Upload folder using huggingface_hub

.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": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -1,3 +1,526 @@
----
-license: mit
----
+---
+base_model: sentence-transformers/stsb-xlm-r-multilingual
+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:193860
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: ഓ, അതെ, ഞാൻ അവരെ കഴുത്ത് ഞെരിച്ച് കൊല്ലുമായിരുന്നു എന്ന ചിന്തയെക്കുറിച്ച്
+    വായിച്ചത് ഞാൻ ഓർക്കുന്നു.
+  sentences:
+  - A major privacy related disaster might be an exception.
+  - আমি এটি সম্পর্কে পড়েছি এবং ভেবেছিলাম যে আমাকে তাদের শ্বাসরোধ করতে হবে।
+  - How do you like it out there?
+- source_sentence: A male tennis player hits a tennis ball at a tennis match.
+  sentences:
+  - You can shower outside in nature with privacy.
+  - രണ്ട് കാറുകൾ ഓടുന്നു.
+  - একজন লোক টেনিস খেলছে।
+- source_sentence: ఒక గోధుమ మరియు తెలుపు కుక్క ఒక ఇంటి ప్రాంగణంలో ఆడుతోంది.
+  sentences:
+  - आँगन में एक कुत्ता खेल रहा है।
+  - तालप्रिय ग्वाडेलोपियन पर्यटकांच्या संख्येपेक्षा जास्त असतील.
+  - সবুজ পোশাকে কিছু মানুষ
+- source_sentence: A baby wearing a pink outfit with flowers on it has its mouth open.
+  sentences:
+  - बैठकीच्या खोलीच्या भिंती पांढऱ्या आहेत.
+  - a baby is in a pink outfit
+  - এটা ভালো হবে, কিন্তু আমি স্বাধীনতা উপভোগ করি।
+- source_sentence: A baby wearing a watch.
+  sentences:
+  - એક બાળક ઘડિયાળ પહેરી રહ્યું છે.
+  - एक बेसबॉल खिलाड़ी गेंद पर झूलता है।
+  - The mans legs are touching.
+model-index:
+- name: SentenceTransformer based on sentence-transformers/stsb-xlm-r-multilingual
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev
+      type: sts-dev
+    metrics:
+    - type: pearson_cosine
+      value: 0.8658165968626415
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8714077275778997
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8695576458225691
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8700925845327402
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8694747813672388
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8703633875862249
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.7735824081876905
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.7728637057026586
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8695576458225691
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8714077275778997
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test
+      type: sts-test
+    metrics:
+    - type: pearson_cosine
+      value: 0.8413454674808685
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8516557437790466
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8406890199541754
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8401478064056196
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8405040750844844
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8402979769379469
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.7261415217517116
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.7095416925344771
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8413454674808685
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8516557437790466
+      name: Spearman Max
+---
+
+# SentenceTransformer based on sentence-transformers/stsb-xlm-r-multilingual
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/stsb-xlm-r-multilingual](https://huggingface.co/sentence-transformers/stsb-xlm-r-multilingual). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [sentence-transformers/stsb-xlm-r-multilingual](https://huggingface.co/sentence-transformers/stsb-xlm-r-multilingual) <!-- at revision e33c331c9f771a2d5ee0b434a970d22281e3fc3e -->
+- **Maximum Sequence Length:** 128 tokens
+- **Output Dimensionality:** 768 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': 128, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'A baby wearing a watch.',
+    'એક બાળક ઘડિયાળ પહેરી રહ્યું છે.',
+    'The mans legs are touching.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# 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: `sts-dev`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.8658     |
+| **spearman_cosine** | **0.8714** |
+| pearson_manhattan   | 0.8696     |
+| spearman_manhattan  | 0.8701     |
+| pearson_euclidean   | 0.8695     |
+| spearman_euclidean  | 0.8704     |
+| pearson_dot         | 0.7736     |
+| spearman_dot        | 0.7729     |
+| pearson_max         | 0.8696     |
+| spearman_max        | 0.8714     |
+
+#### Semantic Similarity
+* Dataset: `sts-test`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.8413     |
+| **spearman_cosine** | **0.8517** |
+| pearson_manhattan   | 0.8407     |
+| spearman_manhattan  | 0.8401     |
+| pearson_euclidean   | 0.8405     |
+| spearman_euclidean  | 0.8403     |
+| pearson_dot         | 0.7261     |
+| spearman_dot        | 0.7095     |
+| pearson_max         | 0.8413     |
+| spearman_max        | 0.8517     |
+
+<!--
+## 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: 193,860 training samples
+* Columns: <code>query</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | query                                                                              | positive                                                                           | negative                                                                          |
+  |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                             | string                                                                            |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 26.96 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 14.19 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 14.86 tokens</li><li>max: 60 tokens</li></ul> |
+* Samples:
+  | query                                                                                                                                                                | positive                                                                                                      | negative                                                                                                  |
+  |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------|
+  | <code>Delos was not only an important religious center, but also a major meeting point for trade between East and West during the Hellenistic and Roman eras.</code> | <code>The East and West met at Delos to trade.</code>                                                         | <code>All of the buildings are open to visitors.</code>                                                   |
+  | <code>काळ्या रंगाचा शर्ट घातलेली एक स्त्री तिच्या उजवीकडे पाहते, तर तिच्या डाव्या बाजूला निळ्या रंगाची बनियान घातलेला एक माणूस काचेतून पाणी पितो.</code>             | <code>કાળા શર્ટમાં મહિલા તેના લખાણ તરફ જોઈ રહી હતી જ્યારે તેની બાજુના સજ્જન તેની તરસ છીપાવી રહ્યા હતા.</code> | <code>Armies of Cathar heretics and Roman church battled near Albi la Rouge.</code>                       |
+  | <code>કોંક્રિટ પગથિયા પર બેઠેલા ધાબળામાં વીંટાળેલા નાના બાળક સાથેનું દંપતી</code>                                                                                    | <code>సంబంధంలో ఉన్న ఇద్దరు వ్యక్తులు ఒక బిడ్డతో కూర్చున్నారు.</code>                                          | <code>যারা আইনি সহায়তা চাইছেন তাদের জন্য এনজেপি ইন্টারনেট ভিত্তিক সহায়তা এবং সহায়তা প্রদান করে।</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
+
+#### Unnamed Dataset
+
+
+* Size: 48,465 evaluation samples
+* Columns: <code>query</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | query                                                                              | positive                                                                           | negative                                                                          |
+  |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                             | string                                                                            |
+  | details | <ul><li>min: 5 tokens</li><li>mean: 27.21 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 14.41 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 14.52 tokens</li><li>max: 61 tokens</li></ul> |
+* Samples:
+  | query                                                                                                                                                                               | positive                                                                | negative                                                     |
+  |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------|:-------------------------------------------------------------|
+  | <code>काउबॉय टोपी और जींस पहने आदमी लकड़ी की इमारत के सामने खड़ा है।</code>                                                                                                         | <code>लाकडी इमारतीसमोर उभा असलेला एक माणूस.</code>                      | <code>ஒரு சூட் அணிந்த ஒரு மனிதர் தெருவைக் கடக்கிறார்.</code> |
+  | <code>7 The Malcolm Baldridge National Quality Award and the President's Quality Award are given to organizations for their overall achievements in quality and performance.</code> | <code>ఒక సంస్థ బాగా పనిచేస్తే, వారికి రెండు అవార్డులు లభిస్తాయి.</code> | <code>விட்டிங்டன் ஒரு வண்டியில் சவாரி செய்தார்.</code>       |
+  | <code>ఈ ఫుట్బాల్ జట్టు ఎరుపు చొక్కాలు మరియు ఎరుపు శిరస్త్రాణాలు ధరిస్తుంది.</code>                                                                                                  | <code>তারা ফুটবল খেলছে।</code>                                          | <code>एक आदमी मेट्रो में है।</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`: 128
+- `per_device_eval_batch_size`: 128
+- `num_train_epochs`: 1
+- `warmup_ratio`: 0.1
+- `bf16`: 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`: 128
+- `per_device_eval_batch_size`: 128
+- `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`: 1
+- `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`: True
+- `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`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | loss   | sts-dev_spearman_cosine | sts-test_spearman_cosine |
+|:------:|:----:|:-------------:|:------:|:-----------------------:|:------------------------:|
+| 0      | 0    | -             | -      | 0.8676                  | -                        |
+| 0.0660 | 50   | -             | 1.6688 | 0.8638                  | -                        |
+| 0.1319 | 100  | 1.9732        | 1.2907 | 0.8670                  | -                        |
+| 0.1979 | 150  | -             | 1.1554 | 0.8677                  | -                        |
+| 0.2639 | 200  | 1.266         | 1.0765 | 0.8671                  | -                        |
+| 0.3298 | 250  | -             | 1.0252 | 0.8674                  | -                        |
+| 0.3958 | 300  | 1.1386        | 0.9857 | 0.8662                  | -                        |
+| 0.4617 | 350  | -             | 0.9448 | 0.8680                  | -                        |
+| 0.5277 | 400  | 1.0391        | 0.9190 | 0.8700                  | -                        |
+| 0.5937 | 450  | -             | 0.8990 | 0.8685                  | -                        |
+| 0.6596 | 500  | 0.9889        | 0.8792 | 0.8696                  | -                        |
+| 0.7256 | 550  | -             | 0.8619 | 0.8719                  | -                        |
+| 0.7916 | 600  | 0.9574        | 0.8501 | 0.8724                  | -                        |
+| 0.8575 | 650  | -             | 0.8415 | 0.8724                  | -                        |
+| 0.9235 | 700  | 0.9253        | 0.8345 | 0.8722                  | -                        |
+| 0.9894 | 750  | -             | 0.8308 | 0.8714                  | -                        |
+| 1.0    | 758  | -             | -      | -                       | 0.8517                   |
+
+
+### Framework Versions
+- Python: 3.9.19
+- 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",
+}
+```
+
+#### 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 +1,29 @@
+{
+  "_name_or_path": "model",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "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": "4.44.2",
+    "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 sha256:43bba0a5a6c43b90d271cbc12018da5e5999e8b1de3fd24f1af38c9cadfa43fd
+size 1112197096

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": 128,
+  "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": false,
+    "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 sha256:6c2ccb33b55c4d157419a2105d6e033f7514c2baa6306471c56b86ab02787613
+size 17083053

tokenizer_config.json

@@ -0,0 +1,63 @@
+{
+  "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": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "full_tokenizer_file": null,
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 128,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}