Add new SentenceTransformer model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "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 +1,555 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:9316
+- loss:MultipleNegativesRankingLoss
+base_model: intfloat/multilingual-e5-large
+widget:
+- source_sentence: Horn band legwearis a type oflegwear, oftenthighhighs, with ahornedcharacter
+    design along the upper band.
+  sentences:
+  - horn band legwear
+  - head out of frame
+  - sweatpants
+- source_sentence: When a character is looping the laces of theiruntied shoelacesinto
+    a sturdy bow.
+  sentences:
+  - hair tie
+  - tying footwear
+  - loose necktie
+- source_sentence: Use this tag if the person's eyewear isremovedfrom their usual
+    place and carried in the hands. If it still rests on the bridge of the nose or
+    head, seeadjusting eyewearand its related tags.
+  sentences:
+  - cow costume
+  - sarong
+  - holding removed eyewear
+- source_sentence: When both of a character's hands are on another character'sthighs.
+  sentences:
+  - baking
+  - triplets
+  - hands on another's thighs
+- source_sentence: A long appendage protruding from the lower back. Often covered
+    in fur or scales. A common feature of animal girls.
+  sentences:
+  - tail
+  - grey-framed eyewear
+  - stomach day
+datasets:
+- meandyou200175/word_embedding
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy@1
+- cosine_accuracy@2
+- cosine_accuracy@5
+- cosine_accuracy@10
+- cosine_accuracy@100
+- cosine_precision@1
+- cosine_precision@2
+- cosine_precision@5
+- cosine_precision@10
+- cosine_precision@100
+- cosine_recall@1
+- cosine_recall@2
+- cosine_recall@5
+- cosine_recall@10
+- cosine_recall@100
+- cosine_ndcg@10
+- cosine_mrr@1
+- cosine_mrr@2
+- cosine_mrr@5
+- cosine_mrr@10
+- cosine_mrr@100
+- cosine_map@100
+model-index:
+- name: SentenceTransformer based on intfloat/multilingual-e5-large
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: Unknown
+      type: unknown
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.8108108108108109
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@2
+      value: 0.8957528957528957
+      name: Cosine Accuracy@2
+    - type: cosine_accuracy@5
+      value: 0.9382239382239382
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9642857142857143
+      name: Cosine Accuracy@10
+    - type: cosine_accuracy@100
+      value: 0.9932432432432432
+      name: Cosine Accuracy@100
+    - type: cosine_precision@1
+      value: 0.8108108108108109
+      name: Cosine Precision@1
+    - type: cosine_precision@2
+      value: 0.44787644787644787
+      name: Cosine Precision@2
+    - type: cosine_precision@5
+      value: 0.18764478764478765
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09642857142857143
+      name: Cosine Precision@10
+    - type: cosine_precision@100
+      value: 0.009932432432432433
+      name: Cosine Precision@100
+    - type: cosine_recall@1
+      value: 0.8108108108108109
+      name: Cosine Recall@1
+    - type: cosine_recall@2
+      value: 0.8957528957528957
+      name: Cosine Recall@2
+    - type: cosine_recall@5
+      value: 0.9382239382239382
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9642857142857143
+      name: Cosine Recall@10
+    - type: cosine_recall@100
+      value: 0.9932432432432432
+      name: Cosine Recall@100
+    - type: cosine_ndcg@10
+      value: 0.8923095558988695
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@1
+      value: 0.8108108108108109
+      name: Cosine Mrr@1
+    - type: cosine_mrr@2
+      value: 0.8532818532818532
+      name: Cosine Mrr@2
+    - type: cosine_mrr@5
+      value: 0.8649292149292154
+      name: Cosine Mrr@5
+    - type: cosine_mrr@10
+      value: 0.8687695348409635
+      name: Cosine Mrr@10
+    - type: cosine_mrr@100
+      value: 0.8700193430588538
+      name: Cosine Mrr@100
+    - type: cosine_map@100
+      value: 0.8700193430588539
+      name: Cosine Map@100
+---
+
+# SentenceTransformer based on intfloat/multilingual-e5-large
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large) on the [word_embedding](https://huggingface.co/datasets/meandyou200175/word_embedding) dataset. 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:** [intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large) <!-- at revision 0dc5580a448e4284468b8909bae50fa925907bc5 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 1024 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [word_embedding](https://huggingface.co/datasets/meandyou200175/word_embedding)
+<!-- - **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': False}) with Transformer model: XLMRobertaModel 
+  (1): Pooling({'word_embedding_dimension': 1024, '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("meandyou200175/e5_large_finetune_word")
+# Run inference
+sentences = [
+    'A long appendage protruding from the lower back. Often covered in fur or scales. A common feature of animal girls.',
+    'tail',
+    'stomach day',
+]
+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
+
+#### Information Retrieval
+
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric               | Value      |
+|:---------------------|:-----------|
+| cosine_accuracy@1    | 0.8108     |
+| cosine_accuracy@2    | 0.8958     |
+| cosine_accuracy@5    | 0.9382     |
+| cosine_accuracy@10   | 0.9643     |
+| cosine_accuracy@100  | 0.9932     |
+| cosine_precision@1   | 0.8108     |
+| cosine_precision@2   | 0.4479     |
+| cosine_precision@5   | 0.1876     |
+| cosine_precision@10  | 0.0964     |
+| cosine_precision@100 | 0.0099     |
+| cosine_recall@1      | 0.8108     |
+| cosine_recall@2      | 0.8958     |
+| cosine_recall@5      | 0.9382     |
+| cosine_recall@10     | 0.9643     |
+| cosine_recall@100    | 0.9932     |
+| **cosine_ndcg@10**   | **0.8923** |
+| cosine_mrr@1         | 0.8108     |
+| cosine_mrr@2         | 0.8533     |
+| cosine_mrr@5         | 0.8649     |
+| cosine_mrr@10        | 0.8688     |
+| cosine_mrr@100       | 0.87       |
+| cosine_map@100       | 0.87       |
+
+<!--
+## 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
+
+#### word_embedding
+
+* Dataset: [word_embedding](https://huggingface.co/datasets/meandyou200175/word_embedding) at [af76b11](https://huggingface.co/datasets/meandyou200175/word_embedding/tree/af76b11c1d93542ca76e864a60b1744d5e02b099)
+* Size: 9,316 training samples
+* Columns: <code>query</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | query                                                                              | positive                                                                        |
+  |:--------|:-----------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                          |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 36.54 tokens</li><li>max: 177 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 5.3 tokens</li><li>max: 13 tokens</li></ul> |
+* Samples:
+  | query                                                                                                                                           | positive                           |
+  |:------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------|
+  | <code>Eyewear shaped like a semicircle.</code>                                                                                                  | <code>semi-circular eyewear</code> |
+  | <code>A handheld electric appliance used fordryingand styling hair.</code>                                                                      | <code>hair dryer</code>            |
+  | <code>When onebreastis exposed while the other remains covered or confined by clothing. Seebreasts outfor when both breasts are exposed.</code> | <code>one breast out</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"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### word_embedding
+
+* Dataset: [word_embedding](https://huggingface.co/datasets/meandyou200175/word_embedding) at [af76b11](https://huggingface.co/datasets/meandyou200175/word_embedding/tree/af76b11c1d93542ca76e864a60b1744d5e02b099)
+* Size: 1,036 evaluation samples
+* Columns: <code>query</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | query                                                                              | positive                                                                         |
+  |:--------|:-----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                           |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 35.89 tokens</li><li>max: 164 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 5.38 tokens</li><li>max: 14 tokens</li></ul> |
+* Samples:
+  | query                                                                                                                                                                                                                                                                                         | positive                  |
+  |:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------|
+  | <code>A machine that manipulates data according to a list of instructions. The ability to store and execute lists of instructions called programs make computers extremely versatile. On Danbooru's images they are most often used fordrawing,playing gamesand accessing theinternet.</code> | <code>computer</code>     |
+  | <code>Aplaying cardwith twoclubs.</code>                                                                                                                                                                                                                                                      | <code>two of clubs</code> |
+  | <code>Yebisu (ヱビス, Ebisu) is a beer produced bySapporo Breweries. It is one of Japan's oldest brands, first being brewed in Tokyo in 1890 by the Japan Beer Brewery Company.</code>                                                                                                           | <code>yebisu</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"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 5
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `batch_sampler`: no_duplicates
+
+#### 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`: 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`: 5
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `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}
+- `tp_size`: 0
+- `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`: None
+- `hub_always_push`: False
+- `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
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | Validation Loss | cosine_ndcg@10 |
+|:------:|:----:|:-------------:|:---------------:|:--------------:|
+| -1     | -1   | -             | -               | 0.7166         |
+| 0.1715 | 100  | 0.8892        | -               | -              |
+| 0.3431 | 200  | 0.1724        | -               | -              |
+| 0.5146 | 300  | 0.1783        | -               | -              |
+| 0.6861 | 400  | 0.1393        | -               | -              |
+| 0.8576 | 500  | 0.1262        | -               | -              |
+| 1.0292 | 600  | 0.1046        | -               | -              |
+| 1.2007 | 700  | 0.0639        | -               | -              |
+| 1.3722 | 800  | 0.0692        | -               | -              |
+| 1.5437 | 900  | 0.043         | -               | -              |
+| 1.7153 | 1000 | 0.0614        | 0.0819          | 0.8774         |
+| 1.8868 | 1100 | 0.0538        | -               | -              |
+| 2.0583 | 1200 | 0.0414        | -               | -              |
+| 2.2298 | 1300 | 0.0146        | -               | -              |
+| 2.4014 | 1400 | 0.0164        | -               | -              |
+| 2.5729 | 1500 | 0.0225        | -               | -              |
+| 2.7444 | 1600 | 0.0215        | -               | -              |
+| 2.9160 | 1700 | 0.0271        | -               | -              |
+| 3.0875 | 1800 | 0.0202        | -               | -              |
+| 3.2590 | 1900 | 0.0194        | -               | -              |
+| 3.4305 | 2000 | 0.0144        | 0.0682          | 0.8923         |
+| 3.6021 | 2100 | 0.0118        | -               | -              |
+| 3.7736 | 2200 | 0.0155        | -               | -              |
+| 3.9451 | 2300 | 0.0177        | -               | -              |
+| 4.1166 | 2400 | 0.0059        | -               | -              |
+| 4.2882 | 2500 | 0.0099        | -               | -              |
+| 4.4597 | 2600 | 0.0056        | -               | -              |
+| 4.6312 | 2700 | 0.0153        | -               | -              |
+| 4.8027 | 2800 | 0.0069        | -               | -              |
+| 4.9743 | 2900 | 0.01          | -               | -              |
+
+
+### Framework Versions
+- Python: 3.11.11
+- Sentence Transformers: 3.4.1
+- Transformers: 4.51.1
+- PyTorch: 2.5.1+cu124
+- Accelerate: 1.3.0
+- Datasets: 3.5.0
+- Tokenizers: 0.21.0
+
+## 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 +1,27 @@
+{
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.51.1",
+    "pytorch": "2.5.1+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24854dafae65ef24432ea85eb056628daff94e85bcb8d60730361305c68126c1
+size 2239607176

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": 512,
+  "do_lower_case": false
+}

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:883b037111086fd4dfebbbc9b7cee11e1517b5e0c0514879478661440f137085
+size 17082987

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}