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 +1,418 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dense
+- generated_from_trainer
+- dataset_size:9984
+- loss:MultipleNegativesRankingLoss
+base_model: sentence-transformers/all-MiniLM-L6-v2
+widget:
+- source_sentence: python to dict if only one item
+  sentences:
+  - "def get_from_gnucash26_date(date_str: str) -> date:\n    \"\"\" Creates a datetime\
+    \ from GnuCash 2.6 date string \"\"\"\n    date_format = \"%Y%m%d\"\n    result\
+    \ = datetime.strptime(date_str, date_format).date()\n    return result"
+  - "def multidict_to_dict(d):\n    \"\"\"\n    Turns a werkzeug.MultiDict or django.MultiValueDict\
+    \ into a dict with\n    list values\n    :param d: a MultiDict or MultiValueDict\
+    \ instance\n    :return: a dict instance\n    \"\"\"\n    return dict((k, v[0]\
+    \ if len(v) == 1 else v) for k, v in iterlists(d))"
+  - "def wipe_table(self, table: str) -> int:\n        \"\"\"Delete all records from\
+    \ a table. Use caution!\"\"\"\n        sql = \"DELETE FROM \" + self.delimit(table)\n\
+    \        return self.db_exec(sql)"
+- source_sentence: how to add a string to a filename in python
+  sentences:
+  - "def html_to_text(content):\n    \"\"\" Converts html content to plain text \"\
+    \"\"\n    text = None\n    h2t = html2text.HTML2Text()\n    h2t.ignore_links =\
+    \ False\n    text = h2t.handle(content)\n    return text"
+  - "def _get_column_by_db_name(cls, name):\n        \"\"\"\n        Returns the column,\
+    \ mapped by db_field name\n        \"\"\"\n        return cls._columns.get(cls._db_map.get(name,\
+    \ name))"
+  - "def add_suffix(fullname, suffix):\n    \"\"\" Add suffix to a full file name\"\
+    \"\"\n    name, ext = os.path.splitext(fullname)\n    return name + '_' + suffix\
+    \ + ext"
+- source_sentence: human readable string of object python
+  sentences:
+  - "def pretty(obj, verbose=False, max_width=79, newline='\\n'):\n    \"\"\"\n  \
+    \  Pretty print the object's representation.\n    \"\"\"\n    stream = StringIO()\n\
+    \    printer = RepresentationPrinter(stream, verbose, max_width, newline)\n  \
+    \  printer.pretty(obj)\n    printer.flush()\n    return stream.getvalue()"
+  - "def asMaskedArray(self):\n        \"\"\" Creates converts to a masked array\n\
+    \        \"\"\"\n        return ma.masked_array(data=self.data, mask=self.mask,\
+    \ fill_value=self.fill_value)"
+  - "def list_depth(list_, func=max, _depth=0):\n    \"\"\"\n    Returns the deepest\
+    \ level of nesting within a list of lists\n\n    Args:\n       list_  : a nested\
+    \ listlike object\n       func   : depth aggregation strategy (defaults to max)\n\
+    \       _depth : internal var\n\n    Example:\n        >>> # ENABLE_DOCTEST\n\
+    \        >>> from utool.util_list import *  # NOQA\n        >>> list_ = [[[[[1]]],\
+    \ [3]], [[1], [3]], [[1], [3]]]\n        >>> result = (list_depth(list_, _depth=0))\n\
+    \        >>> print(result)\n\n    \"\"\"\n    depth_list = [list_depth(item, func=func,\
+    \ _depth=_depth + 1)\n                  for item in  list_ if util_type.is_listlike(item)]\n\
+    \    if len(depth_list) > 0:\n        return func(depth_list)\n    else:\n   \
+    \     return _depth"
+- source_sentence: python parse query param
+  sentences:
+  - "def read_las(source, closefd=True):\n    \"\"\" Entry point for reading las data\
+    \ in pylas\n\n    Reads the whole file into memory.\n\n    >>> las = read_las(\"\
+    pylastests/simple.las\")\n    >>> las.classification\n    array([1, 1, 1, ...,\
+    \ 1, 1, 1], dtype=uint8)\n\n    Parameters\n    ----------\n    source : str or\
+    \ io.BytesIO\n        The source to read data from\n\n    closefd: bool\n    \
+    \        if True and the source is a stream, the function will close it\n    \
+    \        after it is done reading\n\n\n    Returns\n    -------\n    pylas.lasdatas.base.LasBase\n\
+    \        The object you can interact with to get access to the LAS points & VLRs\n\
+    \    \"\"\"\n    with open_las(source, closefd=closefd) as reader:\n        return\
+    \ reader.read()"
+  - "def parse_query_string(query):\n    \"\"\"\n    parse_query_string:\n    very\
+    \ simplistic. won't do the right thing with list values\n    \"\"\"\n    result\
+    \ = {}\n    qparts = query.split('&')\n    for item in qparts:\n        key, value\
+    \ = item.split('=')\n        key = key.strip()\n        value = value.strip()\n\
+    \        result[key] = unquote_plus(value)\n    return result"
+  - "def _clean_dict(target_dict, whitelist=None):\n    \"\"\" Convenience function\
+    \ that removes a dicts keys that have falsy values\n    \"\"\"\n    assert isinstance(target_dict,\
+    \ dict)\n    return {\n        ustr(k).strip(): ustr(v).strip()\n        for k,\
+    \ v in target_dict.items()\n        if v not in (None, Ellipsis, [], (), \"\"\
+    )\n        and (not whitelist or k in whitelist)\n    }"
+- source_sentence: python automatic figure out encoding
+  sentences:
+  - "def get_best_encoding(stream):\n    \"\"\"Returns the default stream encoding\
+    \ if not found.\"\"\"\n    rv = getattr(stream, 'encoding', None) or sys.getdefaultencoding()\n\
+    \    if is_ascii_encoding(rv):\n        return 'utf-8'\n    return rv"
+  - "def is_natural(x):\n    \"\"\"A non-negative integer.\"\"\"\n    try:\n     \
+    \   is_integer = int(x) == x\n    except (TypeError, ValueError):\n        return\
+    \ False\n    return is_integer and x >= 0"
+  - "def _tool_to_dict(tool):\n    \"\"\"Parse a tool definition into a cwl2wdl style\
+    \ dictionary.\n    \"\"\"\n    out = {\"name\": _id_to_name(tool.tool[\"id\"]),\n\
+    \           \"baseCommand\": \" \".join(tool.tool[\"baseCommand\"]),\n       \
+    \    \"arguments\": [],\n           \"inputs\": [_input_to_dict(i) for i in tool.tool[\"\
+    inputs\"]],\n           \"outputs\": [_output_to_dict(o) for o in tool.tool[\"\
+    outputs\"]],\n           \"requirements\": _requirements_to_dict(tool.requirements\
+    \ + tool.hints),\n           \"stdin\": None, \"stdout\": None}\n    return out"
+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/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': 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("Narekatsy/fine-tuned-cosqa")
+# Run inference
+sentences = [
+    'python automatic figure out encoding',
+    'def get_best_encoding(stream):\n    """Returns the default stream encoding if not found."""\n    rv = getattr(stream, \'encoding\', None) or sys.getdefaultencoding()\n    if is_ascii_encoding(rv):\n        return \'utf-8\'\n    return rv',
+    'def _tool_to_dict(tool):\n    """Parse a tool definition into a cwl2wdl style dictionary.\n    """\n    out = {"name": _id_to_name(tool.tool["id"]),\n           "baseCommand": " ".join(tool.tool["baseCommand"]),\n           "arguments": [],\n           "inputs": [_input_to_dict(i) for i in tool.tool["inputs"]],\n           "outputs": [_output_to_dict(o) for o in tool.tool["outputs"]],\n           "requirements": _requirements_to_dict(tool.requirements + tool.hints),\n           "stdin": None, "stdout": None}\n    return out',
+]
+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,  0.6173,  0.1376],
+#         [ 0.6173,  1.0000, -0.0456],
+#         [ 0.1376, -0.0456,  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: 9,984 training samples
+* Columns: <code>sentence_0</code> and <code>sentence_1</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence_0                                                                       | sentence_1                                                                          |
+  |:--------|:---------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                              |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 9.69 tokens</li><li>max: 24 tokens</li></ul> | <ul><li>min: 39 tokens</li><li>mean: 87.33 tokens</li><li>max: 256 tokens</li></ul> |
+* Samples:
+  | sentence_0                                              | sentence_1                                                                                                                                                                                                                                                                                                                                                                                                                   |
+  |:--------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>how to zip files to directory in python</code>    | <code>def unzip_file_to_dir(path_to_zip, output_directory):<br>    """<br>    Extract a ZIP archive to a directory<br>    """<br>    z = ZipFile(path_to_zip, 'r')<br>    z.extractall(output_directory)<br>    z.close()</code>                                                                                                                                                                                             |
+  | <code>mnist multi gpu training python tensorflow</code> | <code>def transformer_tall_pretrain_lm_tpu_adafactor():<br>  """Hparams for transformer on LM pretraining (with 64k vocab) on TPU."""<br>  hparams = transformer_tall_pretrain_lm()<br>  update_hparams_for_tpu(hparams)<br>  hparams.max_length = 1024<br>  # For multi-problem on TPU we need it in absolute examples.<br>  hparams.batch_size = 8<br>  hparams.multiproblem_vocab_size = 2**16<br>  return hparams</code> |
+  | <code>get file name without extension in python</code>  | <code>def remove_ext(fname):<br>    """Removes the extension from a filename<br>    """<br>    bn = os.path.basename(fname)<br>    return os.path.splitext(bn)[0]</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`: 32
+- `per_device_eval_batch_size`: 32
+- `num_train_epochs`: 2
+- `multi_dataset_batch_sampler`: round_robin
+
+#### 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`: 32
+- `per_device_eval_batch_size`: 32
+- `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
+- `num_train_epochs`: 2
+- `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
+- `bf16`: False
+- `fp16`: False
+- `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
+- `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`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+- `router_mapping`: {}
+- `learning_rate_mapping`: {}
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss |
+|:------:|:----:|:-------------:|
+| 1.6026 | 500  | 0.1512        |
+
+
+### Framework Versions
+- Python: 3.11.3
+- Sentence Transformers: 5.1.2
+- Transformers: 4.57.1
+- PyTorch: 2.9.0+cpu
+- Accelerate: 1.11.0
+- Datasets: 4.4.1
+- 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": "4.57.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "sentence_transformers": "5.1.2",
+    "transformers": "4.57.1",
+    "pytorch": "2.9.0+cpu"
+  },
+  "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:b22034c3d5ea67bd613cff69ab219db0a5cedc5bbf13e13aff9d9eedb770e0a1
+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]"
+}