Add new SentenceTransformer model

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "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
+}

README.md

@@ -0,0 +1,922 @@
+---
+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.*
+-->

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "RobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.57.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "model_type": "SentenceTransformer",
+  "__version__": {
+    "sentence_transformers": "5.2.0",
+    "transformers": "4.57.3",
+    "pytorch": "2.9.0+cu126"
+  },
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a25cab114301581bb32a078cb3d4af63721738dbd380069070ca2605c7b4b44
+size 498604904

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 512,
+    "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}