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
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]

Evaluation

Metrics

Information Retrieval

Datasets: dim_768 and dim_512
Evaluated with InformationRetrievalEvaluator

Metric	dim_768	dim_512
cosine_accuracy@1	0.0824	0.0778
cosine_accuracy@3	0.2484	0.235
cosine_accuracy@5	0.3394	0.3275
cosine_accuracy@10	0.4761	0.4656
cosine_precision@1	0.0824	0.0778
cosine_precision@3	0.0828	0.0783
cosine_precision@5	0.0679	0.0655
cosine_precision@10	0.0476	0.0466
cosine_recall@1	0.0824	0.0778
cosine_recall@3	0.2484	0.235
cosine_recall@5	0.3394	0.3275
cosine_recall@10	0.4761	0.4656
cosine_ndcg@10	0.2582	0.2502
cosine_mrr@10	0.1909	0.1837
cosine_map@100	0.2018	0.1947

Training Details

Training Dataset

json

Dataset: json
Size: 132,576 training samples
Columns: anchor and positive
Approximate statistics based on the first 1000 samples:
anchor positive
type string string
details
min: 2 tokens
mean: 26.94 tokens
max: 199 tokens

min: 298 tokens
mean: 543.71 tokens
max: 1266 tokens

	anchor	positive
type	string	string
details	min: 2 tokens mean: 26.94 tokens max: 199 tokens	min: 298 tokens mean: 543.71 tokens max: 1266 tokens

Samples:

anchor	positive
`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?`	1. Key Legal Issues and Holdings: * 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. * 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. * Admissibility of Corporate Insolvency Resolution Process (CIRP): The court's ruling affected the admissibility of the CIRP against the corporate debtor. 2. Significant Facts of the Case: * The corporate debtor, Triumph Realty Pvt. Ltd., had a pre-existing dispute with the operational creditor, Tech India Engineers Pvt. Ltd. * The operational creditor issued a demand notice dated 11.04.2019, which was received by the corporate debtor on 16.04.2019. * The corporate debtor raised disputes through e-mails dated 04.10.2018, 01.11.2018, and 04.12.2018, among o...
`How does the court assess whether a dispute is genuine or merely spurious, hypothetical, or illusory?`	1. Key Legal Issues and Holdings: * 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. * 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. * 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. * 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. 2. Significant Facts of the Case: * The operational creditor, Nirmal K. Dhiran, supp...
`What are the legal implications of dowry demands and cruelty under Indian law, particularly in the context of Section 498-A IPC?`	1. Key Legal Issues and Holdings: * Dowry and Cruelty: The case revolves around allegations of dowry demands and cruelty by the husband (petitioner) towards his wife. * 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. * 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. 2. Significant Facts of the Case: * The petitioner, Mangat Ram, was convicted under Section 498-A IPC. * He was sentenced to one year imprisonment and a fine. * He appealed the conviction and sentence, which was dismissed. * He then filed a revision petition, seeking a reduction in sentence. * The petitioner had already served over two months in prison. * The complainant (wife) had obtained an ex-parte divorce decree. **3. Cou...

Loss: MatryoshkaLoss 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: adamw_torch_fused
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

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: {'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_fused
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

Training Logs