e5-nepali-qa-ir

SentenceTransformer based on intfloat/multilingual-e5-base

This is a sentence-transformers model finetuned from intfloat/multilingual-e5-base. 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: intfloat/multilingual-e5-base <!-- at revision 835193815a3936a24a0ee7dc9e3d48c1fbb19c55 -->
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 dimensions
• 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': 512, 'do_lower_case': False, 'architecture': 'XLMRobertaModel'})
  (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("Funghang/e5-nepali-qa-ir")
# Run inference
queries = [
    "विवाहित व्यक्तिको हकमा साधारण राहदानीको लागि आवेदन कहाँ दिने ?",
]
documents = [
    'ताप्लेजुङ जिल्ला प्रशासन कार्यालयको सम्पर्क नम्बरहरू: नागरिकता फाँट : ०२४-४६०२७०, आर्थिक प्रशासन फाँट : ०२४-४६०५६६, स्थानीय प्रशासन फाँट : ०२४-४६०१९१ हुन् ।',,
    'विवाहित व्यक्तिले आफ्नो स्थायी बसोबास भएको जिल्ला प्रशासन कार्यालय वा नागरिकता रहेको जिल्लास्थित जिल्ला प्रशासन कार्यालयमा आवश्यक कागजात सहित साधारण राहदानीको लागि निवेदन दिन सकिन्छ ।',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 768] [3, 768]

# Get the similarity scores (-1 to 1) for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)


# Convert scores to [0,1] range
similarities_1 = (similarities + 1) / 2

print("\nScaled Similarity Scores (0 to 1):")
print(similarities_1)

<!-- ### 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

Dataset

• Size: 3,840 training samples
• Columns: <code>query</code> and <code>positive</code>
• Approximate statistics based on the first 1000 samples:

  	query	positive
  type	string	string
  details	<ul><li>min: 5 tokens</li><li>mean: 16.31 tokens</li><li>max: 65 tokens</li></ul>	<ul><li>min: 14 tokens</li><li>mean: 40.99 tokens</li><li>max: 338 tokens</li></ul>

• Samples:

  query	positive
  <code>राहदानी कार्यालय संखुवासभाको सम्पर्क नम्बर के हो ?</code>	<code>राहदानी कार्यालय संखुवासभाको सम्पर्क नम्बरहरू ०२९५६०१३४, ०२९५६०१३३, ०२९५६०५३३ हुन् ।</code>
  <code>राहदानीको लागि दर्ता केन्द्र कसरी छनोट गर्ने ?</code>	<code>राहदानी बनाउन दर्ता केन्द्र छनोट गर्दा तपाईंले अनलाइन फाराम भर्दा नै आफ्नो लागि उपयुक्त स्थान चयन गर्नुपर्छ । नेपालमा रहेका जिल्ला वा इलाका प्रशासन कार्यालय वा राहदानी विभाग दर्ता केन्द्रका रूपमा छनोट गर्न सकिन्छ । विदेशमा रहेका नागरिकहरूले भने सम्बन्धित दूतावास वा कन्सुलेटलाई दर्ता केन्द्रका रूपमा छनोट गर्नुपर्छ । साथै, फाराम भर्दा Appointment लिनु पनि अनिवार्य हुन्छ जसले तपाईंलाई सुविधाजनक मिति र समय दिन्छ । यसरी छनोट गरिएको दर्ता केन्द्रमा नै तपाईंले सम्पूर्ण प्रक्रिया पूरा गर्नुपर्छ ।</code>
  <code>म संग राहदानी विभाग काठमाडौंबाट जारी भएको पुरानो हस्तलिखित राहदानी छ भने के मैले पुन राहदानी विभागबाट एमआरपि को लागि आवेदन दिन जिल्लाको सिफारिस ल्याउनु पर्छ ?</code>	<code>यदि तपाईंसँग राहदानी विभाग काठमाडौंबाट जारी भएको पुरानो हस्तलिखित राहदानी छ भने पनि पुन राहदानी विभागबाट एमआरपि को लागि आवेदन दिन जिल्लाको सिफारिस ल्याउनु पर्छ ।</code>

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

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "gather_across_devices": false
  }
  

Evaluation Dataset

Dataset

• Size: 820 evaluation samples
• Columns: <code>query</code> and <code>positive</code>
• Approximate statistics based on the first 820 samples:

  	query	positive
  type	string	string
  details	<ul><li>min: 7 tokens</li><li>mean: 17.08 tokens</li><li>max: 53 tokens</li></ul>	<ul><li>min: 14 tokens</li><li>mean: 45.07 tokens</li><li>max: 175 tokens</li></ul>

• Samples:

  query	positive
  <code>के राहदानी बनाउन फोटोको आवश्यकता पर्छ ?</code>	<code>राहदानी बनाउन फोटोको आवश्यकता हुँदैन, किनभने फोटो खिच्ने काम कार्यालयमै हुन्छ ।</code>
  <code>रुकुम पश्चिमको राहदानी कार्यालयसँग सम्पर्क गर्न कुन नम्बर प्रयोग गर्ने ?</code>	<code>रुकुम पश्चिमको राहदानी कार्यालयका लागि ०८८५३००४०, ०८८५३००९०, ०८८५३००९० नम्बर प्रयोग गर्न सकिन्छ ।</code>
  <code>अफिसियल वा कूटनीतिक राहदानी भएकाले साधारण राहदानी बनाउँदा कुन विकल्प छान्ने ?</code>	<code>अफिसियल र कूटनीतिक राहदानी भएकाले साधारण राहदानी बनाउँदा आफ्नो पुरानो नम्बर बेवास्ता गरी उपयुक्त विकल्प छान्नु पर्छ।</code>

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

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "gather_across_devices": false
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• learning_rate: 3e-05
• num_train_epochs: 5
• warmup_ratio: 0.1
• fp16: True
• load_best_model_at_end: True

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: 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: 3e-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: 5
• 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: True
• 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: 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: None
• hub_always_push: False
• hub_revision: None
• 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
• liger_kernel_config: None
• eval_use_gather_object: False
• average_tokens_across_devices: False
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

</details>

Training Logs

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.12.11
• Sentence Transformers: 5.1.0
• Transformers: 4.55.4
• PyTorch: 2.8.0+cu126
• Accelerate: 1.10.1
• Datasets: 4.0.0
• Tokenizers: 0.21.4

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",
}

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.* -->

Nepali Passport Question Answering: A Low-Resource Dataset for Public Service Applications

@article{begha2026nepali,
  title={Nepali Passport Question Answering: A Low-Resource Dataset for Public Service Applications},
  author={Begha, Funghang Limbu and Acharya, Praveen and Bal, Bal Krishna},
  journal={arXiv preprint arXiv:2603.13320},
  year={2026}
}

Multilingual e5 text embeddings

@article{wang2024multilingual,
  title={Multilingual e5 text embeddings: A technical report},
  author={Wang, Liang and Yang, Nan and Huang, Xiaolong and Yang, Linjun and Majumder, Rangan and Wei, Furu},
  journal={arXiv preprint arXiv:2402.05672},
  year={2024}
}