SentenceTransformer based on Qwen/Qwen3-Embedding-0.6B

This is a sentence-transformers model finetuned from Qwen/Qwen3-Embedding-0.6B on the positives and pairs_with_negatives datasets. 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: Qwen/Qwen3-Embedding-0.6B
Maximum Sequence Length: 128 tokens
Output Dimensionality: 1024 dimensions
Similarity Function: Cosine Similarity
Supported Modality: Text
Training Datasets:
- positives
- pairs_with_negatives

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': 'Qwen3Model'})
  (1): Pooling({'embedding_dimension': 1024, 'pooling_mode': 'lasttoken', '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("sentence_transformers_model_id")
# Run inference
queries = [
    'Instruct: Given an Arabic e-commerce search query, retrieve the product that best matches it\nQuery: فمّا ساعة منبه',
]
documents = [
    'ساعة منبه وردي - QUARTZ',
    'عدسات كاميرات سداسية - ازرق',
    'قلم ايباد - XO-ST-10',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 1024] [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[0.4883, 0.0481, 0.0815]], dtype=torch.bfloat16)

Training Details

Training Datasets

positives

Dataset: positives
Size: 558,253 training samples
Columns: anchor and positive
Approximate statistics based on the first 1000 samples:
anchor positive
type string string
details
min: 23 tokens
mean: 29.07 tokens
max: 39 tokens

min: 5 tokens
mean: 13.99 tokens
max: 27 tokens

	anchor	positive
type	string	string
details	min: 23 tokens mean: 29.07 tokens max: 39 tokens	min: 5 tokens mean: 13.99 tokens max: 27 tokens

Samples:

anchor	positive
`Instruct: Given an Arabic e-commerce search query, retrieve the product that best matches it Query: نحب تشيبس حارة`	`شيبس التوابل الحارة - Doritos Storm`
`Instruct: Given an Arabic e-commerce search query, retrieve the product that best matches it Query: دوريستوس طوفان توابل`	`شيبس التوابل الحارة - Doritos Storm`
`Instruct: Given an Arabic e-commerce search query, retrieve the product that best matches it Query: تشيبس`	`شيبس التوابل الحارة - Doritos Storm`

Loss: CachedMultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim",
    "mini_batch_size": 8,
    "gather_across_devices": false,
    "directions": [
        "query_to_doc"
    ],
    "partition_mode": "joint",
    "hardness_mode": null,
    "hardness_strength": 0.0
}

pairs_with_negatives

Dataset: pairs_with_negatives
Size: 125,517 training samples
Columns: anchor, positive, and negative

Approximate statistics based on the first 1000 samples:

	anchor	positive	negative
type	string	string	string
details	min: 23 tokens mean: 28.74 tokens max: 39 tokens	min: 5 tokens mean: 13.51 tokens max: 27 tokens	min: 4 tokens mean: 12.81 tokens max: 30 tokens

Samples:

anchor	positive	negative
`Instruct: Given an Arabic e-commerce search query, retrieve the product that best matches it Query: دوريستوس طوفان توابل`	`شيبس التوابل الحارة - Doritos Storm`	`شيبس جبنة الناتشو - Doritos`
`Instruct: Given an Arabic e-commerce search query, retrieve the product that best matches it Query: نحب تشيبس حارة`	`شيبس التوابل الحارة - Doritos Storm`	`شيبس جبنة الناتشو - Doritos`
`Instruct: Given an Arabic e-commerce search query, retrieve the product that best matches it Query: دوريستوس`	`شيبس التوابل الحارة - Doritos Storm`	`شيبس جبنة الناتشو - Doritos`

Loss: CachedMultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim",
    "mini_batch_size": 8,
    "gather_across_devices": false,
    "directions": [
        "query_to_doc"
    ],
    "partition_mode": "joint",
    "hardness_mode": null,
    "hardness_strength": 0.0
}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 16
learning_rate: 0.0001
max_steps: 500
lr_scheduler_type: cosine
warmup_steps: 0.05
gradient_checkpointing: True

All Hyperparameters

Click to expand

do_predict: False
prediction_loss_only: True
per_device_train_batch_size: 16
per_device_eval_batch_size: 8
gradient_accumulation_steps: 1
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 0.0001
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 3.0
max_steps: 500
lr_scheduler_type: cosine
lr_scheduler_kwargs: None
warmup_ratio: None
warmup_steps: 0.05
log_level: passive
log_level_replica: warning
log_on_each_node: True
logging_nan_inf_filter: True
enable_jit_checkpoint: False
save_on_each_node: False
save_only_model: False
restore_callback_states_from_checkpoint: False
use_cpu: False
seed: 42
data_seed: None
bf16: False
fp16: False
bf16_full_eval: False
fp16_full_eval: False
tf32: None
local_rank: -1
ddp_backend: None
debug: []
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_prefetch_factor: None
disable_tqdm: False
remove_unused_columns: True
label_names: None
load_best_model_at_end: False
ignore_data_skip: False
fsdp: []
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': 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
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch_fused
optim_args: None
group_by_length: False
length_column_name: length
project: huggingface
trackio_space_id: trackio
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
push_to_hub: False
resume_from_checkpoint: None
hub_model_id: None
hub_strategy: every_save
hub_private_repo: None
hub_always_push: False
hub_revision: None
gradient_checkpointing: True
gradient_checkpointing_kwargs: None
include_for_metrics: []
eval_do_concat_batches: True
auto_find_batch_size: False
full_determinism: False
ddp_timeout: 1800
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
include_num_input_tokens_seen: no
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
eval_on_start: False
use_liger_kernel: False
liger_kernel_config: None
eval_use_gather_object: False
average_tokens_across_devices: True
use_cache: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss
0.0012	25	0.6661
0.0023	50	0.5316
0.0035	75	0.4130
0.0047	100	0.5524
0.0058	125	0.3809
0.0070	150	0.4590
0.0082	175	0.3889
0.0094	200	0.3555
0.0105	225	0.3777
0.0117	250	0.4123
0.0129	275	0.3507
0.0140	300	0.4022
0.0152	325	0.3623
0.0164	350	0.4201
0.0175	375	0.4134
0.0187	400	0.3386
0.0199	425	0.2656
0.0211	450	0.3384
0.0222	475	0.3705
0.0234	500	0.3033

Training Time

Training: 1.9 hours

Framework Versions

Python: 3.12.13
Sentence Transformers: 5.4.1
Transformers: 5.0.0
PyTorch: 2.10.0+cu128
Accelerate: 1.13.0
Datasets: 5.0.0
Tokenizers: 0.22.2

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",
}

CachedMultipleNegativesRankingLoss

@misc{gao2021scaling,
    title={Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup},
    author={Luyu Gao and Yunyi Zhang and Jiawei Han and Jamie Callan},
    year={2021},
    eprint={2101.06983},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}