How to use from the
Use from the
sentence-transformers library
from sentence_transformers import SentenceTransformer

model = SentenceTransformer("Jrinky/model2")

sentences = [
    "What are the factors that influence the treatment and healing of equine lameness",
    "Masterkraft may refer to:\n\nMasterkraft (producer), a record producer\nMSTRKRFT, a Canadian electronic music group",
    "The treatment of equine lameness is a complex subject. Lameness in horses has a variety of causes, and treatment must be tailored to the type and degree of injury, as well as the financial capabilities of the owner. Treatment may be applied locally, systemically, or intralesionally, and the strategy for treatment may change as healing progresses. The end goal is to reduce the pain and inflammation associated with injury, to encourage the injured tissue to heal with normal structure and function, and to ultimately return the horse to the highest level of performance possible following recovery. The process of healing\n\nBone\n\nBone heals by formation of a callus over the defective area. Speed and quality of healing is directly related to the blood supply and fracture stability. Rest is required immediately following injury to reduce movement of the fracture site. Stability may be improved through use of surgical implants or casting, depending on the location of extent of the fracture. Shock wave therapy is sometimes employed in the case of splint bone fracture or stress fractures to the cannon bones, to improve blood flow to the area. Fractures within a joint, such as chip fractures in the knee, hock, or fetlock, require arthroscopic surgery to prevent secondary arthritis of that joint. In some cases, the callus may place pressure on surrounding soft tissue structures. The callus of a splint bone fracture can push on the adjacent suspensory ligament, leading to lameness from secondary suspensory desmitis. Treatment usually involves the removal of the offending callus. On average, bone heals better than soft tissue. It requires less time to heal and, unlike soft tissue which is always weaker after healing, bone heals to 100% strength. However, fracture healing in horses is complicated by their size, flightiness, and desire to stand. Horses are at risk of re-injury of the fracture site, especially when trying to rise after lying down, or when recovering from anesthesia following fracture repair. Forced recumbency is not an option for horses, making healing more difficult. Weight bearing on a single front or hind limb increases the likelihood of support limb laminitis. Additionally, the cost of casting or surgical fixation makes treatment financially unattainable for some owners. While limb fractures are no longer a death-sentence for horses, it is still considered a very serious injury. In general, a horse is more likely to survive if it is small in stature and has a good temperament that will tolerate the months of inactivity required for healing. Fractures that are open, comminuted (very fragmented), or located higher on the limb tend to have a poorer prognosis. Synovial joints\nLameness is most commonly associated with injury to synovial joints, or those joints containing articular cartilage, a joint capsule, and a synovial membrane. Joint disease may affect the joint capsule and synovial membrane, articular cartilage, subchondral bone (the bone underneath the cartilage), menisci, or any ligaments associated with the joint. Damage to any of these tissues leads to inflammation, which is especially problematic in the joint. While degeneration of articular cartilage is a common disease process in working animals, resulting in osteoarthritis, cartilage is aneural (does not contain nerves) and does not produce pain. Pain associated with osteoarthritis is secondary to joint capsule pain, due to joint distention and reduced range of motion, or to pain from the underlying bone, which may become damaged following erosion of the articular cartilage. Inflammatory products, such as inflammatory mediators and cytokines, damage articular cartilage and have been shown to weaken intra-articular ligaments. Therefore, treatment of joint disease should not only address the primary injury producing inflammation, but also the inflammatory cycle that leads to further tissue damage. Cryotherapy, joint lavage, systemic anti-inflammatories, or intra-articular medications are used to reduce joint inflammation. In the case of severe joint pathology such as an osteochondral chip, intra-articular fracture, osteochondritis dissecans lesion, or ligamentous or meniscal injury, arthroscopy may be required to ensure normal function of that joint. Debris within the joint, such as from a chip fracture, can cause long term damage to the synovium and articular cartilage leading to osteoarthritis, and is therefore best removed. Following acute injury, joints often benefit from specialized physical therapy, such as swimming, to prevent the loss of range of motion associated with joint capsule fibrosis. Treatment of joint cartilage injury is difficult and often unrewarding. Partial-thickness defects do not heal. The body will try to repair full-thickness cartilage defects using scar tissue or fibrocartilage, both of which are poor substitutes for normal, healthy articular cartilage. Current treatment includes arthroscopy-produced microfratures within the subchondral plate. These microfractures encourage an inflammatory response within the defect, which recruits stem cells to the area. Unfortunately, these cells differentiate into fibrocartilage, rather than normal joint (hyaline) cartilage, leading to inferior tissue repair at the site of injury. Bone marrow aspirate concentrate (BMAC) has shown some benefits when grafted into the area following microtrauma. However, the primary treatment for degenerative joint disease involves reducing the inflammatory process that is known to accelerate articular cartilage degeneration. Tendon and ligament\n\nTendon is primarily composed of elastic type I collagen. However, mature tendon contains cells that have a limited ability to regenerate. Following injury, tendon lays down type III collagen, or scar tissue, which is stronger than type I collagen but stiffer and less-elastic. This makes it less distensible and more likely to re-injure when the horse begins to stretch the tendon during strenuous work. Certain treatments may improve the final tendon fiber quality, and subsequently increase the likelihood that the horse will return to full performance post-injury. Healing of soft tissue injury is often monitored using ultrasound to assess the lesion size and fiber pattern. Monitoring soft tissue injury with ultrasound allows for a more scientific determination of when to introduce exercise back into the horse's rehabilitation program, and for quick intervention should the injury worsen. Recently, a new ultrasound technique called color Doppler ultrasonography has been used to assess equine tendon injuries. Color Doppler measures the degree of blood flow to a lesion, allowing for more accurate assessment of healing. Rest and hand-walking\nRest is almost always recommended for treatment of lameness because it reduces forces placed on damaged tissue, allowing the normal process of healing to occur. Type and severity of injury determines the duration and degree of rest required. Aggressive limitations of activity may be required in cases of fracture. Horses are kept tied for the several-month duration of healing, to prevent them from lying down and potentially re-injuring the bone while trying to stand. In other cases, rest may be contraindicated. Animals with a history of upward fixation of the patella, polysaccharide storage myopathy, and equine recurrent rhabdomyolysis are often best kept on a schedule of regular exercise. Rest may be counterproductive if the lameness is secondary to osteoarthritis. In this case, mild exercise improves joint mobility and lameness can worsen with confinement. Rest may vary from strict confinement (“stall rest”), to small paddock or pasture turnout, to reduction of exercise intensity. Horses are often unpredictable when on prolonged stall rest, which greatly increases the risk of re-injury when hand-walking is begun. Sedation or additional forms of restraint may be needed to help control the horse during this initial period of",
    "As we stand right now, our broadcasts resemble a mixture between a graduate-level college seminar and a JV football game with the volume turned down 11 notches. Everything the commentators narrate is an explanation simply of what is going on, not speculation as to why they are doing it. They simply state what an ejection means, what a particular whistle is for, or what the purpose was of taking a time out. There is no substance. If Water Polo hopes and expects to be a household name, or at least something that households want on their television instead of the Wednesday Bowling Championships, then we need to institute a change. Most broadcasts are viewed by Water Polo fans…fans that already understand the game and the rules. We don’t need to be spoken to like a freshman college student who’s learning algebra for the first time. Most of us have already done that, and I feel confident in claiming that no one cares to do it again, especially not for entertainment. Production and entertainment value are key to the growth and expansion of any sport, especially Water Polo. Invite a color commentator that knows the game well enough to look for the nuances in the action."
]
embeddings = model.encode(sentences)

similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [4, 4]

SentenceTransformer based on BAAI/bge-m3

This is a sentence-transformers model finetuned from BAAI/bge-m3. It maps sentences & paragraphs to a 1024-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: BAAI/bge-m3
  • Maximum Sequence Length: 1024 tokens
  • Output Dimensionality: 1024 dimensions
  • Similarity Function: Cosine Similarity

Model Sources

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 1024, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, '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:

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("Jrinky/mpnet-base-all-nli-triplet")
# Run inference
sentences = [
    'What rights do individuals have regarding their personal data according to European Regulation no. 679/2016',
    'By consulting this site, data relating to identified or identifiable persons may be processed. The consent mechanisms will be evident, brief and easily understandable; if the original conditions for which consent was requested were to be changed, for example if the purpose of data processing changed, further consent will be required pursuant to European Regulation no. 679/2016. All the documents related to consents collected will be kept separate from any other corporate document. Your personal data will not be disclosed and you are granted the exercise of the rights referred to in Articles. 11-20 of the European Regulation n. 679/2016 by writing to Promoviaggi S.p.A., Viale Gian Galeazzo, nr. 3, 20136 Milano (Italy) or by sending an e-mail to firstname.lastname@example.org.',
    'The regional economy has benefited from these investments in infrastructure. The project owner has also funded the construction of a local school, which is providing benefits to local children. Project impacts and benefits:\n- The project has generated hydropower plant operation/ maintenance jobs for local people. - 24 operational staff have benefited from six months of capacity building in the form of technical training. - The construction of a new transmission line is reducing electricity loss and increasing the electricity supply in the region. - Former low-quality infrastructure systems in the region have improved, e.g. by upgrading roads, and by building bridges and irrigation canals. - A local school has been built. - The project has provided local farmers with support to broaden their agricultural activities to make them more sustainable (e.g. by implementing aquaculture, which reduces the need for logging for farmland). - The project has reduced the need for wood for heating, cooking, and lighting, thus allowing the forest to regenerate and improving soil conditions, hydrology and biodiversity. - The project has improved regional air quality by reducing the need for diesel generators and wood fires.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Training Details

Training Dataset

Unnamed Dataset

  • Size: 6,433 training samples
  • Columns: anchor and positive
  • Approximate statistics based on the first 1000 samples:
    anchor positive
    type string string
    details
    • min: 6 tokens
    • mean: 18.1 tokens
    • max: 38 tokens
    • min: 6 tokens
    • mean: 182.31 tokens
    • max: 1024 tokens
  • Samples:
    anchor positive
    What type of insect is Crambus sudanicola Crambus sudanicola is a moth in the family Crambidae.
    How can you improve storage capacity in standard-height kitchens with unused wall space If you have standard-height cabinets with unused wall space above, increasing the cabinets by six inches can improve storage capacity. Utilize cutlery dividers in drawers to organize cooking utensils and tools and keep them off counters.
    What new guidelines has the Library Association issued regarding the sale of rare books and manuscripts The Library Association has issued new guidelines for the sale of rare books and manuscripts by institutions, writes Kam Patel. The move follows an acrimonious dispute at Keele University over the sale of rare mathematics books for Pounds 1 million. The association said that for an institution to have the authority to sell books, its library should first establish that it has a full legal title to the works.
  • Loss: selfloss.Infonce with these parameters:
    {
        "scale": 20.0,
        "similarity_fct": "cos_sim"
    }
    

Evaluation Dataset

Unnamed Dataset

  • Size: 804 evaluation samples
  • Columns: anchor and positive
  • Approximate statistics based on the first 804 samples:
    anchor positive
    type string string
    details
    • min: 6 tokens
    • mean: 17.78 tokens
    • max: 37 tokens
    • min: 4 tokens
    • mean: 190.09 tokens
    • max: 1024 tokens
  • Samples:
    anchor positive
    What does the speaker suggest about the relationship between unarmed civilians and the metaphor of eggs and a wall One way to read the metaphor, he says, is that unarmed civilians are the eggs, while tanks, guns and white phosphorus shells are the wall. But he also offers a more nuanced interpretation:
    Each of us is, more or less, an egg.
    When did Reed-Rowe retire from the Foreign Service Reed-Rowe completed that assignment July 26, 2013, and was succeeded by Amy J. Hyatt. Reed-Rowe then joined the United States Army War College as a member of the Command team which focuses on the development of the next generation of military, interagency and international leaders. She officially retired from the Foreign Service in July 2014. During her career, Reed-Rowe earned several Department of State Meritorious Honor Awards, recognition from the Republic of the Marshall Islands, and the Republic of Palau, and the U.S. Army Superior Civilian Service Award. Personal
    In addition to English, Reed-Rowe speaks Spanish and French. She has two adult children, Nikkia Rowe and Kevin Anthony Rowe. See also

    List of ambassadors of the United States

    References

    External links
    US Department of State: Ambassadorial Nomination Statement: Helen Reed-Rowe, Ambassador-Designate to Palau, July 21, 2010

    Ambassadors of the United States to Palau
    African-American diplomats
    American women ambassadors
    ...
    When will Star Wars: Galaxy's Edge officially open Star Wars: Galaxy’s Edge may not officially open until the end of June, but for some fans, it could happen even sooner.
  • Loss: selfloss.Infonce with these parameters:
    {
        "scale": 20.0,
        "similarity_fct": "cos_sim"
    }
    

Training Hyperparameters

Non-Default Hyperparameters

  • eval_strategy: steps
  • per_device_train_batch_size: 4
  • per_device_eval_batch_size: 4
  • learning_rate: 2e-05
  • num_train_epochs: 1
  • warmup_ratio: 0.1
  • fp16: True
  • batch_sampler: no_duplicates

All Hyperparameters

Click to expand
  • overwrite_output_dir: False
  • do_predict: False
  • eval_strategy: steps
  • prediction_loss_only: True
  • per_device_train_batch_size: 4
  • per_device_eval_batch_size: 4
  • 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: 1
  • 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: 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
  • prompts: None
  • batch_sampler: no_duplicates
  • multi_dataset_batch_sampler: proportional

Training Logs

Epoch Step Training Loss Validation Loss
0.7407 100 0.2167 0.1060

Framework Versions

  • Python: 3.12.3
  • Sentence Transformers: 3.4.0
  • Transformers: 4.42.4
  • PyTorch: 2.2.0+cu121
  • Accelerate: 1.3.0
  • Datasets: 3.2.0
  • 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",
}

Infonce

@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}
}
Downloads last month
3
Safetensors
Model size
0.6B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Jrinky/model2

Base model

BAAI/bge-m3
Finetuned
(441)
this model

Papers for Jrinky/model2