Tejasw1/votum-case-law-v1

GTE-base Votum Case Law

This is a sentence-transformers model finetuned from Alibaba-NLP/gte-base-en-v1.5 on the json dataset. 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: Alibaba-NLP/gte-base-en-v1.5 <!-- at revision a829fd0e060bb84554da0dfd354d0de0f7712b7f -->
• —Maximum Sequence Length: 8192 tokens
• —Output Dimensionality: 768 dimensions
• —Similarity Function: Cosine Similarity
• —Training Dataset:
• —json
• —Language: en
• —License: apache-2.0

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': 8192, 'do_lower_case': False}) with Transformer model: NewModel 
  (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})
)

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("Tejasw1/votum-case-law-v1")
# Run inference
sentences = [
    'What role does the liquidator play in verifying the claims and charges of secured creditors during the liquidation of a corporate debtor?',
    "**1. Key Legal Issues and Holdings:**\n\n* **Priority of Charges:** The main legal issue is the priority of charges on the secured assets of the corporate debtor, Reid and Taylor India Ltd.\n* **Insolvency and Bankruptcy Code, 2016:** The court considered the provisions of the Insolvency and Bankruptcy Code, 2016, particularly Section 52 and Regulation 37 of the Insolvency and Bankruptcy Board of India (Liquidation Process) Regulations, 2016.\n* **Security Interest:** The court examined the security interest held by the applicant, Finquest Financial Solutions P. Ltd., and other financial creditors, including Edelweiss Asset Reconstruction Co. Ltd.\n* **Entitlement to Realize Security Interest:** The court held that the applicant is entitled to realize their security interest in the manner specified under Section 52(1)(b) read with Regulation 37 of the IBBI (Liquidation Process) Regulations, 2016.\n\n**2. Significant Facts of the Case:**\n\n* The applicant, Finquest Financial Solutions P. Ltd., is a secured creditor with a first pari passu charge on the immovable fixed assets of the corporate debtor.\n* Edelweiss Asset Reconstruction Co. Ltd. is also a secured creditor with a claim on the same assets.\n* The corporate debtor, Reid and Taylor India Ltd., has been under liquidation.\n* Suit No. 84 of 2013 is pending in the Civil Judge (Senior Division), Nanjangud, challenging the first charge created by IDM.\n* The liquidator has verified the documents and found that the applicant is the sole first charge holder of the immovable property of the corporate debtor at Mysore.\n* The Edelweiss had not obtained an NOC from the IDM and had not ventilated their grievance or enforced their rights before any forum.\n\n**3. Court's Ruling:**\n\n* The court ruled that the applicant, Finquest Financial Solutions P. Ltd., is entitled to realize their security interest in the manner specified under Section 52(1)(b) read with Regulation 37 of the IBBI (Liquidation Process) Regulations, 2016.\n* The court held that the applicant is the first charge holder of the immovable fixed assets of the corporate debtor.\n* The court dismissed the objection of Edelweiss Asset Reconstruction Co. Ltd. regarding the priority of charges.\n* The court directed the liquidator to hand over the symbolic possession of the fixed assets of the corporate debtor to the applicant to enable them to proceed with the sale of the assets.\n* The court directed the liquidator to inform the Tribunal about the manner and progress of the sale of assets from time-to-time for further directions/instructions.\n\n**4. Citations:**\n\n* **Insolvency and Bankruptcy Code, 2016**\n* **Regulation 37 of the Insolvency and Bankruptcy Board of India (Liquidation Process) Regulations, 2016**\n* **Suit No. 84 of 2013 filed with the Court of Civil Judge (Senior Division), Nanjangud, Karnataka**",
    "**1. Key Legal Issues and Holdings:**\n\n* **Dowry and Cruelty:** The case revolves around allegations of dowry demands and cruelty by the husband (petitioner) towards his wife.\n* **Section 498-A IPC:** The main legal issue is the application of Section 498-A of the Indian Penal Code, 1860, which deals with cruelty by the husband or his relatives towards a married woman.\n* **Sentencing:** The court considered the appropriateness of the sentence awarded to the petitioner under Section 498-A IPC.\n\n**2. Significant Facts of the Case:**\n\n* The petitioner, Mangat Ram, was convicted under Section 498-A IPC.\n* He was sentenced to one year imprisonment and a fine.\n* He appealed the conviction and sentence, which was dismissed.\n* He then filed a revision petition, seeking a reduction in sentence.\n* The petitioner had already served over two months in prison.\n* The complainant (wife) had obtained an ex-parte divorce decree.\n\n**3. Court's Ruling:**\n\n* The High Court upheld the conviction of the petitioner under Section 498-A IPC.\n* The court reduced the sentence to the period already undergone by the petitioner.\n* The court enhanced the fine to Rs. 5000/-.\n\n**4. Citations:**\n\n* **Yogendra Yadav v. State of Jharkhand**, Criminal Appeal No. 1205 of 2014\n* **Lajpat Rai v. State of Haryana**, Criminal Revision No. 1380 of 1999\n\n**Refined Summary (Updated):**\n\n**1. Key Legal Issues and Holdings:**\n\n* **Default Bail under Section 167(2) Cr.P.C.:** The court considered the applicability of default bail under Section 167(2) Cr.P.C. in cases where the investigating agency fails to file the final report within the prescribed time limit.\n* **Investigation and Filing of Challan:** The court held that the investigation is not considered incomplete merely because the investigating officer awaits reports of experts or fails to append certain documents to the police report.\n* **Role of the Court:** The court emphasized its role in determining whether to permit the prosecutor to adduce evidence of experts and to balance the interest of the accused with the interest of justice.\n\n**2. Significant Facts of the Case:**\n\n* The petitioners, Sukhwinder Kumar @ Sukha, Harpreet Singh @ Bahadur, Navjit Singh, and Rakesh Kumar @ Kesha, were accused of offenses under the Narcotic Drugs and Psychotropic Substances (NDPS) Act, 1985.\n* They filed revision petitions seeking default bail under Section 167(2) Cr.P.C.\n* The prosecution opposed their claims, arguing that the investigating agency had not failed to file the final report within the prescribed time limit.\n* The court considered the rival contentions and held that the petitioners were entitled to default bail.\n\n**3. Court's Ruling:**\n\n* The court disposed of the revision petitions, releasing the petitioners on interim bail till the filing of the report under Section 173 Cr.P.C.\n* The court emphasized the importance of the investigating agency and the prosecuting agency complying with statutory provisions to avoid delay in completing investigations and filing challans.\n* The court noted that the respondent-State had failed to comply with statutory provisions, resulting in the accused getting benefit of default bail.\n\n**4. Citations:**\n\n* **Abdul Azeez P.V. v. National Investigation Agency**, 2015 (1) RCR (Criminal) 239\n* **Mehal Singh v. State of Haryana**, 1978 PLR 480",
]
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. -->

Evaluation

Metrics

Information Retrieval

• —Datasets: dim_768 and dim_512
• —Evaluated with <code>InformationRetrievalEvaluator</code>

<!--

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

json

• —Dataset: json
• —Size: 132,576 training samples
• —Columns: <code>anchor</code> and <code>positive</code>
• —Approximate statistics based on the first 1000 samples: | | anchor | positive | |:--------|:-----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------| | type | string | string | | details | <ul><li>min: 2 tokens</li><li>mean: 26.94 tokens</li><li>max: 199 tokens</li></ul> | <ul><li>min: 298 tokens</li><li>mean: 543.71 tokens</li><li>max: 1266 tokens</li></ul> |
• —Samples: | anchor | positive | |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | <code>What are the legal implications of a court setting aside an order related to the initiation of a Corporate Insolvency Resolution Process due to a pre-existing dispute?</code> | <code>1. Key Legal Issues and Holdings:<br><br> Existence of Dispute: The main legal issue is whether there was an existence of dispute prior to the issuance of the Demand Notice dated 11.04.2019.<br> Section 8 of IBC: The court considered the application of Section 8 of the Insolvency and Bankruptcy Code, 2016, which deals with the requirement of a dispute to be raised by the corporate debtor in response to a demand notice.<br> Admissibility of Corporate Insolvency Resolution Process (CIRP): The court's ruling affected the admissibility of the CIRP against the corporate debtor.<br><br>2. Significant Facts of the Case:<br><br> The corporate debtor, Triumph Realty Pvt. Ltd., had a pre-existing dispute with the operational creditor, Tech India Engineers Pvt. Ltd.<br> The operational creditor issued a demand notice dated 11.04.2019, which was received by the corporate debtor on 16.04.2019.<br> The corporate debtor raised disputes through e-mails dated 04.10.2018, 01.11.2018, and 04.12.2018, among o...</code> | | <code>How does the court assess whether a dispute is genuine or merely spurious, hypothetical, or illusory?</code> | <code>1. Key Legal Issues and Holdings:<br><br> Existence of Dispute: The court considered whether a dispute existed between the parties before the issuance of the Demand Notice under Section 9 of the Insolvency and Bankruptcy Code, 2016.<br> Pre-existing Dispute: The court relied on the principle laid down by the Hon'ble Supreme Court in "Mobilox Innovations Private Limited v. KIRUSA Software Pvt. Ltd." that a dispute must be pre-existing before the receipt of the Demand Notice.<br> Section 8 of the Code: The court analyzed the provisions of Section 8 of the Code, which deals with the procedure for an operational creditor to initiate insolvency proceedings against a corporate debtor.<br> Nature of Dispute: The court held that the dispute was genuine and not spurious, hypothetical, or illusory, and that the corporate debtor had raised a plausible contention that required further investigation.<br><br>2. Significant Facts of the Case:<br><br> The operational creditor, Nirmal K. Dhiran, supp...</code> | | <code>What are the legal implications of dowry demands and cruelty under Indian law, particularly in the context of Section 498-A IPC?</code> | <code>1. Key Legal Issues and Holdings:<br><br> Dowry and Cruelty: The case revolves around allegations of dowry demands and cruelty by the husband (petitioner) towards his wife.<br> Section 498-A IPC: The main legal issue is the application of Section 498-A of the Indian Penal Code, 1860, which deals with cruelty by the husband or his relatives towards a married woman.<br> Rent Control and Eviction: The case also involves a dispute over rent control and eviction under the Uttar Pradesh Urban Buildings (Regulation of Letting, Rent and Eviction) Act, 1972.<br><br>2. Significant Facts of the Case:<br><br> The petitioner, Mangat Ram, was convicted under Section 498-A IPC.<br> He was sentenced to one year imprisonment and a fine.<br> He appealed the conviction and sentence, which was dismissed.<br> He then filed a revision petition, seeking a reduction in sentence.<br> The petitioner had already served over two months in prison.<br> The complainant (wife) had obtained an ex-parte divorce decree.<br><br>**3. Cou...</code> |
• —Loss: <code>MatryoshkaLoss</code> with these parameters:

  {
      "loss": "MultipleNegativesRankingLoss",
      "matryoshka_dims": [
          768,
          512
      ],
      "matryoshka_weights": [
          1,
          1
      ],
      "n_dims_per_step": -1
  }

Training Hyperparameters

Non-Default Hyperparameters

• —eval_strategy: epoch
• —gradient_accumulation_steps: 8
• —learning_rate: 2e-05
• —num_train_epochs: 4
• —lr_scheduler_type: cosine
• —warmup_ratio: 0.1
• —bf16: True
• —tf32: True
• —load_best_model_at_end: True
• —optim: adamwtorchfused
• —batch_sampler: no_duplicates

All Hyperparameters

<details><summary>Click to expand</summary>

• —overwrite_output_dir: False
• —do_predict: False
• —eval_strategy: epoch
• —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: 8
• —eval_accumulation_steps: None
• —torch_empty_cache_steps: None
• —learning_rate: 2e-05
• —weight_decay: 0.0
• —adam_beta1: 0.9
• —adam_beta2: 0.999
• —adam_epsilon: 1e-08
• —max_grad_norm: 1.0
• —num_train_epochs: 4
• —max_steps: -1
• —lr_scheduler_type: cosine
• —lr_scheduler_kwargs: {}
• —warmup_ratio: 0.1
• —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: True
• —fp16: False
• —fp16_opt_level: O1
• —half_precision_backend: auto
• —bf16_full_eval: False
• —fp16_full_eval: False
• —tf32: True
• —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: True
• —ignore_data_skip: False
• —fsdp: []
• —fsdp_min_num_params: 0
• —fsdp_config: {'minnumparams': 0, 'xla': False, 'xlafsdpv2': False, 'xlafsdpgrad_ckpt': False}
• —fsdp_transformer_layer_cls_to_wrap: None
• —accelerator_config: {'splitbatches': False, 'dispatchbatches': None, 'evenbatches': True, 'useseedablesampler': True, 'nonblocking': False, 'gradientaccumulationkwargs': None}
• —deepspeed: None
• —label_smoothing_factor: 0.0
• —optim: adamwtorchfused
• —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
• —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
• —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
• —use_liger_kernel: False
• —eval_use_gather_object: False
• —average_tokens_across_devices: False
• —prompts: None
• —batch_sampler: no_duplicates
• —multi_dataset_batch_sampler: proportional

</details>

Training Logs

<details><summary>Click to expand</summary>

• —The bold row denotes the saved checkpoint. </details>

Framework Versions

• —Python: 3.11.5
• —Sentence Transformers: 3.3.1
• —Transformers: 4.46.3
• —PyTorch: 2.4.1+cu121
• —Accelerate: 0.34.2
• —Datasets: 3.0.0
• —Tokenizers: 0.20.3

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",
}

MatryoshkaLoss

@misc{kusupati2024matryoshka,
    title={Matryoshka Representation Learning},
    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
    year={2024},
    eprint={2205.13147},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

MultipleNegativesRankingLoss

@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. -->