--- language: - nep license: apache-2.0 tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:1046 - loss:MatryoshkaLoss - loss:MultipleNegativesRankingLoss base_model: jangedoo/all-MiniLM-L6-v2-nepali widget: - source_sentence: राहदानीको लागि कागजात सत्यापनमा कस्तो मनोनयनपत्र चाहिन्छ? sentences: - सिम्यान्स अभिलेख किताबको लागि निवेदन फाराम अनुसूची-२क बमोजिमको ढाँचामा आधारित हुन्छ। - कुटनीतिक वा विशेष राहदानीको लागि कागजात सत्यापनमा सम्बन्धित पदमा नियुक्तिको मनोनयनपत्रको प्रमाणित प्रतिलिपि चाहिन्छ। - राहदानी रद्द गर्न महानिर्देशकले स्वीकृति दिन्छ। - source_sentence: राहदानी वितरणमा त्रुटि सच्याउन कति समय लाग्छ? sentences: - राहदानी नियमावली, २०७७ मा अभिलेखको गोपनीयताको उल्लङ्घनको जाँचको नतिजाको अपीलको नतिजाको कार्यान्वयनको अभिलेख बाह्र वर्षसम्म राखिन्छ। - राहदानी वितरणमा त्रुटि सच्याउन सामान्यतः सात कार्यदिन लाग्छ, तर प्रक्रिया जटिल भएमा बढी समय लाग्न सक्छ। - राहदानीको लागि निवेदनमा जाँच गर्ने अधिकारीको नाम, सही, पद, र मिति उल्लेख गर्नुपर्छ। - source_sentence: राहदानीको लागि निवेदनमा कस्तो आवेदन स्रोत उल्लेख गर्नुपर्छ? sentences: - राहदानीको लागि निवेदनमा आवेदन स्रोत (विभाग, जिल्ला, वा नियोग) उल्लेख गर्नुपर्छ। - राहदानी बुझाउने प्रक्रियामा त्रुटि सच्याउन सामान्यतः सात कार्यदिन लाग्छ, तर प्रक्रिया जटिल भएमा बढी समय लाग्न सक्छ। - राहदानीको लिए अनलाइन निवेदनमा निकटतम व्यक्तिसँगको सम्बन्ध (Relationship) उल्लेख गर्नुपर्छ। - source_sentence: विशेष राहदानी कसलाई जारी गरिन्छ? sentences: - राहदानी रद्द गर्न बाहक वा सम्बन्धित निकायको लिखित निवेदन चाहिन्छ। - राहदानी नियमावली, २०७७ मा अभिलेखको गोपनीयताको उल्लङ्घनको जाँचको नतिजाको अपीलको लागि जाँच गर्ने अधिकारीको नाम, सही, पद, र मिति उल्लेख गर्नुपर्छ। - विशेष राहदानी नगरपालिकाका प्रमुख, सहसचिव, जिल्ला न्यायाधीश, प्रदेश लोकसेवा आयोगका सदस्य, लगायतका पदाधिकारीलाई जारी गरिन्छ। - source_sentence: कुटनीतिक राहदानीको लागि निवेदनमा कस्तो ठेगाना विवरण चाहिन्छ? sentences: - कुटनीतिक राहदानीको लागि निवेदनमा जिल्ला, गाउँ/नगरपालिका, वडा नम्बर, गाउँ/सडक, र घर नम्बरको ठेगाना विवरण चाहिन्छ। - राहदानीको लागि कागजात धुल्याउने प्रक्रिया महानिर्देशकको स्वीकृतिमा हुन्छ। - राहदानीको विद्युतीय अभिलेख अनुसूची-७ बमोजिमको ढाँचामा आधारित हुन्छ। pipeline_tag: sentence-similarity library_name: sentence-transformers metrics: - cosine_accuracy@1 - cosine_accuracy@3 - cosine_accuracy@5 - cosine_accuracy@10 - cosine_precision@1 - cosine_precision@3 - cosine_precision@5 - cosine_precision@10 - cosine_recall@1 - cosine_recall@3 - cosine_recall@5 - cosine_recall@10 - cosine_ndcg@10 - cosine_mrr@10 - cosine_map@100 model-index: - name: sentenceTransformer_nepali_embedding results: - task: type: information-retrieval name: Information Retrieval dataset: name: dim 384 type: dim_384 metrics: - type: cosine_accuracy@1 value: 0.41025641025641024 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.6581196581196581 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.7350427350427351 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.8461538461538461 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.41025641025641024 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.21937321937321935 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.14700854700854699 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.0846153846153846 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.41025641025641024 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.6581196581196581 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.7350427350427351 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.8461538461538461 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.6218282635615644 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.5504409171075837 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.5571750406212126 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 256 type: dim_256 metrics: - type: cosine_accuracy@1 value: 0.42735042735042733 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.6410256410256411 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.717948717948718 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.8290598290598291 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.42735042735042733 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.21367521367521364 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.14358974358974358 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.08290598290598289 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.42735042735042733 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.6410256410256411 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.717948717948718 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.8290598290598291 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.6159996592171239 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.5487959571292905 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.5563599760664051 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 128 type: dim_128 metrics: - type: cosine_accuracy@1 value: 0.39316239316239315 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.5811965811965812 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.6752136752136753 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.8034188034188035 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.39316239316239315 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.19373219373219372 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.135042735042735 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.08034188034188033 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.39316239316239315 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.5811965811965812 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.6752136752136753 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.8034188034188035 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.5799237272193319 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.5100054266720935 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.5176470843483384 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 64 type: dim_64 metrics: - type: cosine_accuracy@1 value: 0.38461538461538464 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.5811965811965812 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.6410256410256411 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.7606837606837606 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.38461538461538464 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.1937321937321937 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.12820512820512817 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.07606837606837605 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.38461538461538464 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.5811965811965812 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.6410256410256411 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.7606837606837606 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.565217766093051 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.5036663953330621 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.5140223584530523 name: Cosine Map@100 --- # sentenceTransformer_nepali_embedding This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [jangedoo/all-MiniLM-L6-v2-nepali](https://huggingface.co/jangedoo/all-MiniLM-L6-v2-nepali) on the json dataset. 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:** [jangedoo/all-MiniLM-L6-v2-nepali](https://huggingface.co/jangedoo/all-MiniLM-L6-v2-nepali) - **Maximum Sequence Length:** 256 tokens - **Output Dimensionality:** 384 dimensions - **Similarity Function:** Cosine Similarity - **Training Dataset:** - json - **Language:** nep - **License:** apache-2.0 ### Model Sources - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers) - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) ### Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 256, '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}) (2): Normalize() ) ``` ## Usage ### Direct Usage (Sentence Transformers) First install the Sentence Transformers library: ```bash pip install -U sentence-transformers ``` Then you can load this model and run inference. ```python from sentence_transformers import SentenceTransformer # Download from the 🤗 Hub model = SentenceTransformer("ritesh-07/fine_tuned_model_02") # Run inference sentences = [ 'कुटनीतिक राहदानीको लागि निवेदनमा कस्तो ठेगाना विवरण चाहिन्छ?', 'कुटनीतिक राहदानीको लागि निवेदनमा जिल्ला, गाउँ/नगरपालिका, वडा नम्बर, गाउँ/सडक, र घर नम्बरको ठेगाना विवरण चाहिन्छ।', 'राहदानीको लागि कागजात धुल्याउने प्रक्रिया महानिर्देशकको स्वीकृतिमा हुन्छ।', ] 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] ``` ## Evaluation ### Metrics #### Information Retrieval * Dataset: `dim_384` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters: ```json { "truncate_dim": 384 } ``` | Metric | Value | |:--------------------|:-----------| | cosine_accuracy@1 | 0.4103 | | cosine_accuracy@3 | 0.6581 | | cosine_accuracy@5 | 0.735 | | cosine_accuracy@10 | 0.8462 | | cosine_precision@1 | 0.4103 | | cosine_precision@3 | 0.2194 | | cosine_precision@5 | 0.147 | | cosine_precision@10 | 0.0846 | | cosine_recall@1 | 0.4103 | | cosine_recall@3 | 0.6581 | | cosine_recall@5 | 0.735 | | cosine_recall@10 | 0.8462 | | **cosine_ndcg@10** | **0.6218** | | cosine_mrr@10 | 0.5504 | | cosine_map@100 | 0.5572 | #### Information Retrieval * Dataset: `dim_256` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters: ```json { "truncate_dim": 256 } ``` | Metric | Value | |:--------------------|:----------| | cosine_accuracy@1 | 0.4274 | | cosine_accuracy@3 | 0.641 | | cosine_accuracy@5 | 0.7179 | | cosine_accuracy@10 | 0.8291 | | cosine_precision@1 | 0.4274 | | cosine_precision@3 | 0.2137 | | cosine_precision@5 | 0.1436 | | cosine_precision@10 | 0.0829 | | cosine_recall@1 | 0.4274 | | cosine_recall@3 | 0.641 | | cosine_recall@5 | 0.7179 | | cosine_recall@10 | 0.8291 | | **cosine_ndcg@10** | **0.616** | | cosine_mrr@10 | 0.5488 | | cosine_map@100 | 0.5564 | #### Information Retrieval * Dataset: `dim_128` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters: ```json { "truncate_dim": 128 } ``` | Metric | Value | |:--------------------|:-----------| | cosine_accuracy@1 | 0.3932 | | cosine_accuracy@3 | 0.5812 | | cosine_accuracy@5 | 0.6752 | | cosine_accuracy@10 | 0.8034 | | cosine_precision@1 | 0.3932 | | cosine_precision@3 | 0.1937 | | cosine_precision@5 | 0.135 | | cosine_precision@10 | 0.0803 | | cosine_recall@1 | 0.3932 | | cosine_recall@3 | 0.5812 | | cosine_recall@5 | 0.6752 | | cosine_recall@10 | 0.8034 | | **cosine_ndcg@10** | **0.5799** | | cosine_mrr@10 | 0.51 | | cosine_map@100 | 0.5176 | #### Information Retrieval * Dataset: `dim_64` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters: ```json { "truncate_dim": 64 } ``` | Metric | Value | |:--------------------|:-----------| | cosine_accuracy@1 | 0.3846 | | cosine_accuracy@3 | 0.5812 | | cosine_accuracy@5 | 0.641 | | cosine_accuracy@10 | 0.7607 | | cosine_precision@1 | 0.3846 | | cosine_precision@3 | 0.1937 | | cosine_precision@5 | 0.1282 | | cosine_precision@10 | 0.0761 | | cosine_recall@1 | 0.3846 | | cosine_recall@3 | 0.5812 | | cosine_recall@5 | 0.641 | | cosine_recall@10 | 0.7607 | | **cosine_ndcg@10** | **0.5652** | | cosine_mrr@10 | 0.5037 | | cosine_map@100 | 0.514 | ## Training Details ### Training Dataset #### json * Dataset: json * Size: 1,046 training samples * Columns: anchor and positive * Approximate statistics based on the first 1000 samples: | | anchor | positive | |:--------|:-----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------| | type | string | string | | details | | | * Samples: | anchor | positive | |:----------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------| | राहदानी नियमावली, २०७७ मा अभिलेखको गोपनीयताको उल्लङ्घनको जाँचको नतिजाको अपील कसले जाँच गर्छ? | राहदानी नियमावली, २०७७ मा अभिलेखको गोपनीयताको उल्लङ्घनको जाँचको नतिजाको अपील मन्त्रालयले तोकेको समितिले जाँच गर्छ। | | राहदानी नियमावली, २०७७ मा सत्यापनको लागि कस्तो सही चाहिन्छ? | राहदानी नियमावली, २०७७ मा सत्यापनको लागि निवेदकको सही, र नाबालकको हकमा बाबु, आमा, वा संरक्षकको सही चाहिन्छ। | | राहदानी नियमावली, २०७७ मा कस्तो निकायले राहदानी जारी गर्छ? | राहदानी नियमावली, २०७७ मा विभाग, नियोग, वा जिल्ला प्रशासन कार्यालयले राहदानी जारी गर्छ। | * Loss: [MatryoshkaLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters: ```json { "loss": "MultipleNegativesRankingLoss", "matryoshka_dims": [ 384, 256, 128, 64 ], "matryoshka_weights": [ 1, 1, 1, 1 ], "n_dims_per_step": -1 } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: epoch - `per_device_train_batch_size`: 32 - `per_device_eval_batch_size`: 16 - `gradient_accumulation_steps`: 16 - `learning_rate`: 2e-05 - `num_train_epochs`: 4 - `lr_scheduler_type`: cosine - `warmup_ratio`: 0.1 - `bf16`: True - `tf32`: False - `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`: 32 - `per_device_eval_batch_size`: 16 - `per_gpu_train_batch_size`: None - `per_gpu_eval_batch_size`: None - `gradient_accumulation_steps`: 16 - `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`: False - `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`: no_duplicates - `multi_dataset_batch_sampler`: proportional
### Training Logs | Epoch | Step | Training Loss | dim_384_cosine_ndcg@10 | dim_256_cosine_ndcg@10 | dim_128_cosine_ndcg@10 | dim_64_cosine_ndcg@10 | |:-------:|:-----:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:| | 1.0 | 3 | - | 0.5232 | 0.5074 | 0.4679 | 0.4451 | | 2.0 | 6 | - | 0.5891 | 0.5703 | 0.5555 | 0.5275 | | **3.0** | **9** | **-** | **0.6108** | **0.6052** | **0.5815** | **0.5594** | | 3.4848 | 10 | 2.5112 | - | - | - | - | | 4.0 | 12 | - | 0.6218 | 0.6160 | 0.5799 | 0.5652 | * The bold row denotes the saved checkpoint. ### Framework Versions - Python: 3.11.13 - Sentence Transformers: 4.1.0 - Transformers: 4.53.2 - PyTorch: 2.6.0+cu124 - Accelerate: 1.9.0 - Datasets: 4.0.0 - Tokenizers: 0.21.2 ## Citation ### BibTeX #### Sentence Transformers ```bibtex @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 ```bibtex @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 ```bibtex @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} } ```