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 +1,1025 @@
+---
+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: shubharuidas/codebert-embed-base-dense-retriever
+widget:
+- source_sentence: Best practices for __init__
+  sentences:
+  - "def close(self) -> None:\n        self.sync()\n        self.clear()"
+  - "class MyClass:\n        def __call__(self, state):\n            return\n\n  \
+    \      def class_method(self, state):\n            return"
+  - "def __init__(self, name: str):\n            self.name = name\n            self.lock\
+    \ = threading.Lock()"
+- source_sentence: Explain the close logic
+  sentences:
+  - "def close(self) -> None:\n        self.sync()\n        self.clear()"
+  - "def attach_node(self, key: str, node: StateNodeSpec[Any, ContextT] | None) ->\
+    \ None:\n        if key == START:\n            output_keys = [\n             \
+    \   k\n                for k, v in self.builder.schemas[self.builder.input_schema].items()\n\
+    \                if not is_managed_value(v)\n            ]\n        else:\n  \
+    \          output_keys = list(self.builder.channels) + [\n                k for\
+    \ k, v in self.builder.managed.items()\n            ]\n\n        def _get_updates(\n\
+    \            input: None | dict | Any,\n        ) -> Sequence[tuple[str, Any]]\
+    \ | None:\n            if input is None:\n                return None\n      \
+    \      elif isinstance(input, dict):\n                return [(k, v) for k, v\
+    \ in input.items() if k in output_keys]\n            elif isinstance(input, Command):\n\
+    \                if input.graph == Command.PARENT:\n                    return\
+    \ None\n                return [\n                    (k, v) for k, v in input._update_as_tuples()\
+    \ if k in output_keys\n                ]\n            elif (\n               \
+    \ isinstance(input, (list, tuple))\n                and input\n              \
+    \  and any(isinstance(i, Command) for i in input)\n            ):\n          \
+    \      updates: list[tuple[str, Any]] = []\n                for i in input:\n\
+    \                    if isinstance(i, Command):\n                        if i.graph\
+    \ == Command.PARENT:\n                            continue\n                 \
+    \       updates.extend(\n                            (k, v) for k, v in i._update_as_tuples()\
+    \ if k in output_keys\n                        )\n                    else:\n\
+    \                        updates.extend(_get_updates(i) or ())\n             \
+    \   return updates\n            elif (t := type(input)) and get_cached_annotated_keys(t):\n\
+    \                return get_update_as_tuples(input, output_keys)\n           \
+    \ else:\n                msg = create_error_message(\n                    message=f\"\
+    Expected dict, got {input}\",\n                    error_code=ErrorCode.INVALID_GRAPH_NODE_RETURN_VALUE,\n\
+    \                )\n                raise InvalidUpdateError(msg)\n\n        #\
+    \ state updaters\n        write_entries: tuple[ChannelWriteEntry | ChannelWriteTupleEntry,\
+    \ ...] = (\n            ChannelWriteTupleEntry(\n                mapper=_get_root\
+    \ if output_keys == [\"__root__\"] else _get_updates\n            ),\n       \
+    \     ChannelWriteTupleEntry(\n                mapper=_control_branch,\n     \
+    \           static=_control_static(node.ends)\n                if node is not\
+    \ None and node.ends is not None\n                else None,\n            ),\n\
+    \        )\n\n        # add node and output channel\n        if key == START:\n\
+    \            self.nodes[key] = PregelNode(\n                tags=[TAG_HIDDEN],\n\
+    \                triggers=[START],\n                channels=START,\n        \
+    \        writers=[ChannelWrite(write_entries)],\n            )\n        elif node\
+    \ is not None:\n            input_schema = node.input_schema if node else self.builder.state_schema\n\
+    \            input_channels = list(self.builder.schemas[input_schema])\n     \
+    \       is_single_input = len(input_channels) == 1 and \"__root__\" in input_channels\n\
+    \            if input_schema in self.schema_to_mapper:\n                mapper\
+    \ = self.schema_to_mapper[input_schema]\n            else:\n                mapper\
+    \ = _pick_mapper(input_channels, input_schema)\n                self.schema_to_mapper[input_schema]\
+    \ = mapper\n\n            branch_channel = _CHANNEL_BRANCH_TO.format(key)\n  \
+    \          self.channels[branch_channel] = (\n                LastValueAfterFinish(Any)\n\
+    \                if node.defer\n                else EphemeralValue(Any, guard=False)\n\
+    \            )\n            self.nodes[key] = PregelNode(\n                triggers=[branch_channel],\n\
+    \                # read state keys and managed values\n                channels=(\"\
+    __root__\" if is_single_input else input_channels),\n                # coerce\
+    \ state dict to schema class (eg. pydantic model)\n                mapper=mapper,\n\
+    \                # publish to state keys\n                writers=[ChannelWrite(write_entries)],\n\
+    \                metadata=node.metadata,\n                retry_policy=node.retry_policy,\n\
+    \                cache_policy=node.cache_policy,\n                bound=node.runnable,\
+    \  # type: ignore[arg-type]\n            )\n        else:\n            raise RuntimeError"
+  - "def tick(\n        self,\n        tasks: Iterable[PregelExecutableTask],\n  \
+    \      *,\n        reraise: bool = True,\n        timeout: float | None = None,\n\
+    \        retry_policy: Sequence[RetryPolicy] | None = None,\n        get_waiter:\
+    \ Callable[[], concurrent.futures.Future[None]] | None = None,\n        schedule_task:\
+    \ Callable[\n            [PregelExecutableTask, int, Call | None],\n         \
+    \   PregelExecutableTask | None,\n        ],\n    ) -> Iterator[None]:\n     \
+    \   tasks = tuple(tasks)\n        futures = FuturesDict(\n            callback=weakref.WeakMethod(self.commit),\n\
+    \            event=threading.Event(),\n            future_type=concurrent.futures.Future,\n\
+    \        )\n        # give control back to the caller\n        yield\n       \
+    \ # fast path if single task with no timeout and no waiter\n        if len(tasks)\
+    \ == 0:\n            return\n        elif len(tasks) == 1 and timeout is None\
+    \ and get_waiter is None:\n            t = tasks[0]\n            try:\n      \
+    \          run_with_retry(\n                    t,\n                    retry_policy,\n\
+    \                    configurable={\n                        CONFIG_KEY_CALL:\
+    \ partial(\n                            _call,\n                            weakref.ref(t),\n\
+    \                            retry_policy=retry_policy,\n                    \
+    \        futures=weakref.ref(futures),\n                            schedule_task=schedule_task,\n\
+    \                            submit=self.submit,\n                        ),\n\
+    \                    },\n                )\n                self.commit(t, None)\n\
+    \            except Exception as exc:\n                self.commit(t, exc)\n \
+    \               if reraise and futures:\n                    # will be re-raised\
+    \ after futures are done\n                    fut: concurrent.futures.Future =\
+    \ concurrent.futures.Future()\n                    fut.set_exception(exc)\n  \
+    \                  futures.done.add(fut)\n                elif reraise:\n    \
+    \                if tb := exc.__traceback__:\n                        while tb.tb_next\
+    \ is not None and any(\n                            tb.tb_frame.f_code.co_filename.endswith(name)\n\
+    \                            for name in EXCLUDED_FRAME_FNAMES\n             \
+    \           ):\n                            tb = tb.tb_next\n                \
+    \        exc.__traceback__ = tb\n                    raise\n            if not\
+    \ futures:  # maybe `t` scheduled another task\n                return\n     \
+    \       else:\n                tasks = ()  # don't reschedule this task\n    \
+    \    # add waiter task if requested\n        if get_waiter is not None:\n    \
+    \        futures[get_waiter()] = None\n        # schedule tasks\n        for t\
+    \ in tasks:\n            fut = self.submit()(  # type: ignore[misc]\n        \
+    \        run_with_retry,\n                t,\n                retry_policy,\n\
+    \                configurable={\n                    CONFIG_KEY_CALL: partial(\n\
+    \                        _call,\n                        weakref.ref(t),\n   \
+    \                     retry_policy=retry_policy,\n                        futures=weakref.ref(futures),\n\
+    \                        schedule_task=schedule_task,\n                      \
+    \  submit=self.submit,\n                    ),\n                },\n         \
+    \       __reraise_on_exit__=reraise,\n            )\n            futures[fut]\
+    \ = t\n        # execute tasks, and wait for one to fail or all to finish.\n \
+    \       # each task is independent from all other concurrent tasks\n        #\
+    \ yield updates/debug output as each task finishes\n        end_time = timeout\
+    \ + time.monotonic() if timeout else None\n        while len(futures) > (1 if\
+    \ get_waiter is not None else 0):\n            done, inflight = concurrent.futures.wait(\n\
+    \                futures,\n                return_when=concurrent.futures.FIRST_COMPLETED,\n\
+    \                timeout=(max(0, end_time - time.monotonic()) if end_time else\
+    \ None),\n            )\n            if not done:\n                break  # timed\
+    \ out\n            for fut in done:\n                task = futures.pop(fut)\n\
+    \                if task is None:\n                    # waiter task finished,\
+    \ schedule another\n                    if inflight and get_waiter is not None:\n\
+    \                        futures[get_waiter()] = None\n            else:\n   \
+    \             # remove references to loop vars\n                del fut, task\n\
+    \            # maybe stop other tasks\n            if _should_stop_others(done):\n\
+    \                break\n            # give control back to the caller\n      \
+    \      yield\n        # wait for done callbacks\n        futures.event.wait(\n\
+    \            timeout=(max(0, end_time - time.monotonic()) if end_time else None)\n\
+    \        )\n        # give control back to the caller\n        yield\n       \
+    \ # panic on failure or timeout\n        try:\n            _panic_or_proceed(\n\
+    \                futures.done.union(f for f, t in futures.items() if t is not\
+    \ None),\n                panic=reraise,\n            )\n        except Exception\
+    \ as exc:\n            if tb := exc.__traceback__:\n                while tb.tb_next\
+    \ is not None and any(\n                    tb.tb_frame.f_code.co_filename.endswith(name)\n\
+    \                    for name in EXCLUDED_FRAME_FNAMES\n                ):\n \
+    \                   tb = tb.tb_next\n                exc.__traceback__ = tb\n\
+    \            raise"
+- source_sentence: Explain the async aupdate_state logic
+  sentences:
+  - "class MyClass:\n        def __call__(self, state):\n            return\n\n  \
+    \      def class_method(self, state):\n            return"
+  - "async def aupdate_state(\n        self,\n        config: RunnableConfig,\n  \
+    \      values: dict[str, Any] | Any | None,\n        as_node: str | None = None,\n\
+    \        *,\n        headers: dict[str, str] | None = None,\n        params: QueryParamTypes\
+    \ | None = None,\n    ) -> RunnableConfig:\n        \"\"\"Update the state of\
+    \ a thread.\n\n        This method calls `POST /threads/{thread_id}/state`.\n\n\
+    \        Args:\n            config: A `RunnableConfig` that includes `thread_id`\
+    \ in the\n                `configurable` field.\n            values: Values to\
+    \ update to the state.\n            as_node: Update the state as if this node\
+    \ had just executed.\n\n        Returns:\n            `RunnableConfig` for the\
+    \ updated thread.\n        \"\"\"\n        client = self._validate_client()\n\
+    \        merged_config = merge_configs(self.config, config)\n\n        response:\
+    \ dict = await client.threads.update_state(  # type: ignore\n            thread_id=merged_config[\"\
+    configurable\"][\"thread_id\"],\n            values=values,\n            as_node=as_node,\n\
+    \            checkpoint=self._get_checkpoint(merged_config),\n            headers=headers,\n\
+    \            params=params,\n        )\n        return self._get_config(response[\"\
+    checkpoint\"])"
+  - "def __init__(self, typ: Any, guard: bool = True) -> None:\n        super().__init__(typ)\n\
+    \        self.guard = guard\n        self.value = MISSING"
+- source_sentence: How to implement langchain_to_openai_messages?
+  sentences:
+  - "def __init__(\n        self,\n        message: str,\n        *args: object,\n\
+    \        since: tuple[int, int],\n        expected_removal: tuple[int, int] |\
+    \ None = None,\n    ) -> None:\n        super().__init__(message, *args)\n   \
+    \     self.message = message.rstrip(\".\")\n        self.since = since\n     \
+    \   self.expected_removal = (\n            expected_removal if expected_removal\
+    \ is not None else (since[0] + 1, 0)\n        )"
+  - "def test_batch_get_ops(store: PostgresStore) -> None:\n    # Setup test data\n\
+    \    store.put((\"test\",), \"key1\", {\"data\": \"value1\"})\n    store.put((\"\
+    test\",), \"key2\", {\"data\": \"value2\"})\n\n    ops = [\n        GetOp(namespace=(\"\
+    test\",), key=\"key1\"),\n        GetOp(namespace=(\"test\",), key=\"key2\"),\n\
+    \        GetOp(namespace=(\"test\",), key=\"key3\"),  # Non-existent key\n   \
+    \ ]\n\n    results = store.batch(ops)\n\n    assert len(results) == 3\n    assert\
+    \ results[0] is not None\n    assert results[1] is not None\n    assert results[2]\
+    \ is None\n    assert results[0].key == \"key1\"\n    assert results[1].key ==\
+    \ \"key2\""
+  - "def langchain_to_openai_messages(messages: List[BaseMessage]):\n    \"\"\"\n\
+    \    Convert a list of langchain base messages to a list of openai messages.\n\
+    \n    Parameters:\n        messages (List[BaseMessage]): A list of langchain base\
+    \ messages.\n\n    Returns:\n        List[dict]: A list of openai messages.\n\
+    \    \"\"\"\n\n    return [\n        convert_message_to_dict(m) if isinstance(m,\
+    \ BaseMessage) else m\n        for m in messages\n    ]"
+- source_sentence: Explain the CheckpointPayload logic
+  sentences:
+  - "class LocalDeps(NamedTuple):\n    \"\"\"A container for referencing and managing\
+    \ local Python dependencies.\n\n    A \"local dependency\" is any entry in the\
+    \ config's `dependencies` list\n    that starts with \".\" (dot), denoting a relative\
+    \ path\n    to a local directory containing Python code.\n\n    For each local\
+    \ dependency, the system inspects its directory to\n    determine how it should\
+    \ be installed inside the Docker container.\n\n    Specifically, we detect:\n\n\
+    \    - **Real packages**: Directories containing a `pyproject.toml` or a `setup.py`.\n\
+    \      These can be installed with pip as a regular Python package.\n    - **Faux\
+    \ packages**: Directories that do not include a `pyproject.toml` or\n      `setup.py`\
+    \ but do contain Python files and possibly an `__init__.py`. For\n      these,\
+    \ the code dynamically generates a minimal `pyproject.toml` in the\n      Docker\
+    \ image so that they can still be installed with pip.\n    - **Requirements files**:\
+    \ If a local dependency directory\n      has a `requirements.txt`, it is tracked\
+    \ so that those dependencies\n      can be installed within the Docker container\
+    \ before installing the local package.\n\n    Attributes:\n        pip_reqs: A\
+    \ list of (host_requirements_path, container_requirements_path)\n            tuples.\
+    \ Each entry points to a local `requirements.txt` file and where\n           \
+    \ it should be placed inside the Docker container before running `pip install`.\n\
+    \n        real_pkgs: A dictionary mapping a local directory path (host side) to\
+    \ a\n            tuple of (dependency_string, container_package_path). These directories\n\
+    \            contain the necessary files (e.g., `pyproject.toml` or `setup.py`)\
+    \ to be\n            installed as a standard Python package with pip.\n\n    \
+    \    faux_pkgs: A dictionary mapping a local directory path (host side) to a\n\
+    \            tuple of (dependency_string, container_package_path). For these\n\
+    \            directories—called \"faux packages\"—the code will generate a minimal\n\
+    \            `pyproject.toml` inside the Docker image. This ensures that pip\n\
+    \            recognizes them as installable packages, even though they do not\n\
+    \            natively include packaging metadata.\n\n        working_dir: The\
+    \ path inside the Docker container to use as the working\n            directory.\
+    \ If the local dependency `\".\"` is present in the config, this\n           \
+    \ field captures the path where that dependency will appear in the\n         \
+    \   container (e.g., `/deps/<name>` or similar). Otherwise, it may be `None`.\n\
+    \n        additional_contexts: A list of paths to directories that contain local\n\
+    \            dependencies in parent directories. These directories are added to\
+    \ the\n            Docker build context to ensure that the Dockerfile can access\
+    \ them.\n    \"\"\"\n\n    pip_reqs: list[tuple[pathlib.Path, str]]\n    real_pkgs:\
+    \ dict[pathlib.Path, tuple[str, str]]\n    faux_pkgs: dict[pathlib.Path, tuple[str,\
+    \ str]]\n    # if . is in dependencies, use it as working_dir\n    working_dir:\
+    \ str | None = None\n    # if there are local dependencies in parent directories,\
+    \ use additional_contexts\n    additional_contexts: list[pathlib.Path] = None"
+  - "class CheckpointPayload(TypedDict):\n    config: RunnableConfig | None\n    metadata:\
+    \ CheckpointMetadata\n    values: dict[str, Any]\n    next: list[str]\n    parent_config:\
+    \ RunnableConfig | None\n    tasks: list[CheckpointTask]"
+  - "class _RuntimeOverrides(TypedDict, Generic[ContextT], total=False):\n    context:\
+    \ ContextT\n    store: BaseStore | None\n    stream_writer: StreamWriter\n   \
+    \ previous: Any"
+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 dense retriever
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 768
+      type: dim_768
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.84
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.84
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.84
+      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: 0.84
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.84
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.465
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.16799999999999998
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.504
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.84
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.93
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8886895066001008
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.855
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.877942533867708
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.88
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.88
+      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: 0.88
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.88
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.88
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.465
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.17599999999999993
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.528
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.88
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.93
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.907049725888945
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8883333333333333
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.9038835868016827
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.87
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.87
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.87
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.92
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.87
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.87
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.87
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.46
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.17399999999999996
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.522
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.87
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.92
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8970497258889449
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8783333333333334
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8959313741265157
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.86
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.86
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.86
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.95
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.86
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.86
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.86
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.475
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.17199999999999996
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.516
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.86
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.95
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.9086895066001008
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.875
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8949791356739454
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.84
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.84
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.84
+      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: 0.84
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.84
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.465
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.16799999999999998
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.504
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.84
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.93
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8886895066001008
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.855
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8791923582191525
+      name: Cosine Map@100
+---
+
+# codeBert dense retriever
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [shubharuidas/codebert-embed-base-dense-retriever](https://huggingface.co/shubharuidas/codebert-embed-base-dense-retriever). 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:** [shubharuidas/codebert-embed-base-dense-retriever](https://huggingface.co/shubharuidas/codebert-embed-base-dense-retriever) <!-- at revision 9594580ae943039d0b85feb304404f9b2bb203ce -->
+- **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("shubharuidas/codebert-base-code-embed-mrl-langchain-langgraph")
+# Run inference
+sentences = [
+    'Explain the CheckpointPayload logic',
+    'class CheckpointPayload(TypedDict):\n    config: RunnableConfig | None\n    metadata: CheckpointMetadata\n    values: dict[str, Any]\n    next: list[str]\n    parent_config: RunnableConfig | None\n    tasks: list[CheckpointTask]',
+    'class _RuntimeOverrides(TypedDict, Generic[ContextT], total=False):\n    context: ContextT\n    store: BaseStore | None\n    stream_writer: StreamWriter\n    previous: Any',
+]
+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, 0.7282, 0.2122],
+#         [0.7282, 1.0000, 0.3511],
+#         [0.2122, 0.3511, 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   | 0.84       |
+| cosine_accuracy@3   | 0.84       |
+| cosine_accuracy@5   | 0.84       |
+| cosine_accuracy@10  | 0.93       |
+| cosine_precision@1  | 0.84       |
+| cosine_precision@3  | 0.84       |
+| cosine_precision@5  | 0.84       |
+| cosine_precision@10 | 0.465      |
+| cosine_recall@1     | 0.168      |
+| cosine_recall@3     | 0.504      |
+| cosine_recall@5     | 0.84       |
+| cosine_recall@10    | 0.93       |
+| **cosine_ndcg@10**  | **0.8887** |
+| cosine_mrr@10       | 0.855      |
+| cosine_map@100      | 0.8779     |
+
+#### 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   | 0.88      |
+| cosine_accuracy@3   | 0.88      |
+| cosine_accuracy@5   | 0.88      |
+| cosine_accuracy@10  | 0.93      |
+| cosine_precision@1  | 0.88      |
+| cosine_precision@3  | 0.88      |
+| cosine_precision@5  | 0.88      |
+| cosine_precision@10 | 0.465     |
+| cosine_recall@1     | 0.176     |
+| cosine_recall@3     | 0.528     |
+| cosine_recall@5     | 0.88      |
+| cosine_recall@10    | 0.93      |
+| **cosine_ndcg@10**  | **0.907** |
+| cosine_mrr@10       | 0.8883    |
+| cosine_map@100      | 0.9039    |
+
+#### 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   | 0.87      |
+| cosine_accuracy@3   | 0.87      |
+| cosine_accuracy@5   | 0.87      |
+| cosine_accuracy@10  | 0.92      |
+| cosine_precision@1  | 0.87      |
+| cosine_precision@3  | 0.87      |
+| cosine_precision@5  | 0.87      |
+| cosine_precision@10 | 0.46      |
+| cosine_recall@1     | 0.174     |
+| cosine_recall@3     | 0.522     |
+| cosine_recall@5     | 0.87      |
+| cosine_recall@10    | 0.92      |
+| **cosine_ndcg@10**  | **0.897** |
+| cosine_mrr@10       | 0.8783    |
+| cosine_map@100      | 0.8959    |
+
+#### 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   | 0.86       |
+| cosine_accuracy@3   | 0.86       |
+| cosine_accuracy@5   | 0.86       |
+| cosine_accuracy@10  | 0.95       |
+| cosine_precision@1  | 0.86       |
+| cosine_precision@3  | 0.86       |
+| cosine_precision@5  | 0.86       |
+| cosine_precision@10 | 0.475      |
+| cosine_recall@1     | 0.172      |
+| cosine_recall@3     | 0.516      |
+| cosine_recall@5     | 0.86       |
+| cosine_recall@10    | 0.95       |
+| **cosine_ndcg@10**  | **0.9087** |
+| cosine_mrr@10       | 0.875      |
+| cosine_map@100      | 0.895      |
+
+#### 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   | 0.84       |
+| cosine_accuracy@3   | 0.84       |
+| cosine_accuracy@5   | 0.84       |
+| cosine_accuracy@10  | 0.93       |
+| cosine_precision@1  | 0.84       |
+| cosine_precision@3  | 0.84       |
+| cosine_precision@5  | 0.84       |
+| cosine_precision@10 | 0.465      |
+| cosine_recall@1     | 0.168      |
+| cosine_recall@3     | 0.504      |
+| cosine_recall@5     | 0.84       |
+| cosine_recall@10    | 0.93       |
+| **cosine_ndcg@10**  | **0.8887** |
+| cosine_mrr@10       | 0.855      |
+| cosine_map@100      | 0.8792     |
+
+<!--
+## 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: 13.77 tokens</li><li>max: 356 tokens</li></ul> | <ul><li>min: 14 tokens</li><li>mean: 267.71 tokens</li><li>max: 512 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                                                                                                                                                   | positive                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
+  |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>How does put_item work in Python?</code>                                                                                                                                                                                                           | <code>def put_item(<br>        self,<br>        namespace: Sequence[str],<br>        /,<br>        key: str,<br>        value: Mapping[str, Any],<br>        index: Literal[False] \| list[str] \| None = None,<br>        ttl: int \| None = None,<br>        headers: Mapping[str, str] \| None = None,<br>        params: QueryParamTypes \| None = None,<br>    ) -> None:<br>        """Store or update an item.<br><br>        Args:<br>            namespace: A list of strings representing the namespace path.<br>            key: The unique identifier for the item within the namespace.<br>            value: A dictionary containing the item's data.<br>            index: Controls search indexing - None (use defaults), False (disable), or list of field paths to index.<br>            ttl: Optional time-to-live in minutes for the item, or None for no expiration.<br>            headers: Optional custom headers to include with the request.<br>            params: Optional query parameters to include with the request.<br><br>        Returns:<br>            `None`<br><br>        ???+ example...</code>                 |
+  | <code>Explain the RunsClient:<br>    """Client for managing runs in LangGraph.<br><br>    A run is a single assistant invocation with optional input, config, context, and metadata.<br>    This client manages runs, which can be stateful logic</code> | <code>class RunsClient:<br>    """Client for managing runs in LangGraph.<br><br>    A run is a single assistant invocation with optional input, config, context, and metadata.<br>    This client manages runs, which can be stateful (on threads) or stateless.<br><br>    ???+ example "Example"<br><br>        ```python<br>        client = get_client(url="http://localhost:2024")<br>        run = await client.runs.create(assistant_id="asst_123", thread_id="thread_456", input={"query": "Hello"})<br>        ```<br>    """<br><br>    def __init__(self, http: HttpClient) -> None:<br>        self.http = http<br><br>    @overload<br>    def stream(<br>        self,<br>        thread_id: str,<br>        assistant_id: str,<br>        *,<br>        input: Input \| None = None,<br>        command: Command \| None = None,<br>        stream_mode: StreamMode \| Sequence[StreamMode] = "values",<br>        stream_subgraphs: bool = False,<br>        stream_resumable: bool = False,<br>        metadata: Mapping[str, Any] \| None = None,<br>        config: Config \| None = None,<br>        context: Context \| N...</code> |
+  | <code>Best practices for MyChildDict</code>                                                                                                                                                                                                              | <code>class MyChildDict(MyBaseTypedDict):<br>        val_11: int<br>        val_11b: int \| None<br>        val_11c: int \| None \| str</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`: 2
+- `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`: 2
+- `max_steps`: -1
+- `lr_scheduler_type`: cosine
+- `lr_scheduler_kwargs`: None
+- `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     | 0.6327        | -                      | -                      | -                      | -                      | -                     |
+| 1.0     | 15     | -             | 0.8970                 | 0.8979                 | 0.8925                 | 0.8979                 | 0.8641                |
+| 1.3556  | 20     | 0.2227        | -                      | -                      | -                      | -                      | -                     |
+| **2.0** | **30** | **0.1692**    | **0.8887**             | **0.907**              | **0.897**              | **0.9087**             | **0.8887**            |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.12.12
+- Sentence Transformers: 5.2.0
+- Transformers: 4.57.6
+- 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": "4.57.6",
+  "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": "4.57.6",
+    "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:ef396df74c9322e9fd2672b46ec93c46bb6156b9a1f34f093edf45711f93223e
+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 +1,65 @@
+{
+  "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>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}