SentenceTransformer based on mixedbread-ai/mxbai-embed-large-v1

This is a sentence-transformers model finetuned from mixedbread-ai/mxbai-embed-large-v1. 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: mixedbread-ai/mxbai-embed-large-v1
Maximum Sequence Length: 128 tokens
Output Dimensionality: 1024 tokens
Similarity Function: Cosine Similarity

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': 128, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 1024, '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("Daxtra/onet_sbert-v2")
# Run inference
sentences = [
    'Determine shipping methods, routes, or rates for materials to be shipped.\nPrepare documents, such as work orders, bills of lading, or shipping orders, to route materials.\nPack, seal, label, or affix postage to prepare materials for shipping, using hand tools, power tools, or postage meter.\nRequisition and store shipping materials and supplies to maintain inventory of stock.\nConfer or correspond with establishment representatives to rectify problems, such as damages, shortages, or nonconformance to specifications.',
    'Shipping, Receiving, and Inventory Clerks - Analyze shipping information to make routing decisions.\nRecord shipping information.\nCoordinate shipping activities with external parties.',
    'Office Machine Operators, Except Computer - Monitor equipment operation to ensure proper functioning.\nRead work orders to determine material or setup requirements.\nSort materials or products.\nReport maintenance or equipment problems to appropriate personnel.\nOrder materials, supplies, or equipment.\nCompile data or documentation.\nOperate office equipment.\nProvide information to coworkers.\nDeliver items.\nClean facilities or equipment.\nMaintain office equipment in proper operating condition.\nAttach identification information to products, items or containers.',
]
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: 5,856 training samples
Columns: sentence_0 and sentence_1
Approximate statistics based on the first 1000 samples:
sentence_0 sentence_1
type string string
details
min: 25 tokens
mean: 88.28 tokens
max: 128 tokens

min: 17 tokens
mean: 82.52 tokens
max: 128 tokens

	sentence_0	sentence_1
type	string	string
details	min: 25 tokens mean: 88.28 tokens max: 128 tokens	min: 17 tokens mean: 82.52 tokens max: 128 tokens

Samples:

sentence_0	sentence_1
Compile information about new accounts, enter account information into computers, and file related forms or other documents. Obtain credit records from reporting agencies. Perform teller duties as required. Duplicate records for distribution to branch offices. Execute wire transfers of funds. Collect and record customer deposits and fees and issue receipts, using computers. Inform customers of procedures for applying for services, such as ATM cards, direct deposit of checks, and certificates of deposit.	`New Accounts Clerks - Refer customers to appropriate personnel. Compile data or documentation. Operate office equipment. Obtain personal or financial information about customers or applicants. Discuss goods or services information with customers or patrons. Distribute materials to employees or customers. Schedule appointments. Type documents. Sell products or services.`
`Midwives - Establish and follow emergency or contingency plans for mothers and newborns. Inform patients of how to prepare and supply birth sites. Assess birthing environments to ensure cleanliness, safety, and the availability of appropriate supplies. Perform annual gynecologic exams, including pap smears and breast exams. Provide, or refer patients to other providers for, education or counseling on topics such as genetic testing, newborn care, contraception, or breastfeeding.`	Midwives - Assess physical conditions of patients to aid in diagnosis or treatment. Measure the physical or physiological attributes of patients. Communicate detailed medical information to patients or family members. Collect biological specimens from patients. Care for women during pregnancy and childbirth. Evaluate patient functioning, capabilities, or health. Record patient medical histories. Refer patients to other healthcare practitioners or health resources. Collect medical information from patients, family members, or other medical professionals. Analyze quantitative data to determine effectiveness of treatments or therapies. Treat patients using alternative medical procedures. Diagnose medical conditions. Develop medical treatment plans. Position patients for treatment or examination. Provide health and wellness advice to patients, program participants, or caregivers. Examine patients to assess general physical condition. Analyze patient data to determine patient needs or treatment goals. Conduct research to increase knowledge about medical issues. Monitor patient conditions during treatments, procedures, or activities. Prepare medical supplies or equipment for use. Prepare official health documents or records. Analyze test data or images to inform diagnosis or treatment. Communicate health and wellness information to the public. Treat medical emergencies. Test biological specimens to gather information about patient conditions.
`Plan, prepare, and develop various teaching aids, such as bibliographies, charts, and graphs. Clean classrooms. Operate and maintain audio-visual equipment.`	`Distribute instructional or library materials. Clean facilities or work areas. Supervise school or student activities. Collaborate with other teaching professionals to develop educational programs. Serve on institutional or departmental committees. Create technology-based learning materials. Maintain clean work areas. Evaluate student work. Plan educational activities. Set up classroom materials or equipment. Lead classes or community events. Develop instructional materials.`

Loss: MultipleNegativesRankingLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 24
per_device_eval_batch_size: 24
num_train_epochs: 1
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 24
per_device_eval_batch_size: 24
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: 5e-05
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1
num_train_epochs: 1
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.0
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: False
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
eval_use_gather_object: False
batch_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin

Training Logs

Epoch	Step
0.0984	24
0.1967	48
0.2951	72
0.3934	96
0.4918	120
0.5902	144
0.6885	168
0.7869	192
0.8852	216
0.9836	240
1.0	244

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.2.0
Transformers: 4.44.2
PyTorch: 2.4.1+cu121
Accelerate: 0.34.2
Datasets: 3.0.1
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",
}

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}
}

Daxtra
/

onet_sbert-v2