Add new SentenceTransformer model

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "word_embedding_dimension": 384,
+    "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 +1,462 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dense
+- generated_from_trainer
+- dataset_size:9020
+- loss:MultipleNegativesRankingLoss
+base_model: sentence-transformers/all-MiniLM-L6-v2
+widget:
+- source_sentence: python multiprocessing show cpu count
+  sentences:
+  - "def unique(seq):\n    \"\"\"Return the unique elements of a collection even if\
+    \ those elements are\n       unhashable and unsortable, like dicts and sets\"\"\
+    \"\n    cleaned = []\n    for each in seq:\n        if each not in cleaned:\n\
+    \            cleaned.append(each)\n    return cleaned"
+  - "def is_in(self, point_x, point_y):\n        \"\"\" Test if a point is within\
+    \ this polygonal region \"\"\"\n\n        point_array = array(((point_x, point_y),))\n\
+    \        vertices = array(self.points)\n        winding = self.inside_rule ==\
+    \ \"winding\"\n        result = points_in_polygon(point_array, vertices, winding)\n\
+    \        return result[0]"
+  - "def machine_info():\n    \"\"\"Retrieve core and memory information for the current\
+    \ machine.\n    \"\"\"\n    import psutil\n    BYTES_IN_GIG = 1073741824.0\n \
+    \   free_bytes = psutil.virtual_memory().total\n    return [{\"memory\": float(\"\
+    %.1f\" % (free_bytes / BYTES_IN_GIG)), \"cores\": multiprocessing.cpu_count(),\n\
+    \             \"name\": socket.gethostname()}]"
+- source_sentence: python subplot set the whole title
+  sentences:
+  - "def set_title(self, title, **kwargs):\n        \"\"\"Sets the title on the underlying\
+    \ matplotlib AxesSubplot.\"\"\"\n        ax = self.get_axes()\n        ax.set_title(title,\
+    \ **kwargs)"
+  - "def moving_average(array, n=3):\n    \"\"\"\n    Calculates the moving average\
+    \ of an array.\n\n    Parameters\n    ----------\n    array : array\n        The\
+    \ array to have the moving average taken of\n    n : int\n        The number of\
+    \ points of moving average to take\n    \n    Returns\n    -------\n    MovingAverageArray\
+    \ : array\n        The n-point moving average of the input array\n    \"\"\"\n\
+    \    ret = _np.cumsum(array, dtype=float)\n    ret[n:] = ret[n:] - ret[:-n]\n\
+    \    return ret[n - 1:] / n"
+  - "def to_query_parameters(parameters):\n    \"\"\"Converts DB-API parameter values\
+    \ into query parameters.\n\n    :type parameters: Mapping[str, Any] or Sequence[Any]\n\
+    \    :param parameters: A dictionary or sequence of query parameter values.\n\n\
+    \    :rtype: List[google.cloud.bigquery.query._AbstractQueryParameter]\n    :returns:\
+    \ A list of query parameters.\n    \"\"\"\n    if parameters is None:\n      \
+    \  return []\n\n    if isinstance(parameters, collections_abc.Mapping):\n    \
+    \    return to_query_parameters_dict(parameters)\n\n    return to_query_parameters_list(parameters)"
+- source_sentence: python merge two set to dict
+  sentences:
+  - "def make_regex(separator):\n    \"\"\"Utility function to create regexp for matching\
+    \ escaped separators\n    in strings.\n\n    \"\"\"\n    return re.compile(r'(?:'\
+    \ + re.escape(separator) + r')?((?:[^' +\n                      re.escape(separator)\
+    \ + r'\\\\]|\\\\.)+)')"
+  - "def csvtolist(inputstr):\n    \"\"\" converts a csv string into a list \"\"\"\
+    \n    reader = csv.reader([inputstr], skipinitialspace=True)\n    output = []\n\
+    \    for r in reader:\n        output += r\n    return output"
+  - "def dict_merge(set1, set2):\n    \"\"\"Joins two dictionaries.\"\"\"\n    return\
+    \ dict(list(set1.items()) + list(set2.items()))"
+- source_sentence: python string % substitution float
+  sentences:
+  - "def _configure_logger():\n    \"\"\"Configure the logging module.\"\"\"\n   \
+    \ if not app.debug:\n        _configure_logger_for_production(logging.getLogger())\n\
+    \    elif not app.testing:\n        _configure_logger_for_debugging(logging.getLogger())"
+  - "def __set__(self, instance, value):\n        \"\"\" Set a related object for\
+    \ an instance. \"\"\"\n\n        self.map[id(instance)] = (weakref.ref(instance),\
+    \ value)"
+  - "def format_float(value): # not used\n    \"\"\"Modified form of the 'g' format\
+    \ specifier.\n    \"\"\"\n    string = \"{:g}\".format(value).replace(\"e+\",\
+    \ \"e\")\n    string = re.sub(\"e(-?)0*(\\d+)\", r\"e\\1\\2\", string)\n    return\
+    \ string"
+- source_sentence: bottom 5 rows in python
+  sentences:
+  - "def refresh(self, document):\n\t\t\"\"\" Load a new copy of a document from the\
+    \ database.  does not\n\t\t\treplace the old one \"\"\"\n\t\ttry:\n\t\t\told_cache_size\
+    \ = self.cache_size\n\t\t\tself.cache_size = 0\n\t\t\tobj = self.query(type(document)).filter_by(mongo_id=document.mongo_id).one()\n\
+    \t\tfinally:\n\t\t\tself.cache_size = old_cache_size\n\t\tself.cache_write(obj)\n\
+    \t\treturn obj"
+  - "def table_top_abs(self):\n        \"\"\"Returns the absolute position of table\
+    \ top\"\"\"\n        table_height = np.array([0, 0, self.table_full_size[2]])\n\
+    \        return string_to_array(self.floor.get(\"pos\")) + table_height"
+  - "def get_dimension_array(array):\n    \"\"\"\n    Get dimension of an array getting\
+    \ the number of rows and the max num of\n    columns.\n    \"\"\"\n    if all(isinstance(el,\
+    \ list) for el in array):\n        result = [len(array), len(max([x for x in array],\
+    \ key=len,))]\n\n    # elif array and isinstance(array, list):\n    else:\n  \
+    \      result = [len(array), 1]\n\n    return result"
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+---
+
+# SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2). It maps sentences & paragraphs to a 384-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:** [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) <!-- at revision c9745ed1d9f207416be6d2e6f8de32d1f16199bf -->
+- **Maximum Sequence Length:** 256 tokens
+- **Output Dimensionality:** 384 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/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': 256, 'do_lower_case': False, 'architecture': 'BertModel'})
+  (1): Pooling({'word_embedding_dimension': 384, '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})
+  (2): Normalize()
+)
+```
+
+## 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("Devy1/MiniLM-cosqa-512")
+# Run inference
+sentences = [
+    'bottom 5 rows in python',
+    'def table_top_abs(self):\n        """Returns the absolute position of table top"""\n        table_height = np.array([0, 0, self.table_full_size[2]])\n        return string_to_array(self.floor.get("pos")) + table_height',
+    'def refresh(self, document):\n\t\t""" Load a new copy of a document from the database.  does not\n\t\t\treplace the old one """\n\t\ttry:\n\t\t\told_cache_size = self.cache_size\n\t\t\tself.cache_size = 0\n\t\t\tobj = self.query(type(document)).filter_by(mongo_id=document.mongo_id).one()\n\t\tfinally:\n\t\t\tself.cache_size = old_cache_size\n\t\tself.cache_write(obj)\n\t\treturn obj',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities)
+# tensor([[ 1.0000,  0.4537, -0.0817],
+#         [ 0.4537,  1.0000, -0.0463],
+#         [-0.0817, -0.0463,  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.*
+-->
+
+<!--
+## 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: 9,020 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                           | positive                                                                            |
+  |:--------|:---------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                              |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 9.67 tokens</li><li>max: 21 tokens</li></ul> | <ul><li>min: 40 tokens</li><li>mean: 86.17 tokens</li><li>max: 256 tokens</li></ul> |
+* Samples:
+  | anchor                                                  | positive                                                                                                                                                                                                                                                                                                                                                                                                                      |
+  |:--------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>1d array in char datatype in python</code>        | <code>def _convert_to_array(array_like, dtype):<br>        """<br>        Convert Matrix attributes which are array-like or buffer to array.<br>        """<br>        if isinstance(array_like, bytes):<br>            return np.frombuffer(array_like, dtype=dtype)<br>        return np.asarray(array_like, dtype=dtype)</code>                                                                                            |
+  | <code>python condition non none</code>                  | <code>def _not(condition=None, **kwargs):<br>    """<br>    Return the opposite of input condition.<br><br>    :param condition: condition to process.<br><br>    :result: not condition.<br>    :rtype: bool<br>    """<br><br>    result = True<br><br>    if condition is not None:<br>        result = not run(condition, **kwargs)<br><br>    return result</code>                                                       |
+  | <code>accessing a column from a matrix in python</code> | <code>def get_column(self, X, column):<br>        """Return a column of the given matrix.<br><br>        Args:<br>            X: `numpy.ndarray` or `pandas.DataFrame`.<br>            column: `int` or `str`.<br><br>        Returns:<br>            np.ndarray: Selected column.<br>        """<br>        if isinstance(X, pd.DataFrame):<br>            return X[column].values<br><br>        return X[:, column]</code> |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim",
+      "gather_across_devices": false
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `per_device_train_batch_size`: 512
+- `fp16`: True
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: no
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 512
+- `per_device_eval_batch_size`: 8
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 5e-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`: 3
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.0
+- `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
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: True
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `parallelism_config`: None
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch_fused
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `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`: False
+- `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`: False
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+- `router_mapping`: {}
+- `learning_rate_mapping`: {}
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss |
+|:------:|:----:|:-------------:|
+| 0.0556 | 1    | 1.2259        |
+| 0.1111 | 2    | 1.1589        |
+| 0.1667 | 3    | 0.9588        |
+| 0.2222 | 4    | 1.0265        |
+| 0.2778 | 5    | 0.9783        |
+| 0.3333 | 6    | 0.9464        |
+| 0.3889 | 7    | 0.9527        |
+| 0.4444 | 8    | 0.969         |
+| 0.5    | 9    | 1.0237        |
+| 0.5556 | 10   | 1.0134        |
+| 0.6111 | 11   | 0.9297        |
+| 0.6667 | 12   | 0.9877        |
+| 0.7222 | 13   | 0.9531        |
+| 0.7778 | 14   | 0.9156        |
+| 0.8333 | 15   | 0.8613        |
+| 0.8889 | 16   | 0.83          |
+| 0.9444 | 17   | 0.8991        |
+| 1.0    | 18   | 0.6764        |
+| 1.0556 | 19   | 0.8545        |
+| 1.1111 | 20   | 0.7454        |
+| 1.1667 | 21   | 0.834         |
+| 1.2222 | 22   | 0.7625        |
+| 1.2778 | 23   | 0.7808        |
+| 1.3333 | 24   | 0.817         |
+| 1.3889 | 25   | 0.8032        |
+| 1.4444 | 26   | 0.7854        |
+| 1.5    | 27   | 0.7376        |
+| 1.5556 | 28   | 0.8346        |
+| 1.6111 | 29   | 0.8738        |
+| 1.6667 | 30   | 0.7524        |
+| 1.7222 | 31   | 0.72          |
+| 1.7778 | 32   | 0.711         |
+| 1.8333 | 33   | 0.7498        |
+| 1.8889 | 34   | 0.7597        |
+| 1.9444 | 35   | 0.7883        |
+| 2.0    | 36   | 0.5038        |
+| 2.0556 | 37   | 0.6932        |
+| 2.1111 | 38   | 0.7273        |
+| 2.1667 | 39   | 0.6723        |
+| 2.2222 | 40   | 0.7059        |
+| 2.2778 | 41   | 0.6159        |
+| 2.3333 | 42   | 0.809         |
+| 2.3889 | 43   | 0.6959        |
+| 2.4444 | 44   | 0.7881        |
+| 2.5    | 45   | 0.6861        |
+| 2.5556 | 46   | 0.6545        |
+| 2.6111 | 47   | 0.7235        |
+| 2.6667 | 48   | 0.7031        |
+| 2.7222 | 49   | 0.6679        |
+| 2.7778 | 50   | 0.6835        |
+| 2.8333 | 51   | 0.6773        |
+| 2.8889 | 52   | 0.6972        |
+| 2.9444 | 53   | 0.7043        |
+| 3.0    | 54   | 0.4647        |
+
+
+### Framework Versions
+- Python: 3.10.14
+- Sentence Transformers: 5.1.1
+- Transformers: 4.56.2
+- PyTorch: 2.8.0+cu128
+- Accelerate: 1.10.1
+- Datasets: 4.1.1
+- Tokenizers: 0.22.1
+
+## 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",
+}
+```
+
+#### 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 +1,25 @@
+{
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.56.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "sentence_transformers": "5.1.1",
+    "transformers": "4.56.2",
+    "pytorch": "2.8.0+cu128"
+  },
+  "model_type": "SentenceTransformer",
+  "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:c3cc6f61bd9bde7c0dabc2fc5ced1ba617d3b6d15d162273fecb9dd71fda7aad
+size 90864192

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 256,
+    "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 256,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}