Add new SentenceTransformer model.

.gitattributes

@@ -33,3 +33,5 @@ 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
+unigram.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "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 +1,385 @@
+---
+base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+datasets: []
+language: []
+library_name: sentence-transformers
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:64000
+- loss:DenoisingAutoEncoderLoss
+widget:
+- source_sentence: 𑀟चन𑀙𑀢𑀟 𑀞च𑀪च𑀠च 𑀫𑁣प𑁣 𑀞न𑀠च 𑀞𑁣𑀱च ब𑀢𑀪𑀠च𑀯
+  sentences:
+  - '  णच ब𑀢𑀪𑀠च पच𑀪𑁦 𑀣च 𑀠च𑀫च𑀢𑀲𑀢णच𑀪𑀳च 𑀣च झच𑀟𑁦𑀟𑀳च ञचणच𑀦 𑀞च𑀠च𑀪 णच𑀣𑀣च 𑀠च𑀫च𑀢𑀲𑀢𑀟𑀳च णच ढच𑀪
+    𑀢णचल𑀢𑀯'
+  - ' 𑀣च𑀟बच𑀟𑁦 𑀣च 𑀟चन𑀙𑀢𑀟 𑀠𑁣पच𑀪𑀦 पच𑀟च 𑀢णच 𑀤च𑀠च ढचढढच 𑀞𑁣 𑀞च𑀪च𑀠च 𑀢𑀣च𑀟 च𑀞च 𑀞𑀱चपच𑀟पच 𑀣च
+    𑀠𑁣पच𑀪 𑀣चन𑀞च𑀪 𑀫𑁣प𑁣 𑀣च 𑀳नख𑀦 𑀞न𑀠च णच 𑀲𑀢 𑀟च 𑀞𑁣𑀱च ब𑀢𑀪𑀠च𑀯'
+  - पच𑀪𑁦𑀠𑀢 णच ढनबच 𑀱च झन𑀟ब𑀢णच𑀪 झ𑀱चलल𑁣𑀟 झच𑀲च पच ञचल𑀢ढ𑀢𑀟 झच𑀳च𑀪 𑀢𑀪च𑀟 च बच𑀳च𑀪 पन𑀪𑀞𑀢णणच
+    𑀞न𑀠च णच त𑀢 𑀱च झन𑀟ब𑀢णच𑀪 𑀞𑀱चललचण𑁦 थ𑀯
+- source_sentence: णच𑀟च बचढच 𑀣च लन𑀪च 𑀣च 𑀣च पच 𑀲𑀢 𑀣च
+  sentences:
+  - 𑀘𑁣𑀫𑀟 𑀠𑀢त𑀫च𑁦ल 𑁣ब𑀢𑀣𑀢 𑀝च𑀟 𑀫च𑀢𑀲𑁦𑀳𑀫𑀢 𑀪च𑀟च𑀪 𑀗 बच 𑀱चपच𑀟 𑀣𑀢𑀳च𑀠ढच𑀦 𑀭थ𑀖थ𑀮𑀯
+  - ' 𑀱च𑀟𑀟च𑀟 णच𑀟च पच𑀢𑀠च𑀞च 𑀱च झ𑀱च𑀪च𑀪𑀪न𑀟 𑀫𑀪 𑀳न त𑀢 बचढच 𑀣च लन𑀪च 𑀣च 𑀣न𑀞 ढनञचञञ𑁦𑀟 चणणन𑀞च𑀟𑀳न
+    𑀣च 𑀠च𑀳न 𑀟𑁦𑀠च पच 𑀫च𑀟णच𑀪 𑀣च पच 𑀲𑀢 𑀳चन𑀪𑀢 𑀣च 𑀳चनझ𑀢 𑀲𑀢ण𑁦 𑀣च 𑀣च𑀯'
+  - ' च 𑀞च𑀪𑀞च𑀳𑀫𑀢𑀟 𑀣𑁣𑀞च𑀪𑀦 𑀠च𑀘चल𑀢𑀳च𑀪 लचनण𑁣ण𑀢𑀟 𑀢𑀟𑀣𑀢णच 𑀢पच त𑁦 ढचढढच𑀪 𑀫न𑀞न𑀠च𑀪 𑀞नलच 𑀣च 𑀫च𑀪𑀞𑁣𑀞𑀢𑀟
+    𑀳𑀫च𑀪𑀢𑀙च च 𑀢𑀟𑀣𑀢णच 𑀣च 𑀞न𑀠च पचढढचपच𑀪 𑀣च ढ𑀢𑀟 𑀣𑁣𑀞च 𑀣च 𑀞𑀢णचण𑁦 𑀞च𑀙𑀢𑀣𑁣𑀘𑀢𑀟 𑀞𑀱च𑀪च𑀪𑀪न पच
+    𑀫च𑀟णच𑀪 𑀞𑀱च𑀪च𑀪𑀪न𑀟 लचनणच च 𑀞च𑀳च𑀪𑀯'
+- source_sentence: 𑀣नढच ढढत𑀕 𑀠च𑀠च𑀪 चलचप𑁣न𑀠𑀢
+  sentences:
+  - 𑀣नढच 𑀞न𑀠च  𑀣𑁦𑀟𑀞ष𑀣𑁦𑀟𑀞𑀠च𑀟च𑀤च𑀪पच  ढढत𑀕 𑀠च𑀠च𑀪 𑀞च𑀳𑀳𑁦ण चलचप𑁣न𑀠𑀢 𑀯
+  - '  च𑀟 𑀲च𑀪च 𑀳च𑀠च𑀪𑀱च 𑀞न𑀠च 𑀣चबच ढचणच च𑀟 𑀲च𑀣च𑀣च चणणन𑀞च𑀟 बच 𑀳चन𑀪च𑀟 𑀢णचलच𑀢 𑀟च 𑀟च𑀘𑁦𑀪𑀢णच
+    𑀠च𑀳न णच𑀪च𑀯'
+  - '    𑀫च𑁥च𑀞च च𑀤चढपच𑀪𑀱च णच𑀟च 𑀣च 𑀱च𑀫चलच 𑀠न𑀳च𑀠𑀠च𑀟 च त𑀢𑀞𑀢𑀟 चणणन𑀞च𑀟 णचझ𑀢 𑀣च पच𑀱चबच𑀪𑀯'
+- source_sentence: च𑀟
+  sentences:
+  - 𑀠नपन𑀱च च 𑀪च𑀟च𑀪 र बच 𑀱चपच𑀟 𑀠चणन𑀟 ठ𑀧𑀧ठ𑀦 च𑀞न 𑀟च त𑀢𑀞𑀢𑀟 𑀲च𑀳𑀢𑀟𑀘𑁣𑀘𑀢 𑀬𑀧 𑀣च 𑀞𑁦 त𑀢𑀞𑀢𑀟 𑀱च𑀟𑀢
+    𑀘𑀢𑀪ब𑀢𑀟 𑀣च णच ण𑀢 𑀫चप𑀳च𑀪𑀢𑀟 𑀠𑀢𑀟पन𑀟च 𑀞चञच𑀟 ढचणच𑀟 पच𑀳𑀫𑀢𑀟𑀳च च 𑀞च𑀟𑁣𑀯
+  - '  च𑀟 ण𑀢 𑀢𑀠च𑀟𑀢𑀟 𑀳𑀯'
+  - ' 𑀲च𑀫च𑀣 णच 𑀞च𑀠𑀠चलच 𑀞च𑀞च𑀪 ठ𑀧𑀭ठट𑀭𑀰 𑀣च 𑀞𑀱चललचण𑁦 𑀭𑀧 𑀠च𑀳न ढच𑀟 𑀳𑀫च𑀙च𑀱च च 𑀱च𑀳च𑀟𑀟𑀢 ठ𑁢
+    च 𑀣न𑀞 बच𑀳च𑀯'
+- source_sentence: ब𑀫𑁣𑀳प 𑀢𑀢 𑀳𑀫𑀢𑀟𑁦 𑀠च𑀲𑀢 𑀠च𑀫𑀢𑀠𑀠च𑀟त𑀢𑀦 पच𑀢𑀠च𑀞𑁣𑀟 𑀣च 𑀲च𑀳चलनललन𑀞च णच𑀟च ढच
+    𑀠च𑀤चन𑀟च त𑀢𑀞𑀢𑀟 𑀫च𑀟𑀞चल𑀢 णचण𑀢𑀟
+  sentences:
+  - च𑀠𑀢𑀟पचतत𑀢णच च त𑀢𑀞𑀢𑀟 ब𑀫𑁣𑀳प 𑀳𑁦𑀪𑀢𑁦𑀳 𑀢𑀢 𑀳𑀫𑀢𑀟𑁦 𑀠च𑀲𑀢 𑀠च𑀫𑀢𑀠𑀠च𑀟त𑀢𑀦 पच𑀪𑁦 𑀣च ��𑀢𑀠ढ𑀢𑀟 𑀢𑀟बच𑀟पचपपन𑀟
+    प𑀳च𑀪𑀢𑀟 पच𑀢𑀠च𑀞𑁣𑀟 𑀣𑀢𑀪𑁦ढच 𑀣च 𑀲च𑀳चलनललन𑀞च 𑀟च च𑀠𑀢𑀟त𑀢𑀦 णच𑀟च ढच 𑀠च𑀤चन𑀟च त𑀢𑀞𑀢𑀟 𑀞𑀱च𑀟त𑀢णच𑀪
+    𑀫च𑀟𑀞चल𑀢 णचण𑀢𑀟 पच𑀲𑀢णच𑀪𑀳न𑀯
+  - प𑁣ध𑀳ण ध𑀫𑀢𑀪𑀢 𑀝च𑀟 𑀫च𑀢𑀲𑁦 𑀳𑀫𑀢 च 𑀪च𑀟च𑀪 𑀭𑀭 बच 𑀱चपच𑀟 चबन𑀳पच 𑀭थ𑀗𑀧𑀮 ञच𑀟 𑀱च𑀳च𑀟 ढच𑀣𑀠𑀢𑀟प𑁣𑀟
+    ञच𑀟 𑀤च𑀠ढ𑀢च 𑀟𑁦𑀯
+  - पचबबच𑀲च𑀣𑀢 𑀠चप𑀳नबन𑀟𑀢𑀟 𑀠नपच𑀟𑁦 𑀟𑁦 च 𑀳च𑀳𑀫𑁦𑀟 च𑀪ल𑀢प 𑀣च𑀞𑁦 णच𑀟𑀞𑀢𑀟 चबच𑀣𑁦𑀤 च च𑀪𑁦𑀱च पच प𑀳च𑀞𑀢णच𑀪
+    𑀟𑀢𑀘च𑀪𑀯
+---
+
+# SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-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/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) <!-- at revision bf3bf13ab40c3157080a7ab344c831b9ad18b5eb -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 384 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': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, '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("T-Blue/tsdae_pro_MiniLM_L12_2")
+# Run inference
+sentences = [
+    'ब𑀫𑁣𑀳प 𑀢𑀢 𑀳𑀫𑀢𑀟𑁦 𑀠च𑀲𑀢 𑀠च𑀫𑀢𑀠𑀠च𑀟त𑀢𑀦 पच𑀢𑀠च𑀞𑁣𑀟 𑀣च 𑀲च𑀳चलनललन𑀞च णच𑀟च ढच 𑀠च𑀤चन𑀟च त𑀢𑀞𑀢𑀟 𑀫च𑀟𑀞चल𑀢 णचण𑀢𑀟',
+    'च𑀠𑀢𑀟पचतत𑀢णच च त𑀢𑀞𑀢𑀟 ब𑀫𑁣𑀳प 𑀳𑁦𑀪𑀢𑁦𑀳 𑀢𑀢 𑀳𑀫𑀢𑀟𑁦 𑀠च𑀲𑀢 𑀠च𑀫𑀢𑀠𑀠च𑀟त𑀢𑀦 पच𑀪𑁦 𑀣च ञ𑀢𑀠ढ𑀢𑀟 𑀢𑀟बच𑀟पचपपन𑀟 प𑀳च𑀪𑀢𑀟 पच𑀢𑀠च𑀞𑁣𑀟 𑀣𑀢𑀪𑁦ढच 𑀣च 𑀲च𑀳चलनललन𑀞च 𑀟च च𑀠𑀢𑀟त𑀢𑀦 णच𑀟च ढच 𑀠च𑀤चन𑀟च त𑀢𑀞𑀢𑀟 𑀞𑀱च𑀟त𑀢णच𑀪 𑀫च𑀟𑀞चल𑀢 णचण𑀢𑀟 पच𑀲𑀢णच𑀪𑀳न𑀯',
+    'प𑁣ध𑀳ण ध𑀫𑀢𑀪𑀢 𑀝च𑀟 𑀫च𑀢𑀲𑁦 𑀳𑀫𑀢 च 𑀪च𑀟च𑀪 𑀭𑀭 बच 𑀱चपच𑀟 चबन𑀳पच 𑀭थ𑀗𑀧𑀮 ञच𑀟 𑀱च𑀳च𑀟 ढच𑀣𑀠𑀢𑀟प𑁣𑀟 ञच𑀟 𑀤च𑀠ढ𑀢च 𑀟𑁦𑀯',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# 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.*
+-->
+
+<!--
+## 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: 64,000 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: 4 tokens</li><li>mean: 37.72 tokens</li><li>max: 292 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 90.07 tokens</li><li>max: 512 tokens</li></ul> |
+* Samples:
+  | sentence_0                                         | sentence_1                                                                                                                        |
+  |:---------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------|
+  | <code>𑀞न𑀣न ढ𑀢𑀪𑀟𑀢𑀟𑀦𑀞न𑀳च प𑁦𑀞न𑀟</code>                | <code>प𑁦𑀞न𑀟 पचबच णच𑀟च 𑀞न𑀣न 𑀣च ढ𑀢𑀪𑀟𑀢𑀟𑀦𑀞न𑀳च 𑀣च प𑁦𑀞न𑀟 पचत𑀫𑁣बच𑀯</code>                                                                |
+  | <code>च त𑀢ढ𑀢ण𑁣ण𑀢𑀟 𑀳च𑀣च𑀪𑀱च𑀪 𑀳न झच𑀪च 𑀠चप𑀳चण𑀢𑀟</code> | <code>चढ𑁣𑀞च𑀢𑀞च𑀠च𑀪 च णच𑀱च𑀟त𑀢𑀟 त𑀢ढ𑀢ण𑁣ण𑀢𑀟 𑀳च𑀣च𑀪𑀱च𑀪 𑀘च𑀠च𑀙च𑀦 𑀠च𑀳न च𑀠𑀲च𑀟𑀢 𑀤च 𑀳न 𑀢णच झच𑀪च 𑀠नपच𑀟𑁦 च 𑀠चप𑀳चण𑀢𑀟 चढ𑁣𑀞च𑀟𑀳न𑀯</code>             |
+  | <code>𑀣च बन𑀣न𑀠𑀠च𑀱च 𑀘च𑀪𑀢𑀣न𑀟 𑀠न𑀘चललन पच 𑀯</code>     | <code>   पच ढच 𑀣च बन𑀣न𑀠𑀠च𑀱च बच 𑀘च𑀪𑀢𑀣न𑀟 च𑀟च𑀪त𑀫𑀢𑀳प 𑀣चढच𑀟ष𑀣चढच𑀟 𑀣च 𑀠न𑀘चललन 𑀠च𑀳न चलचझच 𑀣च झन𑀟ब𑀢णच𑀪 𑀠च𑀙च𑀢𑀞चपच 𑀙णच𑀟त𑀢 पच 𑀘च𑀠न𑀳 𑀯</code> |
+* Loss: [<code>DenoisingAutoEncoderLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#denoisingautoencoderloss)
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `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`: 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
+- `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`: 3
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.0
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: 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
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+
+</details>
+
+### Training Logs
+| Epoch | Step  | Training Loss |
+|:-----:|:-----:|:-------------:|
+| 0.125 | 500   | 2.5392        |
+| 0.25  | 1000  | 1.4129        |
+| 0.375 | 1500  | 1.3383        |
+| 0.5   | 2000  | 1.288         |
+| 0.625 | 2500  | 1.2627        |
+| 0.75  | 3000  | 1.239         |
+| 0.875 | 3500  | 1.2208        |
+| 1.0   | 4000  | 1.2041        |
+| 1.125 | 4500  | 1.1743        |
+| 1.25  | 5000  | 1.1633        |
+| 1.375 | 5500  | 1.1526        |
+| 1.5   | 6000  | 1.1375        |
+| 1.625 | 6500  | 1.1313        |
+| 1.75  | 7000  | 1.1246        |
+| 1.875 | 7500  | 1.1162        |
+| 2.0   | 8000  | 1.1096        |
+| 2.125 | 8500  | 1.0876        |
+| 2.25  | 9000  | 1.0839        |
+| 2.375 | 9500  | 1.0791        |
+| 2.5   | 10000 | 1.0697        |
+| 2.625 | 10500 | 1.0671        |
+| 2.75  | 11000 | 1.0644        |
+| 2.875 | 11500 | 1.0579        |
+| 3.0   | 12000 | 1.0528        |
+
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.1
+- Transformers: 4.42.4
+- PyTorch: 2.3.1+cu121
+- Accelerate: 0.33.0
+- Datasets: 2.18.0
+- 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",
+}
+```
+
+#### DenoisingAutoEncoderLoss
+```bibtex
+@inproceedings{wang-2021-TSDAE,
+    title = "TSDAE: Using Transformer-based Sequential Denoising Auto-Encoderfor Unsupervised Sentence Embedding Learning",
+    author = "Wang, Kexin and Reimers, Nils and Gurevych, Iryna", 
+    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
+    month = nov,
+    year = "2021",
+    address = "Punta Cana, Dominican Republic",
+    publisher = "Association for Computational Linguistics",
+    pages = "671--688",
+    url = "https://arxiv.org/abs/2104.06979",
+}
+```
+
+<!--
+## 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 +1,26 @@
+{
+  "_name_or_path": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.42.4",
+    "pytorch": "2.3.1+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 sha256:97beed08cd3135c1335fae2317759357f4f2768f29bc8df1ad95544ccb10c3b7
+size 470637416

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": false
+}

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 +1,64 @@
+{
+  "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>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

unigram.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da145b5e7700ae40f16691ec32a0b1fdc1ee3298db22a31ea55f57a966c4a65d
+size 14763260