This is a sentence-transformers model finetuned from intfloat/multilingual-e5-small on the msmarco-tr dataset. It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for retrieval.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: intfloat/multilingual-e5-small
Maximum Sequence Length: 256 tokens
Output Dimensionality: 384 dimensions
Similarity Function: Cosine Similarity
Supported Modality: Text
Training Dataset:
- msmarco-tr

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': 'BertModel'})
  (1): Pooling({'embedding_dimension': 384, 'pooling_mode': 'mean', '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("emirhanyac/e5-small-msmarco-tr")
# Run inference
queries = [
    'query: Safra kesesi karaciğerin______ marjında bulunur',
]
documents = [
    'passage: Karaciğer, karın boşluğunun üst kısmında diyaframın hemen altında bulunur. Karaciğerin büyük bir kısmı sağ kostal marjın altında bulunur ve ayrıca sol hemidiafragma ulaşmak için sola uzanır. Diyafram karaciğeri pleura, akciğerler, perikardiyum ve kalpten ayırır.',
    "passage: Jay Gatsby (doğum adı James Gatz), F. Scott Fitzgerald'ın 1925 tarihli romanı The Great Gatsby'nin baş karakteridir. Gatsby, West Egg'deki Gotik bir konakta yaşayan inanılmaz derecede zengin bir genç adamdır.",
    'passage: ağaç cerrahisi. n. Budama veya dalları destekleyerek hastalıklı veya hasarlı ağaçların tedavisi. ağaç cerrahı n.',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 384] [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[ 0.4641, -0.0035,  0.1333]])

Evaluation

Metrics

Information Retrieval

Dataset: msmarco-tr-eval
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.833
cosine_accuracy@3	0.914
cosine_accuracy@5	0.932
cosine_accuracy@10	0.951
cosine_precision@1	0.833
cosine_precision@3	0.3047
cosine_precision@5	0.1864
cosine_precision@10	0.0951
cosine_recall@1	0.833
cosine_recall@3	0.914
cosine_recall@5	0.932
cosine_recall@10	0.951
cosine_ndcg@10	0.8955
cosine_mrr@10	0.8773
cosine_map@100	0.8786

Training Details

Training Dataset

msmarco-tr

Dataset: msmarco-tr
Size: 10,000 training samples
Columns: anchor and positive
Approximate statistics based on the first 100 samples:
anchor positive
type string string
modality text text
details
min: 7 tokens
mean: 13.33 tokens
max: 28 tokens
min: 28 tokens
mean: 81.28 tokens
max: 136 tokens

Samples:

anchor	positive
`query: asal meridyen arktik daire veya antarktik daireden geçer mi`	`passage: Dünya'daki boylamın her meridyeni Antarktika Çemberi, Arktik Çemberi ve Dünya'daki diğer tüm enlem paralellerini geçer. Her ikisine de evet. Asal meridyen bir boylam çizgisidir ve bu nedenle hem Kuzey Kutbu hem de Antarktika çemberlerinden geçer, bunlar latent çizgileridir.`
`query: Kaç test şeridi için ilaç ödeyecek`	`passage: Gary'ye göre, Medicare tarafından kapsanan test şeritlerinin sayısı, hastanın insülin kullanıp kullanmadığına bağlı olabilir. Bir yararlanıcı insülin kullanırsa, her ay 100 test şeridine ve lancet'a ve her 6 ayda bir lancet cihazına kadar çıkabilir, dedi Gary.`
`query: Bir kedinin ortalama ömrü`	`passage: Köpeklerin ve Kedilerin Yaşam Beklentisi. Evcil hayvanlarımızın uzun yıllar boyunca hayatımızın bir parçası olacağını umuyoruz, ancak gerçek şu ki, ortalama yaşam beklentisi köpekler için 10-12 yıl ve kediler için 10-14 yıldır. Yaşlı evcil hayvanların çok özel ihtiyaçları vardır ve daha sonraki yıllarda kanser, artrit ve diş hastalıklarına özellikle duyarlıdırlar.`

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: 64
num_train_epochs: 1
learning_rate: 2e-05
warmup_steps: 0.1
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

per_device_train_batch_size: 64
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: 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: no_duplicates
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	msmarco-tr-eval_cosine_ndcg@10
-1	-1	-	0.8841
0.1592	25	1.3794	-
0.3185	50	0.1740	-
0.4777	75	0.1527	-
0.6369	100	0.1369	-
0.7962	125	0.1406	-
0.9554	150	0.1435	-
-1	-1	-	0.8955

Training Time

Training: 5.2 minutes

Framework Versions

Python: 3.13.9
Sentence Transformers: 5.6.0
Transformers: 5.13.1
PyTorch: 2.13.0
Accelerate: 1.14.0
Datasets: 5.0.0
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: 7 tokens mean: 13.33 tokens max: 28 tokens	min: 28 tokens mean: 81.28 tokens max: 136 tokens