| --- |
| base_model: shibing624/text2vec-base-multilingual |
| 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: च बच 𑀱चपच𑀟 पच पच 𑀙णच𑀪 𑀱च𑀳च 𑀠च𑀢 𑀳𑀫𑁦𑀞च𑀪न𑀣च पच 𑀞𑀱चलल𑁣 पच𑀪𑀢𑀫𑀢𑀟 ल𑁣𑀞चत𑀢𑀟 |
| 𑀱च𑀳च𑀟 𑀳च𑀠न 𑀟च𑀳च𑀪च 𑀱च𑀟𑀣च च ल𑁦खच𑀟प𑁦 लच𑀳 धलच𑀟च𑀳 𑀣𑀢ख𑀢𑀳𑀢𑀨𑀟 |
| sentences: |
| - ' च𑀟 पच𑀟पच𑀟त𑁦 पच च 𑀠चप𑀳चण𑀢𑀟 गणच𑀪 पच𑀞च𑀪च𑀪 𑁦च𑀳पल𑁦𑀢ब𑀫 च 𑀤चढ𑁦𑀟 𑀲𑀢𑀣𑀣च ब𑀱च𑀟𑀢 𑀟च 𑀳𑀫𑁦𑀞च𑀪च𑀪 |
| 𑀭थथर च𑀠𑀠च पच 𑀳𑀫च 𑀞चण𑁦 च 𑀤चढ𑁦𑀟𑀯' |
| - ' च 𑀪च𑀟च𑀪 ठ𑀖 बच 𑀱चपच𑀟 𑀘च𑀟च𑀢𑀪न च 𑀳𑀫𑁦𑀞च𑀪च𑀪 ठ𑀧ठ𑀰 पच 𑀞च𑀲च पच𑀪𑀢𑀫𑀢 पच 𑀤च𑀠च 𑀠चपच𑀳𑀫𑀢णच𑀪 |
| 𑀙णच𑀪 𑀱च𑀳च 𑀠च𑀢 𑀞च𑀪च𑀟त𑀢𑀟 𑀳𑀫𑁦𑀞च𑀪न𑀣च पच त𑀢 𑀞𑀱चलल𑁣 च पच𑀪𑀢𑀫𑀢𑀟 ढच𑀪तच ल𑁣𑀞चत𑀢𑀟 𑀣च पच त𑀢 |
| च 𑀱च𑀳च𑀟 𑀣च 𑀳न𑀞च 𑀳च𑀠न 𑀟च𑀳च𑀪च 𑀱च𑀟𑀣च 𑀞न𑀟ब𑀢णच𑀪 पच ढच𑀪त𑁦ल𑁣𑀟च 𑀬ष𑀧 च 𑀞च𑀟 ल𑁦खच𑀟प𑁦 लच𑀳 |
| धलच𑀟च𑀳 च 𑀱च𑀳च𑀟 ध𑀪𑀢𑀠𑁦𑀪च 𑀣𑀢ख𑀢𑀳𑀢𑀨𑀟 𑀯' |
| - ' च 𑀞च𑀞च𑀪 𑀱च𑀳च𑀟𑀳च 𑀟च ढ𑀢णन च त𑀢𑀞𑀢𑀟 ठ𑀧ठ𑀭𑀦 णच 𑀤च𑀠च 𑀣च𑀟 𑀱च𑀳च च 𑀞नल𑁣ढ 𑀣𑀢𑀟 𑀞न𑀠च णच |
| पच𑀢𑀠च𑀞च 𑀠न𑀳न 𑀳न𑀟 त𑀢 𑁦पपच𑀟 ठ𑀧ठ𑀭𑀦 𑀞न𑀠च च𑀟 𑀟च𑀣च 𑀳𑀫𑀢 ब𑀱च𑀟𑀢𑀟 बच𑀳च𑀪 𑀞च𑀞च𑀪 𑀱च𑀳च𑀯' |
| - source_sentence: 𑀣च 𑀟च प𑀳𑁦𑀪𑁦𑀟 च |
| sentences: |
| - ल𑀢𑀳𑀳च𑀲𑀢𑀟 ल𑀢𑀳𑀳च𑀲𑀢𑀟 𑀫चझझ𑀢𑀟 𑀫चझझ𑀢𑀟 𑀠चललच𑀞चबचढचञचणचपच𑀞च𑀣𑀣न𑀟 𑀣च च𑀞च ण𑀢 𑀟𑀢णणच 𑀟च 𑀠न𑀳च𑀠𑀠च𑀟 𑀣𑁣𑀞च𑀪 |
| 𑀫चझझ𑀢𑀟 𑀠चढन𑀞चत𑀢 𑀣𑁣𑀞च𑀪 𑀫च𑀞𑀞𑁣𑀞𑀢𑀟 𑀠च𑀪च ब𑀢𑀣च 𑀣𑁣𑀞च𑀪 𑀫चझझ𑀢𑀟 𑀠च𑀢 ढ𑀢णच𑀟 𑀫च𑀪च𑀘𑀢 𑀣𑁣𑀞च𑀪 𑀫च𑀞𑀞𑁣𑀞𑀢𑀟 |
| 𑀢ल𑀢𑀠𑀢 𑀦 𑀣𑁣𑀞च𑀪 𑀫च𑀞𑀞𑁣𑀞𑀢𑀟 प𑀳𑁣𑀫𑁣𑀟 𑀳𑁣𑀘𑁣𑀘𑀢 ब𑀢 ढ𑀢लल 𑁣𑀲 𑀪𑀢ब𑀫प𑀳𑀦 𑀱च𑀟𑀣च च𑀞च 𑀲𑀢 𑀳च𑀟𑀢 𑀣च ब𑀢 |
| ढ𑀢लल 𑀣𑁣𑀞च𑀪 𑀙णच𑀟 लन𑀱च𑀣𑀢𑀦 पच𑀪𑁣𑀟 झन𑀟ब𑀢ण𑁣ण𑀢𑀟 𑀙णच𑀟 लन𑀱च𑀣𑀢 𑀟च च𑀪𑁦𑀱चत𑀢𑀟 च𑀠𑀢𑀪𑀞च 𑀟𑁦 𑀳न𑀞च |
| प𑀳च𑀪च 𑀣𑁣𑀞च𑀪 𑀫चझझ𑀢𑀟 लचढन𑀪च𑀪𑁦𑀦 झन𑀟ब𑀢णच𑀪 लचढन𑀪च𑀪𑁦 पच च𑀠𑀢𑀪𑀞च पच ढनबच 𑀣𑁣𑀞च𑀪 𑀫चझझ𑀢𑀟 |
| 𑀠न𑀫चलल𑀢 𑀞𑁣 च𑀘च𑀟𑀣च ठ𑀭 𑀞न𑀣𑀢𑀪𑀢𑀟 𑀫च𑀞𑀞𑀢 𑀟च 𑀠च𑀫चल𑀢तत𑀢𑀦 𑀠च𑀪नढनपच𑀟 ढच𑀟 𑀣च𑀪𑀢णच 𑀣च 𑀠च𑀳न |
| 𑀲च𑀳च𑀫च 𑀣𑁣𑀞च𑀪 𑀫चझझ𑀢𑀟 𑀠च𑀢 ढच 𑀣च बन𑀣न𑀠𑀠च𑀱च𑀦 𑀣𑁣𑀟 𑀠च𑀳न ढच 𑀣च चबच𑀘𑀢 𑀞न𑀣𑀢𑀪𑀢𑀟 𑀫च𑀞𑀞𑁣𑀞𑀢𑀟 |
| 𑀘च𑀠𑀢𑀙च𑀟 𑀣𑁣𑀞च 𑀣𑁣𑀞च𑀪 𑀫चझझ𑀢𑀟 𑀠च𑀳न 𑀤च𑁥𑁦 पच तचल𑀢𑀲𑁣𑀪𑀟𑀢च𑀦 𑀣च𑀢𑀣च𑀢पच𑀱च 𑀣च 𑀣𑁣𑀞च𑀪 𑀫चझझ𑀢𑀟 |
| 𑀤च𑁥𑁦 𑀣𑁣𑀞च𑀪 𑀠न𑀳नलन𑀟त𑀢 पच 𑀫च𑀞𑀞𑁣𑀞𑀢𑀟 𑀠चपच च 𑀠च𑀳चललचत𑀢𑀟 𑀟𑁦𑀱 𑀘𑁦𑀪𑀳𑁦ण 𑀣𑁣𑀞च𑀪 𑀫चझझ𑀢𑀟 𑀫चझझ𑀢𑀟 |
| त𑀢𑀟 𑀫च𑀟त𑀢 𑀣च 𑀪च𑀳𑀫च𑀱च 𑀞न𑀣𑀢𑀪𑀢𑀟 𑀫चझझ𑀢𑀟 𑀠च𑀳न 𑀞चप𑀢𑀟 𑀞𑀢𑀪𑁦𑀣𑀢प𑀦 𑀱च𑀟𑀣च 𑀞𑁦 झन𑀟𑀳𑀫𑁦 च त𑀢𑀞𑀢𑀟 |
| 𑀣𑁣𑀞च𑀪 तच𑀪𑀣 𑀟च 𑀳𑀫𑁦𑀞च𑀪चपच ठ𑀧𑀧थ 𑀣𑁣𑀞𑁣𑀞𑀢𑀟 𑀫चझझ𑀢𑀟 𑀠च𑀳न त𑀢 बचढच𑀟 त𑀢𑀟 𑀣न𑀪𑀢 𑀣च 𑀘𑀢𑀠च𑀙𑀢 𑀝𑀣𑁣𑀞च𑀪 |
| 𑀫चझझ𑀢𑀟 𑀠च𑀳न त𑀢 बचढच 𑀣च 𑀘𑀢𑀠च𑀙𑀢 𑀮𑀣नढच 𑀱च𑀳न चढनढन𑀱च𑀟 झ𑀢𑀪च𑀪 𑀫चझझ𑀢𑀟 ढ𑀢𑀪𑀢पच𑀟𑀢णच 𑀫चझझ𑀢𑀟 |
| 𑀣च ढच 𑀤च च 𑀢णच पचनण𑁦𑀱च ढच 𑀣𑁣𑀞च𑀪 𑀞च𑀪𑁦 𑀫च𑀞𑀞𑁣𑀞𑀢𑀟 𑀣च𑀟 च𑀣च𑀠 पच 𑀣न𑀟𑀢णच 𑀞च𑀙𑀢𑀣𑁣𑀘𑀢𑀟 𑀞च𑀪𑁦 |
| 𑀫च𑀞𑀞𑀢𑀟 ढ𑀢ल𑀙च𑀣च𑀠च 𑀟च 𑀣न𑀟𑀢णच 𑀫च𑀞𑀞𑁣𑀞𑀢𑀟 𑀫चल𑀢पपच प𑀳च𑀪𑀢𑀟 𑀣𑁣𑀞च 𑀣𑁣𑀞च𑀪 𑀫च𑀞𑀞𑀢 𑀟च ढ𑀢णन𑀠च𑀟च𑀤च𑀪पच𑀯 |
| - 𑀭𑀰𑀮𑀦 𑀣च लच𑀠ढच𑀪 पचबनललच च त𑀢𑀞𑀢𑀟 𑀪न𑀞न𑀟𑀢𑀟 ढठ 𑀟च प𑀳𑁦𑀪𑁦𑀟 झच𑀳च च 𑀧𑀕𑀖र𑀯 |
| - द द द य𑀞न𑀠च 𑀞न ढचनपच 𑀱च चललच𑀫 𑀞न𑀠च 𑀞च 𑀣च 𑀞न 𑀫चञच𑀱च𑀟𑀢 𑀣च 𑀳𑀫𑀢द 𑀞न𑀠च बच 𑀠च𑀫च𑀢𑀲च 𑀞न |
| ण𑀢 𑀞णचनपचपच𑀱च𑀦 𑀞न𑀠च बच 𑀠चभ चढ𑁣पच 𑀤न𑀠न𑀟पच 𑀣च 𑀠च𑀪चणन 𑀣च 𑀠चपचलचनपच 𑀣च 𑀠चझ𑀱चढत𑀢 𑀠चभचढनत𑀢𑀟 |
| 𑀞न𑀳च𑀟पच𑀦 𑀣च 𑀠चझ𑀱चढत𑀢 𑀠च𑀟𑀢𑀳च𑀟त𑀢𑀦 𑀣च चढ𑁣𑀞𑀢च ब𑁦𑀲𑁦 𑀣च 𑀩च𑀟 𑀫च𑀟णच 𑀣च चढ𑀢𑀟 𑀣च 𑀫च𑀟𑀟न𑀱च𑀟𑀞न |
| 𑀟च 𑀣च𑀠च 𑀳न𑀞च 𑀠चललच𑀞च𑀯 |
| - source_sentence: पच𑀞च 𑀪च𑀱च𑀪 च 𑀳च𑀪𑀞𑀢 |
| sentences: |
| - ' णच पच𑀞च 𑀪च𑀱च𑀪 बच𑀟𑀢 च 𑀠चप𑀳चण𑀢𑀟𑀦 𑀳च𑀪𑀞𑀢 𑀣च𑀠ढच च त𑀢𑀞𑀢𑀟 𑀳𑀫𑀢𑀪𑀢𑀟𑀯' |
| - थ𑀰𑀭𑀗𑀖ठ𑀰ठ𑁢थ𑁢𑀭 𑀦 𑀭𑀧𑀯 |
| - पचलचढ𑀢𑀘च𑀟 𑀣च 𑀪𑁦𑀣𑀢ण𑁣 च𑀟 बचढचपच𑀪 𑀣च पचलचढ𑀢𑀘𑀢𑀟 बच ब𑀫च𑀟च च 𑀭थ𑁢𑀖 𑀞न𑀠च णच𑀟च 𑀞च𑀪𑀞च𑀳𑀫𑀢𑀟 |
| 𑀢𑀞𑁣𑀟 𑀘𑀢𑀫च𑀯 |
| - source_sentence: 𑀱चप𑀳च 𑀣च 𑀟च𑀣च 𑀳न𑀦 𑀣𑀪𑀢ख𑁦 𑀞𑁣𑀱च𑀟𑁦 णच 𑀣च च ल𑁣𑀞चत𑀢𑀟 𑀫च𑀳च𑀳𑀫𑁦𑀟𑀳च𑀯 |
| sentences: |
| - ' ण𑀢𑀟 च𑀢𑀞𑀢 पच𑀪𑁦 𑀣च 𑀳चन𑀪च𑀟 𑀞न𑀟ब𑀢ण𑁣ण𑀢𑀟 णच𑀫न𑀣च𑀱च 𑀣𑁣𑀟 𑀞च𑀪च 𑀱चणच𑀪 𑀣च 𑀞च𑀟 णच𑀟 च𑀣च𑀠 𑀣च |
| 𑀞च𑀪𑀲च𑀲च 𑀫𑀢𑀠𑀠च च प𑀳च𑀞च𑀟𑀢𑀟 चल𑀙न𑀠𑀠𑁣𑀠𑀢𑀟 णच𑀫न𑀣च𑀱च च 𑀠च𑀣च𑀣𑀢𑀟 𑀱च𑀣च𑀟𑀣च च𑀞च 𑀲चपचपपच𑀞च 𑀣च |
| 𑀱च𑀣च𑀟𑀣च च𑀞𑁦 𑀤चलन𑀟पच च 𑀣न𑀟𑀢णच𑀯' |
| - ' 𑀫𑁣पन𑀟च𑀟 च𑀟च 𑀱चप𑀳च 𑀳न पच 𑀫च𑀟णच𑀪 𑀟च𑀙न𑀪च𑀪 𑀣चन𑀞च𑀪 𑀫𑁣प𑁣 𑀣च𑀢𑀣च𑀢 𑀣च णच𑀣𑀣च च𑀞च 𑀟च𑀣च |
| 𑀳न𑀦 पच𑀪𑁦 𑀣च ब𑁦𑀟𑁦खच 𑀣𑀪𑀢ख𑁦 𑀣च 𑀞𑁦 पचढढचपच𑀪 𑀣च त𑁦𑀱च 𑀞𑁣𑀱च𑀟𑁦 𑀲𑀢𑀪च𑀠 णच त𑀢 बचढच 𑀣च 𑀞च𑀳च𑀟त𑁦𑀱च |
| च त𑀢𑀞𑀢𑀟 बच𑀘𑁦𑀪𑁦𑀟 ल𑁣𑀞चत𑀢𑀟 𑀫च𑀳च𑀳𑀫𑁦𑀟𑀳च𑀯' |
| - ' 𑀪च𑀠न𑀞च च त𑀢𑀞𑀢𑀟 झच𑀟च𑀟च𑀟 𑀪चढ𑁣 𑀣𑁣𑀟 𑀞च𑀪𑁦 प𑀳𑀢𑀪𑁦षप𑀳𑀢𑀪𑁦 𑀣चबच 𑀲𑁦𑀳च 𑀠चबच𑀟𑀢𑀟 𑀫𑁦𑀪ढ𑀢त𑀢𑀣𑁦𑀳 |
| 𑀣च लचलचपच 𑀪𑁣𑀣𑁦𑀟प𑀯' |
| - source_sentence: 𑀠चपच𑀞𑀢𑀟 पच𑀟च ढनबच 𑀱च 𑀟च𑀠ध𑁣ल लच𑀣𑀢𑁦𑀳 𑀲त पच 𑀱च𑀳च𑀯 |
| sentences: |
| - ' च 𑀠चपच𑀞𑀢𑀟 𑀞नल𑁣ढ पच𑀟च ढनबच 𑀱च 𑀞𑁣𑀠च𑀳 𑀟च𑀠ध𑁣ल लच𑀣𑀢𑁦𑀳 𑀲त पच 𑀟च𑀠𑀢ढ𑀢च 𑀱च𑀳च𑀯' |
| - ' णच𑀟𑀞न𑀟च𑀟 बन𑀟𑀣न𑀠च𑀪 𑀘𑀣𑁦ण𑀣𑁦𑀫 ब𑀢𑀣च 𑀟𑁦 बच ब𑀢𑀣च𑀘𑁦 𑀠च𑀳न णच𑀱च 𑀟च झच𑀪𑀟𑀢 𑀟च 𑀭𑁢 𑀣च 𑀟च 𑀭𑀬 |
| 𑀟च चल𑁦धध𑀢𑀟 ढ𑁣न𑀪ब𑁦𑁣𑀢𑀳𑀢𑁦𑀦 𑀱चञच𑀟𑀣च 𑀞𑁦 ञचन𑀞𑁦 𑀣च 𑀤च𑀟𑁦𑀟 𑀣नप𑀳𑁦𑀯' |
| - 𑀪च𑀪𑀪चढच 𑀳𑀫𑁦𑀞च𑀪न𑀟 णच 𑀞च𑀳च𑀟त𑁦 ठर𑀯 |
| --- |
| |
| # SentenceTransformer based on shibing624/text2vec-base-multilingual |
|
|
| This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [shibing624/text2vec-base-multilingual](https://huggingface.co/shibing624/text2vec-base-multilingual). 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:** [shibing624/text2vec-base-multilingual](https://huggingface.co/shibing624/text2vec-base-multilingual) <!-- at revision e9215a523d4324733a3c8279d0adff7bf37a7a77 --> |
| - **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_text2vec") |
| # Run inference |
| sentences = [ |
| '𑀠चपच𑀞𑀢𑀟 पच𑀟च ढनबच 𑀱च 𑀟च𑀠ध𑁣ल लच𑀣𑀢𑁦𑀳 𑀲त पच 𑀱च𑀳च𑀯', |
| ' च 𑀠चपच𑀞𑀢𑀟 𑀞नल𑁣ढ पच𑀟च ढनबच 𑀱च 𑀞𑁣𑀠च𑀳 𑀟च𑀠ध𑁣ल लच𑀣𑀢𑁦𑀳 𑀲त पच 𑀟च𑀠𑀢ढ𑀢च 𑀱च𑀳च𑀯', |
| ' णच𑀟𑀞न𑀟च𑀟 बन𑀟𑀣न𑀠च𑀪 𑀘𑀣𑁦ण𑀣𑁦𑀫 ब𑀢𑀣च 𑀟𑁦 बच ब𑀢𑀣च𑀘𑁦 𑀠च𑀳न णच𑀱च 𑀟च झच𑀪𑀟𑀢 𑀟च 𑀭𑁢 𑀣च 𑀟च 𑀭𑀬 𑀟च चल𑁦धध𑀢𑀟 ढ𑁣न𑀪ब𑁦𑁣𑀢𑀳𑀢𑁦𑀦 𑀱चञच𑀟𑀣च 𑀞𑁦 ञचन𑀞𑁦 𑀣च 𑀤च𑀟𑁦𑀟 𑀣नप𑀳𑁦𑀯', |
| ] |
| 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: 3 tokens</li><li>mean: 37.42 tokens</li><li>max: 342 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 89.84 tokens</li><li>max: 512 tokens</li></ul> | |
| * Samples: |
| | sentence_0 | sentence_1 | |
| |:-----------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------| |
| | <code>𑀠नपच𑀟𑁦𑀫च𑀢𑀫न𑀱च𑀟 𑀭थथ𑀬𑀯</code> | <code>𑀞𑀢𑀣𑀢𑀣𑀣𑀢बच𑀪 𑀳च𑀟च𑀙च𑀞नल𑁣ढझच𑀳च𑀳𑀫𑁦𑀟 𑀣न𑀟𑀢णच𑀠च𑀟च𑀤च𑀪पच 𑀪चणचणणन𑀟 𑀠नपच𑀟𑁦𑀫च𑀢𑀫न𑀱च𑀟 𑀭थथ𑀬𑀯</code> | |
| | <code>च 𑀱च𑀘𑁦𑀟 𑀘च𑀠भ𑀢णणच 𑀠च𑀢 𑀞𑀢𑀳𑀫𑀢𑀟 पच बच𑀳𑀞𑀢णच𑀯</code> | <code>𑀘च𑀠भ𑀢णणच𑀪 च ल𑁣𑀞चत𑀢𑀟 𑀢पच त𑁦 पच ढ𑀢णन 𑀣च पच ण𑀢 𑀟च𑀠𑀢𑀘𑀢𑀟 𑀞𑁣𑀞च𑀪𑀢 𑀱च𑀘𑁦𑀟 𑀳च𑀠च𑀪 𑀣च 𑀘च𑀠भ𑀢णणच 𑀠च𑀢 𑀞𑀢𑀳𑀫𑀢𑀟 𑀞च𑀳च पच बच𑀳𑀞𑀢णच𑀯</code> | |
| | <code>𑀯</code> | <code>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 | 4.0592 | |
| | 0.25 | 1000 | 1.6454 | |
| | 0.375 | 1500 | 1.4774 | |
| | 0.5 | 2000 | 1.4131 | |
| | 0.625 | 2500 | 1.3766 | |
| | 0.75 | 3000 | 1.3488 | |
| | 0.875 | 3500 | 1.3252 | |
| | 1.0 | 4000 | 1.3087 | |
| | 1.125 | 4500 | 1.2931 | |
| | 1.25 | 5000 | 1.2772 | |
| | 1.375 | 5500 | 1.2655 | |
| | 1.5 | 6000 | 1.2535 | |
| | 1.625 | 6500 | 1.243 | |
| | 1.75 | 7000 | 1.2305 | |
| | 1.875 | 7500 | 1.223 | |
| | 2.0 | 8000 | 1.216 | |
| | 2.125 | 8500 | 1.2073 | |
| | 2.25 | 9000 | 1.1999 | |
| | 2.375 | 9500 | 1.1935 | |
| | 2.5 | 10000 | 1.1872 | |
| | 2.625 | 10500 | 1.1804 | |
| | 2.75 | 11000 | 1.17 | |
| | 2.875 | 11500 | 1.167 | |
| | 3.0 | 12000 | 1.1623 | |
| |
| |
| ### 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.* |
| --> |
