Add new SentenceTransformer model.

0b46400 verified 7 months ago

17.1 kB

	---
	base_model: sentence-transformers/LaBSE
	datasets: []
	language: []
	library_name: sentence-transformers
	pipeline_tag: sentence-similarity
	tags:
	- sentence-transformers
	- sentence-similarity
	- feature-extraction
	- generated_from_trainer
	- dataset_size:23999
	- loss:MultipleNegativesRankingLoss
	widget:
	- source_sentence: Who led thee through that great and terrible wilderness , wherein
	were fiery serpents , and scorpions , and drought , where there was no water ;
	who brought thee forth water out of the rock of flint ;
	sentences:
	- bad u ai ïa ki ha u Aaron bad ki khun shynrang jong u .
	- U la ïalam ïa phi lyngba ka ri shyiap kaba ïar bad kaba ishyrkhei eh , ha kaba
	la don ki bseiñ kiba don bih bad ki ñianglartham . Ha kata ka ri kaba tyrkhong
	bad ka bym don um , u la pynmih um na u mawsiang na ka bynta jong phi .
	- Ki paidbah na ki jait ba na shatei ki phah khot ïa u , bad nangta ma ki baroh
	ki ïaleit lang sha u Rehoboam bad ki ong ha u ,
	- source_sentence: And , behold , Boaz came from Beth–lehem , and said unto the reapers
	, The Lord be with you . And they answered him , The Lord bless thee .
	sentences:
	- Ko ki briew bymïaineh , to wan noh ; phi long ki jong nga . Ngan shim iwei na
	phi na kawei kawei ka shnong bad ar ngut na kawei kawei ka kur , bad ngan wallam
	pat ïa phi sha u lum Seïon .
	- Hadien katto katne por u Boas da lade hi u wan poi na Bethlehem bad u ai khublei
	ïa ki nongtrei . To U Trai un long ryngkat bad phi ! u ong . U Trai u kyrkhu
	ïa phi ! ki jubab .
	- U Trai u la ong ha u , Khreh bad leit sha ‘ Ka Lynti Ba-beit ,’ bad ha ka ïing
	jong u Judas kylli ïa u briew na Tarsos uba kyrteng u Saul .
	- source_sentence: Jehovah used the prehuman Jesus as his “master worker” in creating
	all other things in heaven and on earth .
	sentences:
	- Shuwa ba un wan long briew U Jehobah u la pyndonkam ïa u Jisu kum u “rangbah nongtrei”
	ha kaba thaw ïa kiei kiei baroh kiba don ha bneng bad ha khyndew .
	- Shisien la don u briew uba la leit ban bet symbai . Katba u dang bet ïa u symbai
	, katto katne na u , ki la hap ha shi lynter ka lynti ïaid kjat , ha kaba ki la
	shah ïuh , bad ki sim ki la bam lut .
	- Ngan ïathuh ïa ka shatei ban shah ïa ki ban leit bad ïa ka shathie ban ym bat
	noh ïa ki . Ai ba ki briew jong nga ki wan phai na ki ri bajngai , na man la ki
	bynta baroh jong ka pyrthei .
	- source_sentence: 'The like figure whereunto even baptism doth also now save us (
	not the putting away of the filth of the flesh , but the answer of a good conscience
	toward God , ) by the resurrection of Jesus Christ :'
	sentences:
	- kaba long ka dak kaba kdew sha ka jingpynbaptis , kaba pyllait im ïa phi mynta
	. Kam dei ka jingsait noh ïa ka jakhlia na ka met , hynrei ka jingkular ba la
	pynlong sha U Blei na ka jingïatiplem babha . Ka pynim ïa phi da ka jingmihpat
	jong U Jisu Khrist ,
	- Ki briew kiba sniew kin ïoh ïa kaei kaba ki dei ban ïoh . Ki briew kiba bha kin
	ïoh bainong na ka bynta ki kam jong ki .
	- Nangta nga la ïohi ïa ka bneng bathymmai bad ïa ka pyrthei bathymmai . Ka bneng
	banyngkong bad ka pyrthei banyngkong ki la jah noh , bad ka duriaw kam don shuh
	.
	- source_sentence: On that day they read in the book of Moses in the audience of the
	people ; and therein was found written , that the Ammonite and the Moabite should
	not come into the congregation of God for ever ;
	sentences:
	- U Elisha u la ïap bad la tep ïa u . Man la ka snem ki kynhun jong ki Moab ki ju
	wan tur thma ïa ka ri Israel .
	- Katba dang pule jam ïa ka Hukum u Moses ha u paidbah , ki poi ha ka bynta kaba
	ong ba ym dei ban shah ïa u nong Amon ne u nong Moab ban ïasnohlang bad ki briew
	jong U Blei .
	- U angel u la jubab , U Mynsiem Bakhuid un sa wan ha pha , bad ka bor jong U Blei
	kan shong halor jong pha . Na kane ka daw , ïa i khunlung bakhuid yn khot U Khun
	U Blei .
	---

	# SentenceTransformer based on sentence-transformers/LaBSE

	This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/LaBSE](https://huggingface.co/sentence-transformers/LaBSE). 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/LaBSE](https://huggingface.co/sentence-transformers/LaBSE) <!-- at revision e34fab64a3011d2176c99545a93d5cbddc9a91b7 -->
	- Maximum Sequence Length: 256 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': 256, 'do_lower_case': False}) with Transformer model: BertModel
	(1): Pooling({'word_embedding_dimension': 768, '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})
	(2): Dense({'in_features': 768, 'out_features': 768, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
	(3): 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("ABHIiiii1/LaBSE-Fine-Tuned-EN-KHA")
	# Run inference
	sentences = [
	'On that day they read in the book of Moses in the audience of the people ; and therein was found written , that the Ammonite and the Moabite should not come into the congregation of God for ever ;',
	'Katba dang pule jam ïa ka Hukum u Moses ha u paidbah , ki poi ha ka bynta kaba ong ba ym dei ban shah ïa u nong Amon ne u nong Moab ban ïasnohlang bad ki briew jong U Blei .',
	'U Elisha u la ïap bad la tep ïa u . Man la ka snem ki kynhun jong ki Moab ki ju wan tur thma ïa ka ri Israel .',
	]
	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.
	-->

	<!--
	## 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: 23,999 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: 6 tokens</li><li>mean: 34.89 tokens</li><li>max: 87 tokens</li></ul> \| <ul><li>min: 8 tokens</li><li>mean: 51.51 tokens</li><li>max: 127 tokens</li></ul> \|
	* Samples:
	\| sentence_0 \| sentence_1 \|
	\|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\|
	\| <code>And Moses went out from Pharaoh , and entreated the Lord .</code> \| <code>U Moses u mihnoh na u Pharaoh , bad u kyrpad ïa U Trai ,</code> \|
	\| <code>In the ninth year of Hoshea the king of Assyria took Samaria , and carried Israel away into Assyria , and placed them in Halah and in Habor by the river of Gozan , and in the cities of the Medes .</code> \| <code>kaba long ka snem kaba khyndai jong ka jingsynshar u Hoshea , u patsha ka Assyria u kurup ïa ka Samaria , u rah ïa ki Israel sha Assyria kum ki koidi , bad pynsah katto katne ngut na ki ha ka nongbah Halah , katto katne pat hajan ka wah Habor ha ka distrik Gosan , bad katto katne ha ki nongbah jong ka Media .</code> \|
	\| <code>And the king said unto Cushi , Is the young man Absalom safe ? And Cushi answered , The enemies of my lord the king , and all that rise against thee to do thee hurt , be as that young man is .</code> \| <code>Hato u samla Absalom u dang im ? u syiem u kylli . U mraw u jubab , Ko Kynrad , nga sngew ba kaei kaba la jia ha u kan jin da la jia ha baroh ki nongshun jong ngi , bad ha baroh kiba ïaleh pyrshah ïa phi .</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

	- `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 \|
	\|:------:\|:----:\|:-------------:\|
	\| 0.3333 \| 500 \| 0.542 \|
	\| 0.6667 \| 1000 \| 0.135 \|
	\| 1.0 \| 1500 \| 0.0926 \|
	\| 1.3333 \| 2000 \| 0.0535 \|
	\| 1.6667 \| 2500 \| 0.0226 \|
	\| 2.0 \| 3000 \| 0.018 \|
	\| 2.3333 \| 3500 \| 0.0124 \|
	\| 2.6667 \| 4000 \| 0.0057 \|
	\| 3.0 \| 4500 \| 0.0053 \|


	### Framework Versions
	- Python: 3.10.13
	- Sentence Transformers: 3.0.1
	- Transformers: 4.42.3
	- PyTorch: 2.1.2
	- Accelerate: 0.32.1
	- Datasets: 2.20.0
	- 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.
	-->