Add new SentenceTransformer model.

46d1967 verified 5 months ago

14.7 kB

	---
	base_model: Bofandra/fine-tuning-use-cmlm-multilingual-quran
	datasets: []
	language: []
	library_name: sentence-transformers
	pipeline_tag: sentence-similarity
	tags:
	- sentence-transformers
	- sentence-similarity
	- feature-extraction
	- generated_from_trainer
	- dataset_size:6225
	- loss:MegaBatchMarginLoss
	widget:
	- source_sentence: يا أيها الذين آمنوا لا تتخذوا الكافرين أولياء من دون المؤمنين أتريدون
	أن تجعلوا لله عليكم سلطانا مبينا
	sentences:
	- And when he attained his full strength and was [mentally] mature, We bestowed
	upon him judgement and knowledge. And thus do We reward the doers of good.
	- Then Moses threw his staff, and at once it devoured what they falsified.
	- O you who have believed, do not take the disbelievers as allies instead of the
	believers. Do you wish to give Allah against yourselves a clear case?
	- source_sentence: قال لم أكن لأسجد لبشر خلقته من صلصال من حمإ مسنون
	sentences:
	- And We left it as a sign, so is there any who will remember?
	- Gardens of perpetual residence, whose doors will be opened to them.
	- He said, "Never would I prostrate to a human whom You created out of clay from
	an altered black mud."
	- source_sentence: وسخر لكم الشمس والقمر دائبين وسخر لكم الليل والنهار
	sentences:
	- And He subjected for you the sun and the moon, continuous [in orbit], and subjected
	for you the night and the day.
	- And We called him from the side of the mount at [his] right and brought him near,
	confiding [to him].
	- And We send not the messengers except as bringers of good tidings and warners.
	And those who disbelieve dispute by [using] falsehood to [attempt to] invalidate
	thereby the truth and have taken My verses, and that of which they are warned,
	in ridicule.
	- source_sentence: إذ دخلوا عليه فقالوا سلاما قال إنا منكم وجلون
	sentences:
	- Indeed, your Lord is most knowing of who strays from His way, and He is most knowing
	of the [rightly] guided.
	- Then they turned away from him and said, "[He was] taught [and is] a madman."
	- When they entered upon him and said, "Peace." [Abraham] said, "Indeed, we are
	fearful of you."
	- source_sentence: فأما من أوتي كتابه بيمينه فيقول هاؤم اقرءوا كتابيه
	sentences:
	- So as for he who is given his record in his right hand, he will say, "Here, read
	my record!
	- And whoever is patient and forgives - indeed, that is of the matters [requiring]
	determination.
	- Indeed, he had [once] been among his people in happiness;
	---

	# SentenceTransformer based on Bofandra/fine-tuning-use-cmlm-multilingual-quran

	This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Bofandra/fine-tuning-use-cmlm-multilingual-quran](https://huggingface.co/Bofandra/fine-tuning-use-cmlm-multilingual-quran). 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: [Bofandra/fine-tuning-use-cmlm-multilingual-quran](https://huggingface.co/Bofandra/fine-tuning-use-cmlm-multilingual-quran) <!-- at revision 7a1271e8909e29e5840b034feeefe22e45dd7a97 -->
	- 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': 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("Bofandra/fine-tuning-use-cmlm-multilingual-quran-translation")
	# Run inference
	sentences = [
	'فأما من أوتي كتابه بيمينه فيقول هاؤم اقرءوا كتابيه',
	'So as for he who is given his record in his right hand, he will say, "Here, read my record!',
	'Indeed, he had [once] been among his people in happiness;',
	]
	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: 6,225 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: 23.11 tokens</li><li>max: 163 tokens</li></ul> \| <ul><li>min: 6 tokens</li><li>mean: 34.63 tokens</li><li>max: 180 tokens</li></ul> \|
	* Samples:
	\| sentence_0 \| sentence_1 \|
	\|:------------------------------------------------------------------------------------------------------------------------------\|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\|
	\| <code>ومن آياته أنك ترى الأرض خاشعة فإذا أنزلنا عليها الماء اهتزت وربت إن الذي أحياها لمحيي الموتى إنه على كل شيء قدير</code> \| <code>And of His signs is that you see the earth stilled, but when We send down upon it rain, it quivers and grows. Indeed, He who has given it life is the Giver of Life to the dead. Indeed, He is over all things competent.</code> \|
	\| <code>من دون الله قالوا ضلوا عنا بل لم نكن ندعو من قبل شيئا كذلك يضل الله الكافرين</code> \| <code>Other than Allah?" They will say, "They have departed from us; rather, we did not used to invoke previously anything." Thus does Allah put astray the disbelievers.</code> \|
	\| <code>أرأيت الذي ينهى</code> \| <code>Have you seen the one who forbids</code> \|
	* Loss: [<code>MegaBatchMarginLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#megabatchmarginloss)

	### Training Hyperparameters
	#### Non-Default Hyperparameters

	- `per_device_train_batch_size`: 4
	- `per_device_eval_batch_size`: 4
	- `num_train_epochs`: 1
	- `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`: 4
	- `per_device_eval_batch_size`: 4
	- `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`: 1
	- `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
	- `batch_sampler`: batch_sampler
	- `multi_dataset_batch_sampler`: round_robin

	</details>

	### Training Logs
	\| Epoch \| Step \| Training Loss \|
	\|:------:\|:----:\|:-------------:\|
	\| 0.3211 \| 500 \| 0.2393 \|
	\| 0.6423 \| 1000 \| 0.1212 \|
	\| 0.9634 \| 1500 \| 0.0715 \|


	### Framework Versions
	- Python: 3.10.12
	- Sentence Transformers: 3.0.1
	- Transformers: 4.41.2
	- PyTorch: 2.3.0+cu121
	- Accelerate: 0.31.0
	- 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",
	}
	```

	#### MegaBatchMarginLoss
	```bibtex
	@inproceedings{wieting-gimpel-2018-paranmt,
	title = "{P}ara{NMT}-50{M}: Pushing the Limits of Paraphrastic Sentence Embeddings with Millions of Machine Translations",
	author = "Wieting, John and Gimpel, Kevin",
	editor = "Gurevych, Iryna and Miyao, Yusuke",
	booktitle = "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
	month = jul,
	year = "2018",
	address = "Melbourne, Australia",
	publisher = "Association for Computational Linguistics",
	url = "https://aclanthology.org/P18-1042",
	doi = "10.18653/v1/P18-1042",
	pages = "451--462",
	}
	```

	<!--
	## 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.
	-->