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 retrieval.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: BAAI/bge-m3
Maximum Sequence Length: 8192 tokens
Output Dimensionality: 1024 dimensions
Similarity Function: Cosine Similarity
Supported Modality: Text

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'XLMRobertaModel'})
  (1): Pooling({'embedding_dimension': 1024, 'pooling_mode': 'cls', '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.

python

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("Akhil109/bge-m3-enterprise")
# Run inference
sentences = [
    'is lapatinib an oral medication',
    'The secondary objectives are safety profile and the response rate. Lapatinib, an oral inhibitor of EGFR and HER2, have been shown to be an effective treatment in HER2/neu overexpressing metastatic breast cancer patient who refractory herceptin, taxane, and anthracycline treatment.',
    'Cesium is the most electropositive stable element. Francium is more electropositive (at least in theory) but only about 30 grams exists on the entire planet as it is hi … ghly radioactive so no one has been able to check. cesium is most electropositive element in periodic table. Ceasium.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.6235, 0.0193],
#         [0.6235, 1.0000, 0.1085],
#         [0.0193, 0.1085, 1.0000]])

Training Details

Training Dataset

Unnamed Dataset

Size: 6,050 training samples
Columns: anchor and positive
Approximate statistics based on the first 100 samples:
anchor positive
type string string
modality text text
details
min: 5 tokens
mean: 10.09 tokens
max: 33 tokens
min: 25 tokens
mean: 85.78 tokens
max: 192 tokens

Samples:

anchor	positive
`)what was the immediate impact of the success of the manhattan project?`	`The presence of communication amid scientific minds was equally important to the success of the Manhattan Project as scientific intellect was. The only cloud hanging over the impressive achievement of the atomic researchers and engineers is what their success truly meant; hundreds of thousands of innocent lives obliterated.`
`_________ justice is designed to repair the harm to victim, the community and the offender caused by the offender criminal act. question 19 options:`	`The approach is based on a theory of justice that considers crime and wrongdoing to be an offense against an individual or community, rather than the State. Restorative justice that fosters dialogue between victim and offender has shown the highest rates of victim satisfaction and offender accountability.`
`why did stalin want control of eastern europe`	`There are 3 main reasons why Stalin wanted to control Eastern Europe. 1.) Russia has historically no secure border. 2.) They wanted to set up satellite countries. 3.)`

Loss: MultipleNegativesRankingLoss with these parameters:
json
1{ 2 "scale": 20.0, 3 "similarity_fct": "cos_sim", 4 "gather_across_devices": false, 5 "directions": [ 6 "query_to_doc" 7 ], 8 "partition_mode": "joint", 9 "hardness_mode": null, 10 "hardness_strength": 0.0 11}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 16
num_train_epochs: 1
learning_rate: 2e-05
warmup_steps: 0.1

All Hyperparameters

Click to expand

per_device_train_batch_size: 16
num_train_epochs: 1
max_steps: -1
learning_rate: 2e-05
lr_scheduler_type: linear
lr_scheduler_kwargs: None
warmup_steps: 0.1
optim: adamw_torch_fused
optim_args: None
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
optim_target_modules: None
gradient_accumulation_steps: 1
average_tokens_across_devices: True
max_grad_norm: 1.0
label_smoothing_factor: 0.0
bf16: False
fp16: False
bf16_full_eval: False
fp16_full_eval: False
tf32: None
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
use_liger_kernel: False
liger_kernel_config: None
use_cache: False
neftune_noise_alpha: None
torch_empty_cache_steps: None
auto_find_batch_size: False
log_on_each_node: True
logging_nan_inf_filter: True
include_num_input_tokens_seen: no
log_level: passive
log_level_replica: warning
disable_tqdm: False
project: huggingface
trackio_space_id: None
trackio_bucket_id: None
trackio_static_space_id: None
per_device_eval_batch_size: 8
prediction_loss_only: True
eval_on_start: False
eval_do_concat_batches: True
eval_use_gather_object: False
eval_accumulation_steps: None
include_for_metrics: []
batch_eval_metrics: False
save_only_model: False
save_on_each_node: False
enable_jit_checkpoint: False
push_to_hub: False
hub_private_repo: None
hub_model_id: None
hub_strategy: every_save
hub_always_push: False
hub_revision: None
load_best_model_at_end: False
ignore_data_skip: False
restore_callback_states_from_checkpoint: False
full_determinism: False
seed: 42
data_seed: None
use_cpu: False
accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
parallelism_config: None
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_pin_memory: True
dataloader_persistent_workers: False
dataloader_prefetch_factor: None
remove_unused_columns: True
label_names: None
train_sampling_strategy: random
length_column_name: length
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
ddp_static_graph: None
ddp_backend: None
ddp_timeout: 1800
fsdp: []
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
deepspeed: None
debug: []
skip_memory_metrics: True
do_predict: False
resume_from_checkpoint: None
warmup_ratio: None
local_rank: -1
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss
0.1319	50	0.0167
0.2639	100	0.0124
0.3958	150	0.0108
0.5277	200	0.0105
0.6596	250	0.0096
0.7916	300	0.0107
0.9235	350	0.0062

Training Time

Training: 24.7 minutes

Framework Versions

Python: 3.12.13
Sentence Transformers: 5.5.1
Transformers: 5.9.0
PyTorch: 2.11.0+cu128
Accelerate: 1.13.0
Datasets: 4.8.5
Tokenizers: 0.22.2

Citation

BibTeX

Sentence Transformers

bibtex

@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

bibtex

@misc{oord2019representationlearningcontrastivepredictive,
      title={Representation Learning with Contrastive Predictive Coding},
      author={Aaron van den Oord and Yazhe Li and Oriol Vinyals},
      year={2019},
      eprint={1807.03748},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/1807.03748},
}

	anchor	positive
type	string	string
modality	text	text
details	min: 5 tokens mean: 10.09 tokens max: 33 tokens	min: 25 tokens mean: 85.78 tokens max: 192 tokens