Add new SentenceTransformer model.

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "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 +1,531 @@
+---
+base_model: llmrails/ember-v1
+datasets: []
+language: []
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+- pearson_manhattan
+- spearman_manhattan
+- pearson_euclidean
+- spearman_euclidean
+- pearson_dot
+- spearman_dot
+- pearson_max
+- spearman_max
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:17500
+- loss:ContrastiveLoss
+widget:
+- source_sentence: 260 Mount Prospect Apt A4
+  sentences:
+  - 254 Mount Apt 304
+  - '110 Nightin - Gale #10'
+  - 3100 35 Apt 2
+- source_sentence: '20 Harding #2'
+  sentences:
+  - '1208 Barclay #2'
+  - '65 Chestnut # 72'
+  - '20 Harding # 2'
+- source_sentence: 396 Manila Apt 2B
+  sentences:
+  - 108 Gaston 1
+  - '175 2nd #710'
+  - '1 - 02 Virginia #102B'
+- source_sentence: '210 Gordon Fl #1'
+  sentences:
+  - 450 Raritan Ste C
+  - '19 Edsall #1'
+  - '210 Gordon # 1'
+- source_sentence: '148 1 / 2 Mill #B'
+  sentences:
+  - '7918 Pershing #'
+  - '91 5th #1'
+  - 148 1 / 2 Mill Apt B
+model-index:
+- name: SentenceTransformer based on llmrails/ember-v1
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: test
+      type: test
+    metrics:
+    - type: pearson_cosine
+      value: 0.7022202945624949
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.5521115900667813
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.5902198760799219
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.5601831188247873
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.5899864734850421
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.5598213668477258
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.5811885721377421
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.45745466821334696
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.7022202945624949
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.5601831188247873
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: validation
+      type: validation
+    metrics:
+    - type: pearson_cosine
+      value: 0.9438614062035536
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.6566095423715015
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.9661648909940331
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.6545897461863388
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.9662831349240031
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.6545799233453334
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.7832494697144132
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.6240051940767
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.9662831349240031
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.6566095423715015
+      name: Spearman Max
+---
+
+# SentenceTransformer based on llmrails/ember-v1
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [llmrails/ember-v1](https://huggingface.co/llmrails/ember-v1). It maps sentences & paragraphs to a 1024-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:** [llmrails/ember-v1](https://huggingface.co/llmrails/ember-v1) <!-- at revision 5e5ce5904901f6ce1c353a95020f17f09e5d021d -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 1024 tokens
+- **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': 512, 'do_lower_case': True}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, '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("jarredparrett/fine-tuned-address-model-ember-v1")
+# Run inference
+sentences = [
+    '148 1 / 2 Mill #B',
+    '148 1 / 2 Mill Apt B',
+    '7918 Pershing #',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 1024]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### 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
+
+#### Semantic Similarity
+* Dataset: `test`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric             | Value      |
+|:-------------------|:-----------|
+| pearson_cosine     | 0.7022     |
+| spearman_cosine    | 0.5521     |
+| pearson_manhattan  | 0.5902     |
+| spearman_manhattan | 0.5602     |
+| pearson_euclidean  | 0.59       |
+| spearman_euclidean | 0.5598     |
+| pearson_dot        | 0.5812     |
+| spearman_dot       | 0.4575     |
+| pearson_max        | 0.7022     |
+| **spearman_max**   | **0.5602** |
+
+#### Semantic Similarity
+* Dataset: `validation`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric             | Value      |
+|:-------------------|:-----------|
+| pearson_cosine     | 0.9439     |
+| spearman_cosine    | 0.6566     |
+| pearson_manhattan  | 0.9662     |
+| spearman_manhattan | 0.6546     |
+| pearson_euclidean  | 0.9663     |
+| spearman_euclidean | 0.6546     |
+| pearson_dot        | 0.7832     |
+| spearman_dot       | 0.624      |
+| pearson_max        | 0.9663     |
+| **spearman_max**   | **0.6566** |
+
+<!--
+## 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: 17,500 training samples
+* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence_0                                                                       | sentence_1                                                                       | label                                           |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                           | string                                                                           | int                                             |
+  | details | <ul><li>min: 5 tokens</li><li>mean: 6.97 tokens</li><li>max: 12 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 6.96 tokens</li><li>max: 12 tokens</li></ul> | <ul><li>0: ~17.80%</li><li>1: ~82.20%</li></ul> |
+* Samples:
+  | sentence_0                      | sentence_1                          | label          |
+  |:--------------------------------|:------------------------------------|:---------------|
+  | <code>94 Liberty 1</code>       | <code>94 Liberty Flr 1</code>       | <code>1</code> |
+  | <code>166 Randolph Apt 1</code> | <code>166 Randolph Flr 1</code>     | <code>1</code> |
+  | <code>400 Dutch Apt E12</code>  | <code>400 Dutch Neck Apt E12</code> | <code>1</code> |
+* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
+  ```json
+  {
+      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
+      "margin": 0.5,
+      "size_average": true
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `num_train_epochs`: 4
+- `multi_dataset_batch_sampler`: round_robin
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `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`: 4
+- `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`: 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}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `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`: False
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `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
+- `dispatch_batches`: None
+- `split_batches`: 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
+- `eval_use_gather_object`: False
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | test_spearman_max | validation_spearman_max |
+|:------:|:----:|:-------------:|:-----------------:|:-----------------------:|
+| 0      | 0    | -             | 0.5602            | -                       |
+| 0.0914 | 100  | -             | -                 | 0.6565                  |
+| 0.1828 | 200  | -             | -                 | 0.6567                  |
+| 0.2742 | 300  | -             | -                 | 0.6558                  |
+| 0.3656 | 400  | -             | -                 | 0.6560                  |
+| 0.4570 | 500  | 0.0039        | -                 | 0.6560                  |
+| 0.5484 | 600  | -             | -                 | 0.6555                  |
+| 0.6399 | 700  | -             | -                 | 0.6559                  |
+| 0.7313 | 800  | -             | -                 | 0.6561                  |
+| 0.8227 | 900  | -             | -                 | 0.6555                  |
+| 0.9141 | 1000 | 0.0019        | -                 | 0.6558                  |
+| 1.0    | 1094 | -             | -                 | 0.6560                  |
+| 1.0055 | 1100 | -             | -                 | 0.6561                  |
+| 1.0969 | 1200 | -             | -                 | 0.6560                  |
+| 1.1883 | 1300 | -             | -                 | 0.6559                  |
+| 1.2797 | 1400 | -             | -                 | 0.6555                  |
+| 1.3711 | 1500 | 0.0014        | -                 | 0.6558                  |
+| 1.4625 | 1600 | -             | -                 | 0.6560                  |
+| 1.5539 | 1700 | -             | -                 | 0.6557                  |
+| 1.6453 | 1800 | -             | -                 | 0.6561                  |
+| 1.7367 | 1900 | -             | -                 | 0.6561                  |
+| 1.8282 | 2000 | 0.001         | -                 | 0.6562                  |
+| 1.9196 | 2100 | -             | -                 | 0.6563                  |
+| 2.0    | 2188 | -             | -                 | 0.6564                  |
+| 2.0110 | 2200 | -             | -                 | 0.6565                  |
+| 2.1024 | 2300 | -             | -                 | 0.6565                  |
+| 2.1938 | 2400 | -             | -                 | 0.6560                  |
+| 2.2852 | 2500 | 0.0009        | -                 | 0.6557                  |
+| 2.3766 | 2600 | -             | -                 | 0.6559                  |
+| 2.4680 | 2700 | -             | -                 | 0.6560                  |
+| 2.5594 | 2800 | -             | -                 | 0.6560                  |
+| 2.6508 | 2900 | -             | -                 | 0.6564                  |
+| 2.7422 | 3000 | 0.0007        | -                 | 0.6565                  |
+| 2.8336 | 3100 | -             | -                 | 0.6565                  |
+| 2.9250 | 3200 | -             | -                 | 0.6564                  |
+| 3.0    | 3282 | -             | -                 | 0.6565                  |
+| 3.0165 | 3300 | -             | -                 | 0.6566                  |
+| 3.1079 | 3400 | -             | -                 | 0.6568                  |
+| 3.1993 | 3500 | 0.0007        | -                 | 0.6565                  |
+| 3.2907 | 3600 | -             | -                 | 0.6563                  |
+| 3.3821 | 3700 | -             | -                 | 0.6564                  |
+| 3.4735 | 3800 | -             | -                 | 0.6565                  |
+| 3.5649 | 3900 | -             | -                 | 0.6565                  |
+| 3.6563 | 4000 | 0.0005        | -                 | 0.6566                  |
+| 3.7477 | 4100 | -             | -                 | 0.6566                  |
+| 3.8391 | 4200 | -             | -                 | 0.6566                  |
+| 3.9305 | 4300 | -             | -                 | 0.6566                  |
+| 4.0    | 4376 | -             | -                 | 0.6566                  |
+
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.1
+- Transformers: 4.44.2
+- PyTorch: 2.4.0+cu121
+- Accelerate: 0.33.0
+- Datasets: 2.21.0
+- Tokenizers: 0.19.1
+
+## 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",
+}
+```
+
+#### ContrastiveLoss
+```bibtex
+@inproceedings{hadsell2006dimensionality,
+    author={Hadsell, R. and Chopra, S. and LeCun, Y.},
+    booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)}, 
+    title={Dimensionality Reduction by Learning an Invariant Mapping}, 
+    year={2006},
+    volume={2},
+    number={},
+    pages={1735-1742},
+    doi={10.1109/CVPR.2006.100}
+}
+```
+
+<!--
+## 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 +1,32 @@
+{
+  "_name_or_path": "llmrails/ember-v1",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.44.2",
+    "pytorch": "2.4.0+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ae8985e4d849f850ac8b62bccca94c2de3626635daa446053ead54708fdea3a
+size 1340612432

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": true
+}

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 +1,64 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "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]"
+}