README.md

metadata

base_model: Bofandra/fine-tuning-use-cmlm-multilingual-quran-translation
datasets: []
language: []
library_name: sentence-transformers
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:609
  - loss:MegaBatchMarginLoss
widget:
  - source_sentence: So which of the favors of your Lord would you deny
    sentences:
      - ' This is a straight path.'
      - >-
        Have they not traveled through the land and seen how was the end of
        those before them? Allah destroyed [everything] over them, and for the
        disbelievers is something comparable.
      - So which of the favors of your Lord would you deny?
  - source_sentence: >-
      So would you perhaps, if you turned away, cause corruption on earth and
      sever your [ties of] relationship
    sentences:
      - >-
        Said [the king to the women], "What was your condition when you sought
        to seduce Joseph?" They said, "Perfect is Allah! We know about him no
        evil." The wife of al-'Azeez said, "Now the truth has become evident. It
        was I who sought to seduce him, and indeed, he is of the truthful.
      - >-
        Then do they not reflect upon the Qur'an, or are there locks upon
        [their] hearts?
      - ' Allah has not created the heavens and the earth and what is between them except in truth and for a specified term. And indeed, many of the people, in [the matter of] the meeting with their Lord, are disbelievers.'
  - source_sentence: >-
      Then is he who will shield with his face the worst of the punishment on
      the Day of Resurrection [like one secure from it]
    sentences:
      - ' But you will never find in the way of Allah any change, and you will never find in the way of Allah any alteration.'
      - ' Then We made the sun for it an indication.'
      - ' And it will be said to the wrongdoers, "Taste what you used to earn."'
  - source_sentence: Then is it the judgement of [the time of] ignorance they desire
    sentences:
      - Or do you have a clear authority?
      - >-
        And they both raced to the door, and she tore his shirt from the back,
        and they found her husband at the door. She said, "What is the
        recompense of one who intended evil for your wife but that he be
        imprisoned or a painful punishment?"
      - ' But who is better than Allah in judgement for a people who are certain [in faith].'
  - source_sentence: Say, "Who provides for you from the heaven and the earth
    sentences:
      - Except for our first death, and we will not be punished?"
      - And gave a little and [then] refrained?
      - ' Or who controls hearing and sight and who brings the living out of the dead and brings the dead out of the living and who arranges [every] matter'

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

This is a sentence-transformers model finetuned from Bofandra/fine-tuning-use-cmlm-multilingual-quran-translation. 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-translation
• Maximum Sequence Length: 256 tokens
• Output Dimensionality: 768 tokens
• Similarity Function: Cosine Similarity

Model Sources

• Documentation: Sentence Transformers Documentation
• Repository: Sentence Transformers on GitHub
• Hugging Face: Sentence Transformers on Hugging Face

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:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("Bofandra/fine-tuning-use-cmlm-multilingual-quran-translation-qa")
# Run inference
sentences = [
    'Say, "Who provides for you from the heaven and the earth',
    ' Or who controls hearing and sight and who brings the living out of the dead and brings the dead out of the living and who arranges [every] matter',
    'And gave a little and [then] refrained?',
]
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]

Training Details

Training Dataset

Unnamed Dataset

• Size: 609 training samples
• Columns: sentence_0 and sentence_1
• Approximate statistics based on the first 1000 samples:

  	sentence_0	sentence_1
  type	string	string
  details	min: 3 tokens mean: 29.19 tokens max: 93 tokens	min: 3 tokens mean: 29.93 tokens max: 141 tokens

• Samples:

  sentence_0	sentence_1
  And then there came to them that which they were promised	Shall I inform you upon whom the devils descend?
  But when the truth came to them from Us, they said, "Why was he not given like that which was given to Moses	" Did they not disbelieve in that which was given to Moses before
  Have you not considered the assembly of the Children of Israel after [the time of] Moses when they said to a prophet of theirs, "Send to us a king, and we will fight in the way of Allah "	He said, "Would you perhaps refrain from fighting if fighting was prescribed for you

• Loss: 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

Click to expand

• 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
• eval_on_start: False
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: round_robin

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 3.0.1
• Transformers: 4.42.3
• PyTorch: 2.3.0+cu121
• Accelerate: 0.31.0
• Datasets: 2.20.0
• Tokenizers: 0.19.1

Citation

BibTeX

Sentence Transformers

@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

@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",
}