custom-hindi-emb-model-contrastive

SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2

This is a sentence-transformers model finetuned from sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2. It maps sentences & paragraphs to a 384-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: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 <!-- at revision bf3bf13ab40c3157080a7ab344c831b9ad18b5eb -->
• Maximum Sequence Length: 128 tokens
• Output Dimensionality: 384 tokens
• Similarity Function: Cosine Similarity

<!-- - **Training Dataset:** Unknown --> <!-- - **Language:** Unknown --> <!-- - **License:** Unknown -->

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': 128, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 384, '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("amorfati/custom-hindi-emb-model-contrastive")
# Run inference
sentences = [
    ' Team India : पूरा भरोसा हम चैंपियन बनेंगे... अब चैंपियंस ट्रॉफी और WTC की बारी, जय शाह का बड़ा बयान; कौन होगा कप्तान? ',
    'Team India : कौन होगा टीम इंडिया का नया बॉलिंग कोच? विनय कुमार नहीं! इस वर्ल्ड कप विनर की खुल सकती है किस्मत',
    'Samsung Galaxy Ring हुई लॉन्च, 9 साइज और 3 कलर ऑप्शन में मिलेगी, जानें फीचर्स',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# 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: 1,800 training samples
• Columns: <code>premise</code>, <code>hypothesis</code>, and <code>label</code>
• Approximate statistics based on the first 1000 samples:

  	premise	hypothesis	label
  type	string	string	int
  details	<ul><li>min: 12 tokens</li><li>mean: 31.99 tokens</li><li>max: 52 tokens</li></ul>	<ul><li>min: 12 tokens</li><li>mean: 31.68 tokens</li><li>max: 52 tokens</li></ul>	<ul><li>0: 100.00%</li></ul>

• Samples:

  premise	hypothesis	label
  <code> पति से छिपकर पत्नी का करना चाहिए ये काम, सुधा मूर्ति की ये बात संवार देगी आपकी शादी </code>	<code> Bangladeshi Hindus: 'हिंदू बन गए हैं आसान टारेगट' - ढाका में हमलों के बाद बांग्लादेशी हिंदू ने बताया देश का 'काला सच' </code>	<code>0</code>
  <code> फर्जी कॉल, SMS से लेकर WhatsApp मैसेज तक, Chakshu पोर्टल पर करें हर फ्रॉड की शिकायत, होगी कार्रवाई </code>	<code> विदेशी Trucks में ड्राइवर को सिर्फ AC ही नहीं बल्कि, मिलती हैं ये लग्जरी सुविधाएं </code>	<code>0</code>
  <code> GK Quiz: कौन सा जीव है जिसे अपनी मौत आने से पहले उसे पता चल जाता है? </code>	<code> Indian Army Recruitment 2024: इंडियन आर्मी में निकली डायरेक्ट भर्ती, हवलदार समेत इन पदों पर मिलेगी नौकरी </code>	<code>0</code>

• Loss: <code>ContrastiveLoss</code> with these parameters:

  {
      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
      "margin": 0.5,
      "size_average": true
  }
  

Evaluation Dataset

Unnamed Dataset

• Size: 200 evaluation samples
• Columns: <code>premise</code>, <code>hypothesis</code>, and <code>label</code>
• Approximate statistics based on the first 1000 samples:

  	premise	hypothesis	label
  type	string	string	int
  details	<ul><li>min: 12 tokens</li><li>mean: 31.98 tokens</li><li>max: 61 tokens</li></ul>	<ul><li>min: 12 tokens</li><li>mean: 32.0 tokens</li><li>max: 61 tokens</li></ul>	<ul><li>1: 100.00%</li></ul>

• Samples:

  premise	hypothesis	label
  <code> Vastu Tips: घर के मुख्य दरवाजे पर ये एक चीज लटकाने से दौड़ी आएंगी मां लक्ष्मी, पैसों की तंगी से मिलेगा छुटकारा </code>	<code>Vastu Tips: घर के मुख्य दरवाजे पर ये एक चीज लटकाने से दौड़ी आएंगी मां लक्ष्मी, पैसों की तंगी से मिलेगा छुटकारा</code>	<code>1</code>
  <code> CLAT 2025: कल से शुरू हो रही रज‍िस्‍ट्रेशन प्रक्र‍िया, अप्‍लाई करने के ल‍िए क्‍या योग्‍यता चाह‍िए; क्‍या होगा एग्‍जाम पैटर्न और क‍ितनी होगी फीस जानें </code>	<code>CLAT 2025: कल से शुरू हो रही रज‍िस्‍ट्रेशन प्रक्र‍िया, अप्‍लाई करने के ल‍िए क्‍या योग्‍यता चाह‍िए; क्‍या होगा एग्‍जाम पैटर्न और क‍ितनी होगी फीस जानें</code>	<code>1</code>
  <code> XAT 2025: 15 जुलाई से शुरू होंगे रजिस्ट्रेशन, जानें कैसे भरें एप्लिकेशन फॉर्म </code>	<code>XAT 2025: 15 जुलाई से शुरू होंगे रजिस्ट्रेशन, जानें कैसे भरें एप्लिकेशन फॉर्म</code>	<code>1</code>

• Loss: <code>ContrastiveLoss</code> with these parameters:

  {
      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
      "margin": 0.5,
      "size_average": true
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• learning_rate: 2e-05
• num_train_epochs: 20
• warmup_ratio: 0.1

All Hyperparameters

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

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 1
• eval_accumulation_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: 20
• max_steps: -1
• lr_scheduler_type: linear
• 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: 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: proportional

</details>

Training Logs

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 3.0.1
• Transformers: 4.42.4
• PyTorch: 2.3.1+cu121
• Accelerate: 0.32.1
• 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",
}

ContrastiveLoss

@inproceedings{hadsell2006dimensionality,
    author={Hadsell, R. and Chopra, S. and LeCun, Y.},
    booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)}, 
    title={Dimensionality Reduction by Learning an Invariant Mapping}, 
    year={2006},
    volume={2},
    number={},
    pages={1735-1742},
    doi={10.1109/CVPR.2006.100}
}

<!-- ## 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.* -->