SentenceTransformer based on sentence-transformers/all-mpnet-base-v2

This is a sentence-transformers model finetuned from sentence-transformers/all-mpnet-base-v2 on the json dataset. It maps sentences & paragraphs to a 768-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: sentence-transformers/all-mpnet-base-v2
Maximum Sequence Length: 384 tokens
Output Dimensionality: 768 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': 384, 'do_lower_case': False}) with Transformer model: MPNetModel 
  (1): Pooling({'word_embedding_dimension': 768, '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:

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("stephenhib/all-mpnet-base-v2-patabs-1epoc-batch32-100")
# Run inference
sentences = [
    'A computer-implemented method determines an orientation parameter value of a prosthetic component. The method includes receiving a first desired separation distance (d1) between a tibial prosthetic component (120) and a femoral prosthetic component (110) at a first flexion position (521) of a knee joint (100) and estimating a first estimated separation distance (g1) between the tibial prosthetic component and the femoral prosthetic component at the first flexion position of the knee joint for at least one potential orientation of the femoral prosthet¬ic component. The method also includes determining a first orientation para¬meter value of the femoral prosthetic component by comparing the first estimated separation distance to the first desired separation distance and out¬putting the first orientation parameter value via a user interface (400).',
    'SYSTEMS AND METHOD FOR PROSTHETIC COMPONENT ORIENTATION',
    'TWO-WAY VALVE FOR CONTROLLING A TEMPERATURE OF A COOLANT FOR AN INTERNAL COMBUSTION ENGINE',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

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

Training Details

Training Dataset

json

Dataset: json
Size: 768,201 training samples
Columns: positive and anchor
Approximate statistics based on the first 1000 samples:
positive anchor
type string string
details
min: 13 tokens
mean: 163.82 tokens
max: 384 tokens

min: 3 tokens
mean: 12.34 tokens
max: 73 tokens

	positive	anchor
type	string	string
details	min: 13 tokens mean: 163.82 tokens max: 384 tokens	min: 3 tokens mean: 12.34 tokens max: 73 tokens

Samples:

positive	anchor
`According to an example aspect of the present invention, there is provided an apparatus and method to control mining vehicles, in particular as electric mining vehicles, taking into account the state of charge the batteries of said mining vehicles.`	`MINING VEHICLE CONTROL`
`The invention is related to a new soft heterophasic random propylene copolymer with improved optical properties, as well as the process by which the heterophasic random propylene copolymer is produced.`	`SOFT HETEROPHASIC RANDOM PROPYLENE COPOLYMER WITH IMPROVED CLARITY`
The present invention relates to a valve assembly 10 for controlling a volute connecting opening 324 of a multi-channel turbine 500. The valve assembly 10 comprises a housing portion 300, a valve body 100 and an internal lever 200. The housing portion 300 defines a first volute channel 312, a second volute channel 314 and a volute connecting region 320. The housing portion 300 further comprises a cavity 340. The cavity 340 is separated from the volutes 312, 314 and can be accessed from outside the housing portion 300 via a housing opening 342 which extends from outside the housing portion 300 into the cavity 340. The volute connection region 320 is located between the first volute channel 312 and the second volute channel 314 and defines a volute connecting opening 324. The valve body 100 is inserted in the cavity 340 of the housing portion 300 and comprises at least one fin 120. The internal lever 200 is coupled with the valve body 100 and configured to pivotably move the valve body 100 between a first position and a second position. In the first position of the valve body 100, the fin 120 blocks the volute connecting opening 324. Thus, exhaust gases are substantially prevented from overflowing from the first volute channel 312 to the second volute channel 314 and vice versa. In the second position of the valve body 100 the fin 120 clears the volute connecting opening 324. Thus, exhaust gases are enabled to overflow from the first volute channel 312 to the second volute channel 314 and vice versa.	`VALVE ASSEMBLY FOR MULTI-CHANNEL TURBINE`

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: 4
per_device_eval_batch_size: 2
learning_rate: 2e-05
num_train_epochs: 1
warmup_ratio: 0.1
bf16: 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: 2
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: 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: True
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
use_liger_kernel: False
eval_use_gather_object: False
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Framework Versions

Python: 3.11.9
Sentence Transformers: 3.2.0
Transformers: 4.45.2
PyTorch: 2.5.0+cu124
Accelerate: 1.0.1
Datasets: 3.0.1
Tokenizers: 0.20.1

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}
}

stephenhib
/

all-mpnet-base-v2-patabs-1epoc-batch32-100