TaylorAI_bge-micro-v2_FareedKhan_prime_synthetic_data_2k_10_32

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 <!-- at revision 3edf6d7de0faa426b09780416fe61009f26ae589 -->
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 384 tokens
• Similarity Function: Cosine Similarity
• Training Dataset:
  • json

<!-- - **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}) 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]

<!-- ### 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.* -->

Evaluation

Metrics

Information Retrieval

• Dataset: dim_384
• Evaluated with <code>InformationRetrievalEvaluator</code>

<!-- ## 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

json

• Dataset: json
• Size: 1,814 training samples
• Columns: <code>positive</code> and <code>anchor</code>
• Approximate statistics based on the first 1000 samples:

  	positive	anchor
  type	string	string
  details	<ul><li>min: 2 tokens</li><li>mean: 247.16 tokens</li><li>max: 512 tokens</li></ul>	<ul><li>min: 13 tokens</li><li>mean: 35.28 tokens</li><li>max: 113 tokens</li></ul>

• Samples:

  positive	anchor
  <code><br><br>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.<br><br>### Risk Factors<br>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.<br><br>### Genetic Inheritance<br>- 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.<br>- 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.<br><br>### Complications and Symptoms<br>- Abnormal bleeding: This is the most common symptom, ranging from mild to life-threatening.<br>- Subcutaneous hemorrhage and intracranial hemorrhage: These can lead to serious complications and require immediate medical attention.<br>- Joint damage: Frequent bleeding into joints can result in arthritis, joint destruction, and limitation of joint mobility.<br>- Gastrointestinal, genitourinary, and epistaxis: These are other sites where bleeding can occur, often with minor trauma.<br><br>### Treatment and Management<br>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.<br><br>### Diagnosis<br>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.<br><br>### See a Doctor<br>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.<br><br>### Carrying and Symptoms in Female Carriers<br>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.<br><br>### In Conclusion<br>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.</code>	<code>Which condition should be avoided when prescribing medications for outdated forms of contact dermatitis resulting from poison oak exposure?</code>
  <code><br><br>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.<br><br>Symptoms and Impacts:<br>1. Polydipsia (increased thirst) and polyuria (frequent urination) are the primary symptoms, typically exceeding 10 liters of fluid intake and urine output per day.<br>2. Dehydration can result from excessive fluid loss unless compensated, causing electrolyte</code>	<code>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?</code>
  <code><br><br>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. <br><br>### Key Components and Their Roles:<br><br>- 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.<br><br>- 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.<br><br>- 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.<br><br>- 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.<br><br>- 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.<br><br>### Pathway Description:<br><br>The pathway described includes mechanisms by which ligand binding to p75 NTR leads to ceramide production, which in</code>	<code>Which signaling pathway interacts with both p75 NTR receptor signaling and the nerve growth factor (NGF) gene/protein in a hierarchical manner?</code>

• Loss: <code>MatryoshkaLoss</code> 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

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

• 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

</details>

Training Logs

• 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}
}

<!-- ## 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.* -->