metadata

base_model: TaylorAI/bge-micro-v2
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
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:1814
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
widget:
  - source_sentence: >-

      Based on the provided information, it seems like you are listing various
      substances and the potential side effects associated with them. Here's a
      summary:


      **Substances and Related Side Effects:**


      1. **Amitriptyline**
         - Hyperkeratosis
         - Muscle weakness
         - Abnormal macular morphology
         - Visual impairment
         - Anxiety
         - Abnormality of the endocrine system
         - Hypothyroidism
         - Inflammatory abnormality of the skin
         - Eczema
         - Skin ulcer
         - Erythema
         - Jaundice
         - Hyperhidrosis
         - Blurred vision
         - Abnormality of extrapyramidal motor function
         - Hepatic steatosis
         - Increased body weight
         - Arrhythmia
         - Supraventricular arrhythmia
         - Congestive heart failure
         - Abnormality of blood and blood-forming tissues
         - Thrombocytopenia
         - Renal insufficiency
         - Fever
         - Hypoglycemia
         - Dehydration
         - Pain
         - Esophageal stenosis
         - Gait disturbance
        
    sentences:
      - >-
        Can you provide me with a list of medications that could cause loss of
        appetite and a smooth tongue sensation as side effects?
      - >-
        What are the secondary diseases related to breast cancer characterized
        by gene expression changes associated with genomic variations affecting
        cell growth and division, and present symptoms like pain, fatigue,
        breathing problems, vomiting, changes in bowel movements, and wasting,
        particularly during treatment?
      - >-
        Which drugs targeting the dopamine transporter encoded by SLC6A3 gene
        are approved for managing Major Depressive Disorder, Generalized Anxiety
        Disorder, neuropathic pain, osteoarthritis, and stress urinary
        incontinence?
  - source_sentence: >-

      Alvespimycin, a derivative of Geldanamycin and a Heat Shock Protein 90
      (HSP90) inhibitor, falls under the drug category on DrugBank. It
      encompasses Amides, HSP90 Heat-Shock Proteins, Lactams, and Quinones. This
      compound is currently under investigation for its antineoplastic potential
      in treating solid tumors, advanced solid tumors, or acute myeloid
      leukemia. Alvespimycin's typical half-life spans from 9.9 to 54.1 hours,
      with a median duration of 18.2 hours, making it a longer-acting drug in
      its pharmacodynamics profile. Alvespimycin functions by inhibiting HSP90,
      which consequently disrupts the correct folding and function of
      oncoproteins derived from HSP90 client proteins, a critical role in
      cellular proliferation, and apoptosis suppression. The medication targets
      oncogenic kinases like BRAF, inducing their proteasomal degradation and
      facilitating depletion of oncoproteins. Notably, Alvespimycin shows a
      minimal degree of protein binding and is more selective in its effect on
      tumors compared to normal tissues. The drug also aids in increasing the
      potency of telomerase inhibition by imetelstat, as demonstrated in
      pre-clinical models of human osteosarcoma.
    sentences:
      - >-
        Could you give me a list of medications that interact with the HSP90AA1
        gene or protein and have a metabolic half-life ranging from 9.9 to 54.1
        hours?
      - >-
        Which diseases are categorized as forerunners or variations of benign
        cervical tumors in current medical classifications?
      - >-
        Can you give me an overview of diseases related to SLC13A5 gene
        abnormalities that involve dysregulation of enzyme activity?
  - source_sentence: >-

      The gene DRAXIN, also known by various aliases such as 'AGPA3119',
      'C1orf187', 'UNQ3119', and 'neucrin', is located on chromosome 1 in the
      genomic region defined by its start position at 11691710 and end position
      at 11725857. DRAXIN, classified as "dorsal inhibitory axon guidance
      protein", is predicted to play a role in the inhibition of the canonical
      Wnt signaling pathway, negative regulation of neuron projection
      development, and nervous system development. It is also indicated to be
      active in the extracellular region.


      Studies have revealed that this protein interacts with another gene (NTN1)
      and is associated with a range of diseases including Parkinson disease,
      juvenile onset Parkinson disease 19A, early-onset
      parkinsonism-intellectual disability syndrome, parkinsonian-pyramidal
      syndrome, X-linked parkinsonism-spasticity syndrome,
      hemiparkinsonism-hemiatrophy syndrome, atypical juvenile parkinsonism, and
      hereditary late onset Parkinson disease. It is involved across various
      biological processes such as Wnt signaling pathway, negative regulation of
      the canonical Wnt pathway, negative regulation of axon extension, and
      negative regulation of neuron apoptotic process. DRAXIN is known to have
      expression in numerous anatomical entities like blood, prefrontal cortex,
      female reproductive system, brain, cerebral cortex, uterus, endometrium,
      frontal cortex, temporal lobe, amygdala, forebrain, neocortex, Ammon's
      horn, cerebellum, cerebellar cortex, and dorsolateral prefrontal cortex;
      however, its expression is absent in colonic mucosa, quadriceps femoris,
      vastus lateralis, deltoid, biceps
    sentences:
      - >-
        What are the common Alzheimer's treatments that could cause chest
        discomfort, and can you list those with a duration of effect lasting
        about three days?
      - >-
        Which genes or proteins are not expressed in either the small intestinal
        or colonic mucosal tissues?
      - >-
        Identify the Y-linked gene associated with spermatogenic failure that's
        located in the Y chromosome's nonrecombining zone and exclusively
        expressed in testes.
  - source_sentence: >-

      TRMT5, also known by aliases such as COXPD26, KIAA1393, PNSED, and TRM5,
      is a gene encoding the tRNA methyltransferase 5. This enzyme is
      responsible for methylating the N1 position of guanosine-37 (G37) in
      specific tRNAs using S-adenosyl methionine. It plays a role in modifying
      tRNAs, which contain 13 to 14 nucleotides modified posttranscriptionally
      by nucleotide-specific enzymes (Brule
    sentences:
      - >-
        Which gene or protein is known to interact with the one associated with
        defective ABCB11, which leads to PFIC2 and BRIC2, and plays a regulatory
        role in the expression of genes critical for liver development and
        functionality?
      - >-
        Which genes or proteins are known to interact with tRNA
        (guanine(37)-N(1))-methyltransferase activity?
      - >-
        What is the biosynthetic pathway that falls under 'Creation of C4 and C2
        activators' and also involves the MASP1 gene or its protein product?
  - source_sentence: >-


      Muscular dystrophy is a group of inherited disorders characterized by
      progressive muscle weakness and wasting. Here's a concise overview of the
      information you've provided:


      ### Types of Muscular Dystrophy:

      - **Duchenne Muscular Dystrophy**: Most common in young boys,
      characterized by severe muscle weakness and consequent inability to walk
      by adolescence.

      - **Becker Muscular Dystrophy**: Less severe than Duchenne but still
      progressive, affecting males.

      - **Facioscapulohumeral Muscular Dystrophy (FSHD)**: Affects the face,
      shoulder, and upper arm muscles, common in the teenage to adult years.

      - **
    sentences:
      - >-
        Identify a metabolic pathway that is associated with both glyoxylate
        metabolism and glycine degradation and is capable of interacting with a
        common gene or protein.
      - >-
        Which gene/protein belonging to the activator 1 small subunit family is
        involved in interactions with the gene/protein associated with
        compromised DNA recombination inhibition at telomeres resulting from
        DAXX mutations?
      - >-
        I need details on a disease linked to the COL6A2 gene, presenting with
        progressive muscle weakening in specific groups and worsening muscle
        strength over time.
model-index:
  - name: SentenceTransformer based on TaylorAI/bge-micro-v2
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 384
          type: dim_384
        metrics:
          - type: cosine_accuracy@1
            value: 0.41089108910891087
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.49504950495049505
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.5346534653465347
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.5693069306930693
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.41089108910891087
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.165016501650165
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.10693069306930691
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.05693069306930693
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.41089108910891087
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.49504950495049505
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.5346534653465347
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.5693069306930693
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.48660626760149667
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.46036657237152295
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.4675921280486482
            name: Cosine Map@100

SentenceTransformer based on TaylorAI/bge-micro-v2

This is a sentence-transformers model finetuned from TaylorAI/bge-micro-v2 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: TaylorAI/bge-micro-v2
Maximum Sequence Length: 512 tokens
Output Dimensionality: 384 tokens
Similarity Function: Cosine Similarity
Training Dataset:
- json

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}) 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("FareedKhan/TaylorAI_bge-micro-v2_FareedKhan_prime_synthetic_data_2k_10_32")
# Run inference
sentences = [
    "\n\nMuscular dystrophy is a group of inherited disorders characterized by progressive muscle weakness and wasting. Here's a concise overview of the information you've provided:\n\n### Types of Muscular Dystrophy:\n- **Duchenne Muscular Dystrophy**: Most common in young boys, characterized by severe muscle weakness and consequent inability to walk by adolescence.\n- **Becker Muscular Dystrophy**: Less severe than Duchenne but still progressive, affecting males.\n- **Facioscapulohumeral Muscular Dystrophy (FSHD)**: Affects the face, shoulder, and upper arm muscles, common in the teenage to adult years.\n- **",
    'I need details on a disease linked to the COL6A2 gene, presenting with progressive muscle weakening in specific groups and worsening muscle strength over time.',
    'Identify a metabolic pathway that is associated with both glyoxylate metabolism and glycine degradation and is capable of interacting with a common gene or protein.',
]
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

Metric	Value
cosine_accuracy@1	0.4109
cosine_accuracy@3	0.495
cosine_accuracy@5	0.5347
cosine_accuracy@10	0.5693
cosine_precision@1	0.4109
cosine_precision@3	0.165
cosine_precision@5	0.1069
cosine_precision@10	0.0569
cosine_recall@1	0.4109
cosine_recall@3	0.495
cosine_recall@5	0.5347
cosine_recall@10	0.5693
cosine_ndcg@10	0.4866
cosine_mrr@10	0.4604
cosine_map@100	0.4676

Training Details

Training Dataset

json

Dataset: json
Size: 1,814 training samples
Columns: positive and anchor
Approximate statistics based on the first 1000 samples:
positive anchor
type string string
details
min: 2 tokens
mean: 247.16 tokens
max: 512 tokens

min: 13 tokens
mean: 35.28 tokens
max: 113 tokens

	positive	anchor
type	string	string
details	min: 2 tokens mean: 247.16 tokens max: 512 tokens	min: 13 tokens mean: 35.28 tokens max: 113 tokens

Samples:

positive	anchor
Hemophilia is an inherited bleeding disorder that occurs when a person's body does not produce enough of certain clotting factors, leading to prolonged bleeding and, in severe cases, spontaneous bleeding into joints and muscles. The disorder is typically associated with mutations in the genes that code for clotting factors VIII (for hemophilia A) and IX (for hemophilia B). It can be categorized based on the specific clotting factor affected and the mode of inheritance. ### Risk Factors The biggest risk factor for hemophilia is a family history of the disorder. If a family member, particularly a parent or a close relative, has hemophilia, there is an increased risk for the disease due to the genetic predisposition. ### Genetic Inheritance - Hemophilia A (Severe) or Factor VIII deficiency: Often affects males due to the inheritance pattern X-linked recessive. A carrier female has a 50% chance of passing the gene to each of her offspring. - Hemophilia B (Severe) or Factor IX deficiency: Also typically X-linked recessive, mostly affecting males. Carrier females are likely to pass the gene to their male offspring only. ### Complications and Symptoms - Abnormal bleeding: This is the most common symptom, ranging from mild to life-threatening. - Subcutaneous hemorrhage and intracranial hemorrhage: These can lead to serious complications and require immediate medical attention. - Joint damage: Frequent bleeding into joints can result in arthritis, joint destruction, and limitation of joint mobility. - Gastrointestinal, genitourinary, and epistaxis: These are other sites where bleeding can occur, often with minor trauma. ### Treatment and Management Treatment for hemophilia often involves replacing the missing clotting factors using infused or transfused factors. This can be through Factor VIII concentrate for hemophilia A or Factor IX concentrate for hemophilia B. Prophylactic treatments are often administered to prevent bleeding episodes and maintain normal joint function. ### Diagnosis Diagnosis of hemophilia is typically made through a series of blood tests to measure clotting times and factor levels. Genetic testing is also recommended in families with a history of hemophilia to identify carriers and those with more severe symptoms. ### See a Doctor It's important to see a doctor if you or your child shows signs of prolonged bleeding or if there is a family history of hemophilia. Early diagnosis and appropriate treatment can significantly improve outcomes and quality of life. ### Carrying and Symptoms in Female Carriers While female carriers are usually asymptomatic, they can experience mild symptoms under specific circumstances such as during pregnancy (gastrointestinal bleeding) or menopause (menorrhagia). Genetic testing can confirm an asymptomatic carrier status, which is important for family planning and counseling. ### In Conclusion Hemophilia is a complex condition that requires careful management to prevent complications and maintain quality of life. Early diagnosis, genetic counseling, and proper treatment are crucial for managing this inherited bleeding disorder effectively.	`Which condition should be avoided when prescribing medications for outdated forms of contact dermatitis resulting from poison oak exposure?`
Assistant: Diabetes insipidus, a rare but serious condition, can manifest with a series of symptoms and has diverse impacts on various systems of the body. Primarily characterized by increased thirst, significant urination, and dehydration, diabetes insipidus requires prompt medical intervention. Symptoms and Impacts: 1. Polydipsia (increased thirst) and polyuria (frequent urination) are the primary symptoms, typically exceeding 10 liters of fluid intake and urine output per day. 2. Dehydration can result from excessive fluid loss unless compensated, causing electrolyte	`What medical condition could I have that involves persistent thirst, frequent urination, and unexplained weight loss, and is associated with a familial disorder affecting water balance similar to diabetes insipidus, but not identical, as it involves an inability to concentrate urine? My father has it, and my doctor suggested managing salt intake and water consumption, mentioning that medication may be available to reduce the urination. What is the name of this disease?`
The pathway described in this document is titled "p75 NTR receptor-mediated signalling" which suggests that it centers around the activity of the p75 neurotrophin receptor (p75 NTR), a cell surface receptor that plays a crucial role in neuronal development, survival, and function. ### Key Components and Their Roles: - Neurotrophin (NGF or Nerve Growth Factor): This is a ligand that binds to the p75 NTR. Binding of NGF to p75 NTR initiates a cascade of events resulting in various cellular responses. - p75 NTR: The receptor itself is pivotal, as its binding with ligands like NGF modulates signal transduction in cells, affecting survival, differentiation, and various aspects of cellular metabolism and function. - Sphingomyelinase (SMPD2): This gene/protein is implicated in the pathway, with involvement in modulating ceramide production upon NGF Binding to p75 NTR. Sphingomyelinase is activated by the NGF:p75NTR complex, suggesting an integral role in the effector phase of the signaling cascade. - Ceramide: A lipid derived from sphingomyelin that plays a key role in cellular signaling. Ceramide's production upon ligand-receptor binding can lead to either cell survival or apoptosis depending on the context within specific cell types. - JNK (c-Jun N-terminal kinase): This is a serine/threonine kinase that can be activated by ceramide and is involved in various cellular processes including apoptosis, cell cycle regulation, and differentiation. ### Pathway Description: The pathway described includes mechanisms by which ligand binding to p75 NTR leads to ceramide production, which in	`Which signaling pathway interacts with both p75 NTR receptor signaling and the nerve growth factor (NGF) gene/protein in a hierarchical manner?`

Loss: MatryoshkaLoss with these parameters:

{
    "loss": "MultipleNegativesRankingLoss",
    "matryoshka_dims": [
        384
    ],
    "matryoshka_weights": [
        1
    ],
    "n_dims_per_step": -1
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: epoch
per_device_train_batch_size: 32
learning_rate: 1e-05
num_train_epochs: 10
warmup_ratio: 0.1
bf16: True
tf32: False
load_best_model_at_end: True

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: 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: 1e-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: 10
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: 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
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
use_liger_kernel: False
eval_use_gather_object: False
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	dim_384_cosine_map@100
0	0	-	0.4238
0.1754	10	1.9916	-
0.3509	20	1.8049	-
0.5263	30	1.8366	-
0.7018	40	1.8585	-
0.8772	50	1.7288	-
1.0	57	-	0.4326
1.0526	60	1.6438	-
1.2281	70	1.5404	-
1.4035	80	1.6168	-
1.5789	90	1.5432	-
1.7544	100	1.4976	-
1.9298	110	1.5275	-
2.0	114	-	0.4422
2.1053	120	1.3276	-
2.2807	130	1.3629	-
2.4561	140	1.4108	-
2.6316	150	1.3338	-
2.8070	160	1.4043	-
2.9825	170	1.4664	-
3.0	171	-	0.4487
3.1579	180	1.2225	-
3.3333	190	1.2557	-
3.5088	200	1.3518	-
3.6842	210	1.3227	-
3.8596	220	1.3391	-
4.0	228	-	0.4561
4.0351	230	1.2035	-
4.2105	240	1.197	-
4.3860	250	1.2908	-
4.5614	260	1.1738	-
4.7368	270	1.1855	-
4.9123	280	1.2118	-
5.0	285	-	0.4578
5.0877	290	1.1835	-
5.2632	300	1.1624	-
5.4386	310	1.2075	-
5.6140	320	1.1771	-
5.7895	330	1.0814	-
5.9649	340	1.2039	-
6.0	342	-	0.4584
6.1404	350	1.2029	-
6.3158	360	1.1043	-
6.4912	370	1.2011	-
6.6667	380	1.0401	-
6.8421	390	1.0732	-
7.0	399	-	0.4624
7.0175	400	1.1137	-
7.1930	410	1.0946	-
7.3684	420	1.1581	-
7.5439	430	1.0605	-
7.7193	440	1.076	-
7.8947	450	1.2689	-
8.0	456	-	0.4680
8.0702	460	1.0004	-
8.2456	470	1.1387	-
8.4211	480	1.0652	-
8.5965	490	1.0879	-
8.7719	500	1.1845	-
8.9474	510	1.0979	-
9.0	513	-	0.4684
9.1228	520	1.0588	-
9.2982	530	1.2412	-
9.4737	540	1.0261	-
9.6491	550	1.0919	-
9.8246	560	1.129	-
10.0	570	1.0425	0.4676

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.10.10
Sentence Transformers: 3.1.1
Transformers: 4.45.1
PyTorch: 2.2.1+cu121
Accelerate: 0.34.2
Datasets: 3.0.1
Tokenizers: 0.20.0

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}
}