SentenceTransformer based on rossieRuby/nyayadrishti-bert

This is a sentence-transformers model finetuned from rossieRuby/nyayadrishti-bert. 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: rossieRuby/nyayadrishti-bert
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 dimensions
• 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': 512, '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})
)

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("sentence_transformers_model_id")
# Run inference
sentences = [
    'Article 45 of Indian Constitution',
    'Provision for free and compulsory education for children The State shall endeavour to provide, within a period of ten years from the commencement of this Constitution, for free and compulsory education for all children until they complete the age of fourteen years"\nArticle 46 of Indian Constitution,"Promotion of educational and economic interests of Scheduled Castes, Scheduled Tribes and other weaker sections The State shall promote with special care the educational and economic interests of the weaker sections of the people, and, in particular, of the Scheduled Castes and the Scheduled Tribes, and shall protect them from social injustice and all forms of exploitation","Below is an instruction that describes a task or a question. Write a response that appropriately completes the request.',
    'Extent of executive power of State Subject to the provisions of this Constitution, the executive power of a State shall extend to the matters with respect to which the Legislature of the State has power to make laws Provided that in any matter with respect to which the Legislature of a State and Parliament have power to make laws, the executive power of the State shall be subject to, and limited by, the executive power expressly conferred by the Constitution or by any law made by Parliament upon the Union or authorities thereof Council of Ministers"\nArticle 163 of Indian Constitution,"Council of Ministers to aid and advise Governor\n(1) There shall be a council of Ministers with the chief Minister at the head to aid and advise the Governor in the exercise of his functions, except in so far as he is by or under this constitution required to exercise his functions or any of them in his discretion\n(2) If any question arises whether any matter is or is not a matter as respects which the Governor is by or under this Constitution required to act in his discretion, the decision of the Governor in his discretion shall be final, and the validity of anything done by the Governor shall not be called in question on the ground that he ought or ought not to have acted in his discretion\n(3) The question whether any, and if so what, advice was tendered by Ministers to the Governor shall not be inquired into in any court","Below is an instruction that describes a task or a question. Write a response that appropriately completes the request.',
]
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: 999 training samples
• Columns: sentence_0, sentence_1, and label
• Approximate statistics based on the first 999 samples:

  	sentence_0	sentence_1	label
  type	string	string	float
  details	min: 7 tokens mean: 13.33 tokens max: 100 tokens	min: 3 tokens mean: 210.82 tokens max: 512 tokens	min: 1.0 mean: 1.0 max: 1.0

• Samples:

  sentence_0	sentence_1	label
  What can I do if I disagree with the amount of outstanding demand?	​​You can choose ‘Disagree with Demand (Either in Full or Part)’. After you select the option, you need to select from the list of reasons due to which you disagree with the amount of demand. After selecting the relevant option from the list, you need to provide details for each reason before submitting the response. If you partially disagree with the demand, you should pay the undisputed portion of the demand (i.e. with which you agree).​​	1.0
  Article 48A of Indian Constitution	Protection and improvement of environment and safeguarding of forests and wild life The State shall endeavour to protect and improve the environment and to safeguard the forests and wild life of the country" Article 49 of Indian Constitution,"Protection of monuments and places and objects of national importance It shall be the obligation of the State to protect every monument or place or object of artistic or historic interests, declared by or under law made by Parliament to be of national importance, from spoliation, disfigurement, destruction, removal, disposal or export, as the case may be","Below is an instruction that describes a task or a question. Write a response that appropriately completes the request.	1.0
  Article 165 of Indian Constitution	Advocate General for the State (1) The Governor of each State shall appoint a person who is qualified to be appointed a Judge of a High Court to be Advocate General for the State (2) It shall be the duty of the Advocate General to give advice to the Government of the State upon such legal matters, and to perform such other duties of a legal character, as may from time to time be referred or assigned to him by the Governor, and to discharge the functions conferred on him by or under this Constitution or any other law for the time being in force (3) The Advocate General shall hold office during the pleasure of the Governor, and shall receive such remuneration as the Governor may determine Conduct of Government Business" Article 166 of Indian Constitution,"Conduct of business of the Government of a State (1) All executive action of the Government of a State shall be expressed to be taken in the name of the Governor (2) Orders and other instruments made and executed in the name of the Gove...	1.0

• Loss: CosineSimilarityLoss with these parameters:

  {
      "loss_fct": "torch.nn.modules.loss.MSELoss"
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• num_train_epochs: 0.1
• 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: 8
• per_device_eval_batch_size: 8
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 1
• eval_accumulation_steps: None
• torch_empty_cache_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: 0.1
• 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}
• tp_size: 0
• 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: None
• hub_always_push: False
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• include_for_metrics: []
• 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
• 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
• use_liger_kernel: False
• eval_use_gather_object: False
• average_tokens_across_devices: False
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: round_robin

Framework Versions

• Python: 3.11.12
• Sentence Transformers: 3.4.1
• Transformers: 4.51.3
• PyTorch: 2.6.0+cu124
• Accelerate: 1.6.0
• Datasets: 3.6.0
• Tokenizers: 0.21.1

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",
}