This is a sentence-transformers model finetuned from capemox/ettin-encoder-17m-pretrain-50m on the msmarco-embed-dense_on-triples-v3 dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for retrieval.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: capemox/ettin-encoder-17m-pretrain-50m
Maximum Sequence Length: 8192 tokens
Output Dimensionality: 768 dimensions
Similarity Function: Cosine Similarity
Supported Modality: Text
Training Dataset:
- msmarco-embed-dense_on-triples-v3

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': 'ModernBertModel'})
  (1): Pooling({'embedding_dimension': 256, 'pooling_mode': 'cls', 'include_prompt': True})
  (2): Dense({'in_features': 256, 'out_features': 768, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity', 'module_input_name': 'sentence_embedding', 'module_output_name': 'sentence_embedding'})
  (3): 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("sentence_transformers_model_id")
# Run inference
queries = [
    'define reservedness',
]
documents = [
    'Definition of reservedness in the English dictionary The definition of reservedness in the dictionary is the quality or state of being cool or formal in manner or of being restrained, silent, or reticent. english words that begin like reservedness reserve tank',
    "Princeton's WordNet(0.00 / 0 votes)Rate this definition: 1  reserved(adj) set aside for the use of a particular person or party. 2  reserved(adj) marked by self-restraint and reticence.",
    'In a computer language, a reserved word is a word that cannot be used as an identifier, such as the name of a variable, function, or label â\x80\x93 it is reserved from use. This is a syntactic definition, and a reserved word may have no meaning. A closely related and often conflated notion is a keyword, which is a word with special meaning in a particular context. This is a semantic definition. By contrast, names in a standard library but not built into the language are not considered reserved ...',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 768] [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[0.5320, 0.4636, 0.3707]])

Evaluation

Metrics

Information Retrieval

Datasets: NanoClimateFEVER, NanoDBPedia, NanoFEVER, NanoFiQA2018, NanoHotpotQA, NanoMSMARCO, NanoNFCorpus, NanoNQ, NanoQuoraRetrieval, NanoSCIDOCS, NanoArguAna, NanoSciFact and NanoTouche2020
Evaluated with InformationRetrievalEvaluator with these parameters:
json
1{ 2 "query_prompt": "query: ", 3 "corpus_prompt": "document: " 4}

Metric	NanoClimateFEVER	NanoDBPedia	NanoFEVER	NanoFiQA2018	NanoHotpotQA	NanoMSMARCO	NanoNFCorpus	NanoNQ	NanoQuoraRetrieval	NanoSCIDOCS	NanoArguAna	NanoSciFact	NanoTouche2020
cosine_accuracy@1	0.26	0.56	0.56	0.26	0.54	0.3	0.42	0.26	0.84	0.24	0.08	0.34	0.5714
cosine_accuracy@3	0.4	0.76	0.8	0.46	0.76	0.54	0.46	0.48	0.96	0.4	0.32	0.54	0.8367
cosine_accuracy@5	0.56	0.8	0.86	0.64	0.76	0.64	0.56	0.54	1.0	0.52	0.46	0.56	0.898
cosine_accuracy@10	0.66	0.86	0.9	0.7	0.82	0.76	0.64	0.68	1.0	0.62	0.54	0.62	0.9796
cosine_precision@1	0.26	0.56	0.56	0.26	0.54	0.3	0.42	0.26	0.84	0.24	0.08	0.34	0.5714
cosine_precision@3	0.1733	0.5	0.2733	0.1867	0.3333	0.18	0.32	0.16	0.38	0.18	0.1067	0.2	0.517
cosine_precision@5	0.14	0.48	0.176	0.16	0.204	0.128	0.28	0.108	0.256	0.172	0.092	0.128	0.498
cosine_precision@10	0.086	0.404	0.092	0.098	0.114	0.076	0.228	0.068	0.134	0.122	0.054	0.072	0.4367
cosine_recall@1	0.1017	0.0498	0.53	0.1399	0.27	0.3	0.0291	0.24	0.764	0.049	0.08	0.315	0.0401
cosine_recall@3	0.2183	0.1139	0.78	0.276	0.5	0.54	0.0557	0.45	0.9147	0.1127	0.32	0.525	0.1104
cosine_recall@5	0.3007	0.1549	0.84	0.4096	0.51	0.64	0.0664	0.5	0.9693	0.1767	0.46	0.555	0.174
cosine_recall@10	0.3573	0.229	0.8667	0.4854	0.57	0.76	0.1061	0.63	0.99	0.2497	0.54	0.62	0.29
cosine_ndcg@10	0.2816	0.4775	0.7181	0.3499	0.5209	0.5205	0.2818	0.4391	0.9278	0.2268	0.2978	0.4842	0.4805
cosine_mrr@10	0.3716	0.6667	0.6857	0.3898	0.6437	0.4452	0.4679	0.3978	0.91	0.3449	0.2207	0.4427	0.7127
cosine_map@100	0.2128	0.3258	0.6655	0.2702	0.4542	0.4553	0.1071	0.379	0.8999	0.1651	0.233	0.4466	0.3715

Nano BEIR

Dataset: NanoBEIR_mean
Evaluated with NanoBEIREvaluator with these parameters:
json
1{ 2 "dataset_names": [ 3 "climatefever", 4 "dbpedia", 5 "fever", 6 "fiqa2018", 7 "hotpotqa", 8 "msmarco", 9 "nfcorpus", 10 "nq", 11 "quoraretrieval", 12 "scidocs", 13 "arguana", 14 "scifact", 15 "touche2020" 16 ], 17 "dataset_id": "sentence-transformers/NanoBEIR-en", 18 "query_prompts": { 19 "climatefever": "query: ", 20 "dbpedia": "query: ", 21 "fever": "query: ", 22 "fiqa2018": "query: ", 23 "hotpotqa": "query: ", 24 "msmarco": "query: ", 25 "nfcorpus": "query: ", 26 "nq": "query: ", 27 "quoraretrieval": "query: ", 28 "scidocs": "query: ", 29 "arguana": "query: ", 30 "scifact": "query: ", 31 "touche2020": "query: " 32 }, 33 "corpus_prompts": { 34 "climatefever": "document: ", 35 "dbpedia": "document: ", 36 "fever": "document: ", 37 "fiqa2018": "document: ", 38 "hotpotqa": "document: ", 39 "msmarco": "document: ", 40 "nfcorpus": "document: ", 41 "nq": "document: ", 42 "quoraretrieval": "document: ", 43 "scidocs": "document: ", 44 "arguana": "document: ", 45 "scifact": "document: ", 46 "touche2020": "document: " 47 } 48}

Metric	Value
cosine_accuracy@1	0.4024
cosine_accuracy@3	0.5936
cosine_accuracy@5	0.6768
cosine_accuracy@10	0.7523
cosine_precision@1	0.4024
cosine_precision@3	0.27
cosine_precision@5	0.2171
cosine_precision@10	0.1527
cosine_recall@1	0.2237
cosine_recall@3	0.3782
cosine_recall@5	0.4428
cosine_recall@10	0.5149
cosine_ndcg@10	0.462
cosine_mrr@10	0.5153
cosine_map@100	0.3835

Training Details

Training Dataset

msmarco-embed-dense_on-triples-v3

Dataset: msmarco-embed-dense_on-triples-v3
Size: 483,497 training samples
Columns: query, positive, negative_1, negative_2, negative_3, negative_4, negative_5, negative_6, negative_7, negative_8, and label |
Loss: EmbedDistillLoss with these parameters:
json
1{ 2 "distance_metric": "l2", 3 "projection_dim": null 4}

Evaluation Dataset

msmarco-embed-dense_on-triples-v3

Dataset: msmarco-embed-dense_on-triples-v3
Size: 10,000 evaluation samples
Loss: EmbedDistillLoss with these parameters:

json
1{ 2 "distance_metric": "l2", 3 "projection_dim": null 4}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 128
num_train_epochs: 4
max_steps: 15000
learning_rate: 0.0001
lr_scheduler_type: constant
weight_decay: 0.01
bf16: True
per_device_eval_batch_size: 16
seed: 12
dataloader_num_workers: 2
remove_unused_columns: False

All Hyperparameters

Click to expand

per_device_train_batch_size: 128
num_train_epochs: 4
max_steps: 15000
learning_rate: 0.0001
lr_scheduler_type: constant
lr_scheduler_kwargs: None
warmup_steps: 0
optim: adamw_torch_fused
optim_args: None
weight_decay: 0.01
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: True
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: 16
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: 12
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: 2
dataloader_pin_memory: True
dataloader_persistent_workers: False
dataloader_prefetch_factor: None
remove_unused_columns: False
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: None
fsdp_config: None
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 Time

Training: 3.3 hours
Evaluation: 32.0 minutes
Total: 3.9 hours

Framework Versions

Python: 3.11.12
Sentence Transformers: 5.6.1
Transformers: 5.14.1
PyTorch: 2.13.0+cu130
Accelerate: 1.14.0
Datasets: 5.0.1
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",
}

EmbedDistillLoss

bibtex

@article{kim2023embeddistill,
    title={EmbedDistill: A Geometric Knowledge Distillation for Information Retrieval},
    author={Kim, Seungyeon and Rawat, Ankit Singh and Zaheer, Manzil and Jayasumana, Sadeep and Sadhanala, Veeranjaneyulu and Jitkrittum, Wittawat and Menon, Aditya Krishna and Fergus, Rob and Kumar, Sanjiv},
    year={2023},
    eprint={2301.12005},
    archivePrefix={arXiv},
    primaryClass={cs.IR}
}

much1na/ettin-encoder-17m-v3-vendor-embeddistill

SentenceTransformer based on capemox/ettin-encoder-17m-pretrain-50m

Model Details

Model Description

Model Sources

Full Model Architecture

Usage

Direct Usage (Sentence Transformers)

Evaluation

Metrics

Information Retrieval

Nano BEIR

Training Details

Training Dataset

msmarco-embed-dense_on-triples-v3

Evaluation Dataset

msmarco-embed-dense_on-triples-v3

Training Hyperparameters

Non-Default Hyperparameters

All Hyperparameters

Training Time

Framework Versions

Citation

BibTeX

Sentence Transformers

EmbedDistillLoss

much1na/
ettin-encoder-17m-v3-vendor-embeddistill