(colours)<br> while not self._sequence_stop_signal:<br> #Resolve our colour<br> next_colour = colours[i]<br> i = (i+1) % total_colours #ensures we are never asking for more colours than provided<br> if fade: #Fading is a blocking process, thus we let the fade l...</code>
  <code>Sets the additional element count if buffer resize is required, defaults to initialElementCount of factory method.</code>	<code>public void setResizeElementCount(int v) { vboSet.setResizeElementCount(v); }</code>	<code>public int getResizeElementCount() { return vboSet.getResizeElementCount(); }</code>
  <code>delete a specific incident</code>	<code>def delete_specific_incident(self, incident_id):<br> self.cursor.execute("""DELETE FROM incidents WHERE incident_id ='%s' AND status='draft'<br> """ %(incident_id))<br> self.commiting()<br> return incident_id</code>	<code>def delete(openstack_resource):<br> openstack_resource.delete()</code>

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

  {
      "loss": "MultipleNegativesRankingLoss",
      "matryoshka_dims": [
          384,
          256,
          128,
          64
      ],
      "matryoshka_weights": [
          1.0,
          1.0,
          1.0,
          1.0
      ],
      "n_dims_per_step": -1
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 32
• gradient_accumulation_steps: 2
• learning_rate: 2e-05
• num_train_epochs: 1
• warmup_ratio: 0.05
• fp16: True
• batch_sampler: no_duplicates

All Hyperparameters

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

• overwrite_output_dir: False
• do_predict: False
• prediction_loss_only: True
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 8
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 2
• eval_accumulation_steps: None
• torch_empty_cache_steps: None
• learning_rate: 2e-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: 1
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: None
• warmup_ratio: 0.05
• 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
• 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
• project: huggingface
• trackio_space_id: trackio
• 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: no
• 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: True
• prompts: None
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

</details>

Training Logs

Training Time

• Training: 28.8 minutes
• Evaluation: 1.7 seconds
• Total: 28.9 minutes

Framework Versions

• Python: 3.13.7
• Sentence Transformers: 5.6.0
• Transformers: 4.57.6
• PyTorch: 2.12.1+cu126
• Accelerate: 1.13.0
• Datasets: 4.8.5
• 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",
}

MatryoshkaLoss

@misc{kusupati2024matryoshka,
    title={Matryoshka Representation Learning},
    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
    year={2024},
    eprint={2205.13147},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

MultipleNegativesRankingLoss

@misc{oord2019representationlearningcontrastivepredictive,
      title={Representation Learning with Contrastive Predictive Coding},
      author={Aaron van den Oord and Yazhe Li and Oriol Vinyals},
      year={2019},
      eprint={1807.03748},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/1807.03748},
}

<!-- ## 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.* -->