Hugging Face's logo

Buckets:
neuroarte12
/
codebert-embed-base-dense-retriever-bucket

Files
xet
neuroarte12/codebert-embed-base-dense-retriever-bucket / README.md
neuroarte12's picture
neuroarte12
preview code
|
download
raw
41 kB
---
language:
- en
license: apache-2.0
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- dense
- generated_from_trainer
- dataset_size:900
- loss:MatryoshkaLoss
- loss:MultipleNegativesRankingLoss
base_model: microsoft/codebert-base
widget:
- source_sentence: Best practices for _invocation_params
 sentences:
 - "def after_model(self, state: StateT, runtime: Runtime[ContextT]) -> dict[str,\
 \ Any] | None:\n \"\"\"Logic to run after the model is called.\n\n \
 \ Args:\n state: The current agent state.\n runtime:\
 \ The runtime context.\n\n Returns:\n Agent state updates to\
 \ apply after model call.\n \"\"\""
 - "def _get_trace_callbacks(\n project_name: str | None = None,\n example_id:\
 \ str | UUID | None = None,\n callback_manager: CallbackManager | AsyncCallbackManager\
 \ | None = None,\n) -> Callbacks:\n if _tracing_v2_is_enabled():\n project_name_\
 \ = project_name or _get_tracer_project()\n tracer = tracing_v2_callback_var.get()\
 \ or LangChainTracer(\n project_name=project_name_,\n example_id=example_id,\n\
 \ )\n if callback_manager is None:\n cb = cast(\"Callbacks\"\
 , [tracer])\n else:\n if not any(\n isinstance(handler,\
 \ LangChainTracer)\n for handler in callback_manager.handlers\n\
 \ ):\n callback_manager.add_handler(tracer)\n \
 \ # If it already has a LangChainTracer, we don't need to add another\
 \ one.\n # this would likely mess up the trace hierarchy.\n \
 \ cb = callback_manager\n else:\n cb = None\n return cb"
 - "def _invocation_params(self) -> dict[str, Any]:\n params: dict = {\"model\"\
 : self.model, **self.model_kwargs}\n if self.dimensions is not None:\n\
 \ params[\"dimensions\"] = self.dimensions\n return params"
- source_sentence: How does _approximate_token_counter work in Python?
 sentences:
 - "def _approximate_token_counter(messages: Sequence[BaseMessage]) -> int:\n \
 \ \"\"\"Wrapper for `count_tokens_approximately` that matches expected signature.\"\
 \"\"\n return count_tokens_approximately(messages)"
 - "def remove_request_headers(request: Any) -> Any:\n for k in request.headers:\n\
 \ request.headers[k] = \"**REDACTED**\"\n return request"
 - "def get_format_instructions(self) -> str:\n \"\"\"Returns formatting instructions\
 \ for the given output parser.\"\"\"\n return self.format_instructions"
- source_sentence: How to implement _create_thread_and_run?
 sentences:
 - "async def on_retriever_end(\n self, documents: Sequence[Document], **kwargs:\
 \ Any\n ) -> None:\n \"\"\"Run when the retriever ends running.\n\n\
 \ Args:\n documents: The retrieved documents.\n **kwargs:\
 \ Additional keyword arguments.\n\n \"\"\"\n if not self.handlers:\n\
 \ return\n await ahandle_event(\n self.handlers,\n\
 \ \"on_retriever_end\",\n \"ignore_retriever\",\n \
 \ documents,\n run_id=self.run_id,\n parent_run_id=self.parent_run_id,\n\
 \ tags=self.tags,\n **kwargs,\n )"
 - "def _create_thread_and_run(self, input_dict: dict, thread: dict) -> Any:\n \
 \ params = {\n k: v\n for k, v in input_dict.items()\n\
 \ if k\n in (\n \"instructions\",\n \
 \ \"model\",\n \"tools\",\n \"parallel_tool_calls\"\
 ,\n \"top_p\",\n \"temperature\",\n \
 \ \"max_completion_tokens\",\n \"max_prompt_tokens\",\n \
 \ \"run_metadata\",\n )\n }\n return self.client.beta.threads.create_and_run(\n\
 \ assistant_id=self.assistant_id,\n thread=thread,\n \
 \ **params,\n )"
 - "def test_pandas_output_parser_col_no_array() -> None:\n with pytest.raises(OutputParserException):\n\
 \ parser.parse(\"column:num_legs\")"
- source_sentence: Explain the get_token_ids logic
 sentences:
 - "def _runnable(inputs: dict[str, Any]) -> str:\n if inputs[\"text\"] == \"\
 foo\":\n return \"first\"\n if \"exception\" not in inputs:\n \
 \ msg = \"missing exception\"\n raise ValueError(msg)\n if inputs[\"\
 text\"] == \"bar\":\n return \"second\"\n if isinstance(inputs[\"exception\"\
 ], ValueError):\n raise RuntimeError # noqa: TRY004\n return \"third\""
 - "def validate_params(cls, values: dict) -> dict:\n \"\"\"Validate similarity\
 \ parameters.\"\"\"\n if values[\"k\"] is None and values[\"similarity_threshold\"\
 ] is None:\n msg = \"Must specify one of `k` or `similarity_threshold`.\"\
 \n raise ValueError(msg)\n return values"
 - "def get_token_ids(self, text: str) -> list[int]:\n \"\"\"Return the ordered\
 \ IDs of the tokens in a text.\n\n Args:\n text: The string\
 \ input to tokenize.\n\n Returns:\n A list of IDs corresponding\
 \ to the tokens in the text, in order they occur\n in the text.\n\
 \ \"\"\"\n if self.custom_get_token_ids is not None:\n \
 \ return self.custom_get_token_ids(text)\n return _get_token_ids_default_method(text)"
- source_sentence: How does __init__ work in Python?
 sentences:
 - "def test_loading_few_shot_prompt_from_json() -> None:\n \"\"\"Test loading\
 \ few shot prompt from json.\"\"\"\n with change_directory(EXAMPLE_DIR):\n\
 \ prompt = load_prompt(\"few_shot_prompt.json\")\n expected_prompt\
 \ = FewShotPromptTemplate(\n input_variables=[\"adjective\"],\n \
 \ prefix=\"Write antonyms for the following words.\",\n example_prompt=PromptTemplate(\n\
 \ input_variables=[\"input\", \"output\"],\n template=\"\
 Input: {input}\\nOutput: {output}\",\n ),\n examples=[\n\
 \ {\"input\": \"happy\", \"output\": \"sad\"},\n \
 \ {\"input\": \"tall\", \"output\": \"short\"},\n ],\n \
 \ suffix=\"Input: {adjective}\\nOutput:\",\n )\n assert prompt ==\
 \ expected_prompt"
 - "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"
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
- cosine_accuracy@1
- cosine_accuracy@3
- cosine_accuracy@5
- cosine_accuracy@10
- cosine_precision@1
- cosine_precision@3
- cosine_precision@5
- cosine_precision@10
- cosine_recall@1
- cosine_recall@3
- cosine_recall@5
- cosine_recall@10
- cosine_ndcg@10
- cosine_mrr@10
- cosine_map@100
model-index:
- name: codeBert Base
 results:
 - task:
 type: information-retrieval
 name: Information Retrieval
 dataset:
 name: dim 768
 type: dim_768
 metrics:
 - type: cosine_accuracy@1
 value: 0.83
 name: Cosine Accuracy@1
 - type: cosine_accuracy@3
 value: 0.85
 name: Cosine Accuracy@3
 - type: cosine_accuracy@5
 value: 0.86
 name: Cosine Accuracy@5
 - type: cosine_accuracy@10
 value: 0.94
 name: Cosine Accuracy@10
 - type: cosine_precision@1
 value: 0.83
 name: Cosine Precision@1
 - type: cosine_precision@3
 value: 0.83
 name: Cosine Precision@3
 - type: cosine_precision@5
 value: 0.83
 name: Cosine Precision@5
 - type: cosine_precision@10
 value: 0.45299999999999996
 name: Cosine Precision@10
 - type: cosine_recall@1
 value: 0.16599999999999998
 name: Cosine Recall@1
 - type: cosine_recall@3
 value: 0.498
 name: Cosine Recall@3
 - type: cosine_recall@5
 value: 0.83
 name: Cosine Recall@5
 - type: cosine_recall@10
 value: 0.9059999999999999
 name: Cosine Recall@10
 - type: cosine_ndcg@10
 value: 0.8712089918828809
 name: Cosine Ndcg@10
 - type: cosine_mrr@10
 value: 0.8532738095238095
 name: Cosine Mrr@10
 - type: cosine_map@100
 value: 0.861635686929646
 name: Cosine Map@100
 - task:
 type: information-retrieval
 name: Information Retrieval
 dataset:
 name: dim 512
 type: dim_512
 metrics:
 - type: cosine_accuracy@1
 value: 0.85
 name: Cosine Accuracy@1
 - type: cosine_accuracy@3
 value: 0.86
 name: Cosine Accuracy@3
 - type: cosine_accuracy@5
 value: 0.87
 name: Cosine Accuracy@5
 - type: cosine_accuracy@10
 value: 0.95
 name: Cosine Accuracy@10
 - type: cosine_precision@1
 value: 0.85
 name: Cosine Precision@1
 - type: cosine_precision@3
 value: 0.84
 name: Cosine Precision@3
 - type: cosine_precision@5
 value: 0.8419999999999999
 name: Cosine Precision@5
 - type: cosine_precision@10
 value: 0.45299999999999996
 name: Cosine Precision@10
 - type: cosine_recall@1
 value: 0.16999999999999996
 name: Cosine Recall@1
 - type: cosine_recall@3
 value: 0.504
 name: Cosine Recall@3
 - type: cosine_recall@5
 value: 0.8419999999999999
 name: Cosine Recall@5
 - type: cosine_recall@10
 value: 0.9059999999999999
 name: Cosine Recall@10
 - type: cosine_ndcg@10
 value: 0.8775797199885595
 name: Cosine Ndcg@10
 - type: cosine_mrr@10
 value: 0.8699404761904762
 name: Cosine Mrr@10
 - type: cosine_map@100
 value: 0.8692738075020783
 name: Cosine Map@100
 - task:
 type: information-retrieval
 name: Information Retrieval
 dataset:
 name: dim 256
 type: dim_256
 metrics:
 - type: cosine_accuracy@1
 value: 0.86
 name: Cosine Accuracy@1
 - type: cosine_accuracy@3
 value: 0.89
 name: Cosine Accuracy@3
 - type: cosine_accuracy@5
 value: 0.9
 name: Cosine Accuracy@5
 - type: cosine_accuracy@10
 value: 0.93
 name: Cosine Accuracy@10
 - type: cosine_precision@1
 value: 0.86
 name: Cosine Precision@1
 - type: cosine_precision@3
 value: 0.85
 name: Cosine Precision@3
 - type: cosine_precision@5
 value: 0.85
 name: Cosine Precision@5
 - type: cosine_precision@10
 value: 0.45
 name: Cosine Precision@10
 - type: cosine_recall@1
 value: 0.17199999999999996
 name: Cosine Recall@1
 - type: cosine_recall@3
 value: 0.51
 name: Cosine Recall@3
 - type: cosine_recall@5
 value: 0.85
 name: Cosine Recall@5
 - type: cosine_recall@10
 value: 0.9
 name: Cosine Recall@10
 - type: cosine_ndcg@10
 value: 0.8789938349894767
 name: Cosine Ndcg@10
 - type: cosine_mrr@10
 value: 0.8805952380952381
 name: Cosine Mrr@10
 - type: cosine_map@100
 value: 0.8726611807317667
 name: Cosine Map@100
 - task:
 type: information-retrieval
 name: Information Retrieval
 dataset:
 name: dim 128
 type: dim_128
 metrics:
 - type: cosine_accuracy@1
 value: 0.84
 name: Cosine Accuracy@1
 - type: cosine_accuracy@3
 value: 0.87
 name: Cosine Accuracy@3
 - type: cosine_accuracy@5
 value: 0.88
 name: Cosine Accuracy@5
 - type: cosine_accuracy@10
 value: 0.93
 name: Cosine Accuracy@10
 - type: cosine_precision@1
 value: 0.84
 name: Cosine Precision@1
 - type: cosine_precision@3
 value: 0.8366666666666667
 name: Cosine Precision@3
 - type: cosine_precision@5
 value: 0.8419999999999999
 name: Cosine Precision@5
 - type: cosine_precision@10
 value: 0.455
 name: Cosine Precision@10
 - type: cosine_recall@1
 value: 0.16799999999999998
 name: Cosine Recall@1
 - type: cosine_recall@3
 value: 0.502
 name: Cosine Recall@3
 - type: cosine_recall@5
 value: 0.8419999999999999
 name: Cosine Recall@5
 - type: cosine_recall@10
 value: 0.91
 name: Cosine Recall@10
 - type: cosine_ndcg@10
 value: 0.8777095006932575
 name: Cosine Ndcg@10
 - type: cosine_mrr@10
 value: 0.8630000000000001
 name: Cosine Mrr@10
 - type: cosine_map@100
 value: 0.8661619081282643
 name: Cosine Map@100
 - task:
 type: information-retrieval
 name: Information Retrieval
 dataset:
 name: dim 64
 type: dim_64
 metrics:
 - type: cosine_accuracy@1
 value: 0.78
 name: Cosine Accuracy@1
 - type: cosine_accuracy@3
 value: 0.81
 name: Cosine Accuracy@3
 - type: cosine_accuracy@5
 value: 0.81
 name: Cosine Accuracy@5
 - type: cosine_accuracy@10
 value: 0.93
 name: Cosine Accuracy@10
 - type: cosine_precision@1
 value: 0.78
 name: Cosine Precision@1
 - type: cosine_precision@3
 value: 0.7866666666666667
 name: Cosine Precision@3
 - type: cosine_precision@5
 value: 0.7859999999999999
 name: Cosine Precision@5
 - type: cosine_precision@10
 value: 0.44799999999999995
 name: Cosine Precision@10
 - type: cosine_recall@1
 value: 0.15599999999999997
 name: Cosine Recall@1
 - type: cosine_recall@3
 value: 0.472
 name: Cosine Recall@3
 - type: cosine_recall@5
 value: 0.7859999999999999
 name: Cosine Recall@5
 - type: cosine_recall@10
 value: 0.8959999999999999
 name: Cosine Recall@10
 - type: cosine_ndcg@10
 value: 0.8445404597381452
 name: Cosine Ndcg@10
 - type: cosine_mrr@10
 value: 0.8120634920634922
 name: Cosine Mrr@10
 - type: cosine_map@100
 value: 0.8308457034802883
 name: Cosine Map@100
---
# codeBert Base
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [microsoft/codebert-base](https://huggingface.co/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](https://huggingface.co/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](https://sbert.net)
- **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers)
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
### 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:
```bash
pip install -U sentence-transformers
```
Then you can load this model and run inference.
```python
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>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
 ```json
 {
 "truncate_dim": 768
 }
 ```
| Metric | Value |
|:--------------------|:-----------|
| cosine_accuracy@1 | 0.83 |
| cosine_accuracy@3 | 0.85 |
| cosine_accuracy@5 | 0.86 |
| cosine_accuracy@10 | 0.94 |
| cosine_precision@1 | 0.83 |
| cosine_precision@3 | 0.83 |
| cosine_precision@5 | 0.83 |
| cosine_precision@10 | 0.453 |
| cosine_recall@1 | 0.166 |
| cosine_recall@3 | 0.498 |
| cosine_recall@5 | 0.83 |
| cosine_recall@10 | 0.906 |
| **cosine_ndcg@10** | **0.8712** |
| cosine_mrr@10 | 0.8533 |
| cosine_map@100 | 0.8616 |
#### Information Retrieval
* Dataset: `dim_512`
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
 ```json
 {
 "truncate_dim": 512
 }
 ```
| Metric | Value |
|:--------------------|:-----------|
| cosine_accuracy@1 | 0.85 |
| cosine_accuracy@3 | 0.86 |
| cosine_accuracy@5 | 0.87 |
| cosine_accuracy@10 | 0.95 |
| cosine_precision@1 | 0.85 |
| cosine_precision@3 | 0.84 |
| cosine_precision@5 | 0.842 |
| cosine_precision@10 | 0.453 |
| cosine_recall@1 | 0.17 |
| cosine_recall@3 | 0.504 |
| cosine_recall@5 | 0.842 |
| cosine_recall@10 | 0.906 |
| **cosine_ndcg@10** | **0.8776** |
| cosine_mrr@10 | 0.8699 |
| cosine_map@100 | 0.8693 |
#### Information Retrieval
* Dataset: `dim_256`
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
 ```json
 {
 "truncate_dim": 256
 }
 ```
| Metric | Value |
|:--------------------|:----------|
| cosine_accuracy@1 | 0.86 |
| cosine_accuracy@3 | 0.89 |
| cosine_accuracy@5 | 0.9 |
| cosine_accuracy@10 | 0.93 |
| cosine_precision@1 | 0.86 |
| cosine_precision@3 | 0.85 |
| cosine_precision@5 | 0.85 |
| cosine_precision@10 | 0.45 |
| cosine_recall@1 | 0.172 |
| cosine_recall@3 | 0.51 |
| cosine_recall@5 | 0.85 |
| cosine_recall@10 | 0.9 |
| **cosine_ndcg@10** | **0.879** |
| cosine_mrr@10 | 0.8806 |
| cosine_map@100 | 0.8727 |
#### Information Retrieval
* Dataset: `dim_128`
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
 ```json
 {
 "truncate_dim": 128
 }
 ```
| Metric | Value |
|:--------------------|:-----------|
| cosine_accuracy@1 | 0.84 |
| cosine_accuracy@3 | 0.87 |
| cosine_accuracy@5 | 0.88 |
| cosine_accuracy@10 | 0.93 |
| cosine_precision@1 | 0.84 |
| cosine_precision@3 | 0.8367 |
| cosine_precision@5 | 0.842 |
| cosine_precision@10 | 0.455 |
| cosine_recall@1 | 0.168 |
| cosine_recall@3 | 0.502 |
| cosine_recall@5 | 0.842 |
| cosine_recall@10 | 0.91 |
| **cosine_ndcg@10** | **0.8777** |
| cosine_mrr@10 | 0.863 |
| cosine_map@100 | 0.8662 |
#### Information Retrieval
* Dataset: `dim_64`
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
 ```json
 {
 "truncate_dim": 64
 }
 ```
| Metric | Value |
|:--------------------|:-----------|
| cosine_accuracy@1 | 0.78 |
| cosine_accuracy@3 | 0.81 |
| cosine_accuracy@5 | 0.81 |
| cosine_accuracy@10 | 0.93 |
| cosine_precision@1 | 0.78 |
| cosine_precision@3 | 0.7867 |
| cosine_precision@5 | 0.786 |
| cosine_precision@10 | 0.448 |
| cosine_recall@1 | 0.156 |
| cosine_recall@3 | 0.472 |
| cosine_recall@5 | 0.786 |
| cosine_recall@10 | 0.896 |
| **cosine_ndcg@10** | **0.8445** |
| cosine_mrr@10 | 0.8121 |
| cosine_map@100 | 0.8308 |
<!--
## 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 test_qdrant_similarity_search_with_relevance_scores logic</code> | <code>def test_qdrant_similarity_search_with_relevance_scores(<br> batch_size: int,<br> content_payload_key: str,<br> metadata_payload_key: str,<br> vector_name: str \| None,<br>) -> None:<br> """Test end to end construction and search."""<br> texts = ["foo", "bar", "baz"]<br> docsearch = Qdrant.from_texts(<br> texts,<br> ConsistentFakeEmbeddings(),<br> location=":memory:",<br> content_payload_key=content_payload_key,<br> metadata_payload_key=metadata_payload_key,<br> batch_size=batch_size,<br> vector_name=vector_name,<br> )<br> output = docsearch.similarity_search_with_relevance_scores("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 random_name</code> | <code>def random_name() -> 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>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
 ```json
 {
 "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`: {'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
- `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
| Epoch | Step | Training Loss | dim_768_cosine_ndcg@10 | dim_512_cosine_ndcg@10 | dim_256_cosine_ndcg@10 | dim_128_cosine_ndcg@10 | dim_64_cosine_ndcg@10 |
|:-------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|
| 0.7111 | 10 | 6.8447 | - | - | - | - | - |
| 1.0 | 15 | - | 0.1025 | 0.0367 | 0.0548 | 0.0502 | 0.1185 |
| 0.7111 | 10 | 4.8545 | - | - | - | - | - |
| 1.0 | 15 | - | 0.2250 | 0.3047 | 0.2895 | 0.2892 | 0.3178 |
| 0.7111 | 10 | 1.9011 | - | - | - | - | - |
| 1.0 | 15 | - | 0.6530 | 0.6393 | 0.6269 | 0.6631 | 0.6658 |
| 1.3556 | 20 | 0.6349 | - | - | - | - | - |
| 2.0 | 30 | 0.1887 | 0.8480 | 0.8643 | 0.8641 | 0.8532 | 0.7974 |
| 2.7111 | 40 | 0.0959 | - | - | - | - | - |
| 3.0 | 45 | - | 0.8688 | 0.8774 | 0.8754 | 0.8725 | 0.8457 |
| 3.3556 | 50 | 0.0359 | - | - | - | - | - |
| **4.0** | **60** | **0.0515** | **0.8712** | **0.8776** | **0.879** | **0.8777** | **0.8445** |
* 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
```bibtex
@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
```bibtex
@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
```bibtex
@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.*
-->

Xet Storage Details

Size:
41 kB
·
Xet hash:
d1b19d228be577bfd2d3d40f6b98ebc3aae4262b49794dd098463902fbb6c37e

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.