shubharuidas/codebert-embed-base-dense-retriever

codeBert Base

This is a sentence-transformers model finetuned from microsoft/codebert-base. 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: microsoft/codebert-base <!-- at revision 3b0952feddeffad0063f274080e3c23d75e7eb39 -->
• —Maximum Sequence Length: 512 tokens
• —Output Dimensionality: 768 dimensions
• —Similarity Function: Cosine Similarity <!-- - Training Dataset: Unknown -->
• —Language: en
• —License: apache-2.0

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': 'RobertaModel'})
  (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("killdollar/codebert-embed-base-dense-retriever")
# Run inference
sentences = [
    'How does __init__ work in Python?',
    'def __init__(\n        self,\n        encoding_name: str = "gpt2",\n        model_name: str | None = None,\n        allowed_special: Literal["all"] | AbstractSet[str] = set(),\n        disallowed_special: Literal["all"] | Collection[str] = "all",\n        **kwargs: Any,\n    ) -> None:\n        """Create a new `TextSplitter`.\n\n        Args:\n            encoding_name: The name of the tiktoken encoding to use.\n            model_name: The name of the model to use. If provided, this will\n                override the `encoding_name`.\n            allowed_special: Special tokens that are allowed during encoding.\n            disallowed_special: Special tokens that are disallowed during encoding.\n\n        Raises:\n            ImportError: If the tiktoken package is not installed.\n        """\n        super().__init__(**kwargs)\n        if not _HAS_TIKTOKEN:\n            msg = (\n                "Could not import tiktoken python package. "\n                "This is needed in order to for TokenTextSplitter. "\n                "Please install it with `pip install tiktoken`."\n            )\n            raise ImportError(msg)\n\n        if model_name is not None:\n            enc = tiktoken.encoding_for_model(model_name)\n        else:\n            enc = tiktoken.get_encoding(encoding_name)\n        self._tokenizer = enc\n        self._allowed_special = allowed_special\n        self._disallowed_special = disallowed_special',
    'def test_fixed_message_response_when_docs_found() -> None:\n    fixed_resp = "I don\'t know"\n    answer = "I know the answer!"\n    llm = FakeListLLM(responses=[answer])\n    retriever = SequentialRetriever(\n        sequential_responses=[[Document(page_content=answer)]],\n    )\n    memory = ConversationBufferMemory(\n        k=1,\n        output_key="answer",\n        memory_key="chat_history",\n        return_messages=True,\n    )\n    qa_chain = ConversationalRetrievalChain.from_llm(\n        llm=llm,\n        memory=memory,\n        retriever=retriever,\n        return_source_documents=True,\n        rephrase_question=False,\n        response_if_no_docs_found=fixed_resp,\n        verbose=True,\n    )\n    got = qa_chain("What is the answer?")\n    assert got["chat_history"][1].content == answer\n    assert got["answer"] == answer',
]
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, 0.7336, 0.0979],
#         [0.7336, 1.0000, 0.1742],
#         [0.0979, 0.1742, 1.0000]])

<!--

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: dim_768
• —Evaluated with <code>InformationRetrievalEvaluator</code> with these parameters:

  {
      "truncate_dim": 768
  }

Information Retrieval

• —Dataset: dim_512
• —Evaluated with <code>InformationRetrievalEvaluator</code> with these parameters:

  {
      "truncate_dim": 512
  }

Information Retrieval

• —Dataset: dim_256
• —Evaluated with <code>InformationRetrievalEvaluator</code> with these parameters:

  {
      "truncate_dim": 256
  }

Information Retrieval

• —Dataset: dim_128
• —Evaluated with <code>InformationRetrievalEvaluator</code> with these parameters:

  {
      "truncate_dim": 128
  }

Information Retrieval

• —Dataset: dim_64
• —Evaluated with <code>InformationRetrievalEvaluator</code> with these parameters:

  {
      "truncate_dim": 64
  }

<!--

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: 900 training samples
• —Columns: <code>anchor</code> and <code>positive</code>
• —Approximate statistics based on the first 900 samples: | | anchor | positive | |:--------|:----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------| | type | string | string | | details | <ul><li>min: 6 tokens</li><li>mean: 13.15 tokens</li><li>max: 42 tokens</li></ul> | <ul><li>min: 25 tokens</li><li>mean: 239.87 tokens</li><li>max: 512 tokens</li></ul> |
• —Samples: | anchor | positive | |:-----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | <code>Explain the testqdrantsimilaritysearchwithrelevancescores logic</code> | <code>def testqdrantsimilaritysearchwithrelevancescores(<br> batchsize: int,<br> contentpayloadkey: str,<br> metadatapayloadkey: str,<br> vectorname: str \| None,<br>) -> None:<br> """Test end to end construction and search."""<br> texts = ["foo", "bar", "baz"]<br> docsearch = Qdrant.fromtexts(<br> texts,<br> ConsistentFakeEmbeddings(),<br> location=":memory:",<br> contentpayloadkey=contentpayloadkey,<br> metadatapayloadkey=metadatapayloadkey,<br> batchsize=batchsize,<br> vectorname=vectorname,<br> )<br> output = docsearch.similaritysearchwithrelevancescores("foo", k=3)<br><br> assert all(<br> (score <= 1 or np.isclose(score, 1)) and score >= 0 for , score in output<br> )</code> | | <code>How to implement LangChainPendingDeprecationWarning?</code> | <code>class LangChainPendingDeprecationWarning(PendingDeprecationWarning):<br> """A class for issuing deprecation warnings for LangChain users."""</code> | | <code>Example usage of randomname</code> | <code>def randomname() -> str:<br> """Generate a random name."""<br> adjective = random.choice(adjectives) # noqa: S311<br> noun = random.choice(nouns) # noqa: S311<br> number = random.randint(1, 100) # noqa: S311<br> return f"{adjective}-{noun}-{number}"</code> |
• —Loss: <code>MatryoshkaLoss</code> with these parameters:

  {
      "loss": "MultipleNegativesRankingLoss",
      "matryoshka_dims": [
          768,
          512,
          256,
          128,
          64
      ],
      "matryoshka_weights": [
          1,
          1,
          1,
          1,
          1
      ],
      "n_dims_per_step": -1
  }

Training Hyperparameters

Non-Default Hyperparameters

• —eval_strategy: epoch
• —per_device_train_batch_size: 4
• —per_device_eval_batch_size: 4
• —gradient_accumulation_steps: 16
• —learning_rate: 2e-05
• —num_train_epochs: 4
• —lr_scheduler_type: cosine
• —warmup_ratio: 0.1
• —fp16: True
• —load_best_model_at_end: True
• —optim: adamw_torch
• —batch_sampler: no_duplicates

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: 4
• —per_device_eval_batch_size: 4
• —per_gpu_train_batch_size: None
• —per_gpu_eval_batch_size: None
• —gradient_accumulation_steps: 16
• —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: 4
• —max_steps: -1
• —lr_scheduler_type: cosine
• —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
• —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: True
• —ignore_data_skip: False
• —fsdp: []
• —fsdp_min_num_params: 0
• —fsdp_config: {'minnumparams': 0, 'xla': False, 'xlafsdpv2': False, 'xlafsdpgrad_ckpt': False}
• —fsdp_transformer_layer_cls_to_wrap: None
• —accelerator_config: {'splitbatches': False, 'dispatchbatches': None, 'evenbatches': True, 'useseedablesampler': True, 'nonblocking': False, 'gradientaccumulationkwargs': None}
• —parallelism_config: None
• —deepspeed: None
• —label_smoothing_factor: 0.0
• —optim: adamw_torch
• —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

• —The bold row denotes the saved checkpoint.

Framework Versions

• —Python: 3.12.12
• —Sentence Transformers: 5.2.0
• —Transformers: 4.57.3
• —PyTorch: 2.9.0+cu126
• —Accelerate: 1.12.0
• —Datasets: 4.0.0
• —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{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. -->