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 tokensmean: 29.07 tokensmax: 39 tokens	min: 5 tokensmean: 13.99 tokensmax: 27 tokens

• Samples:

  anchor	positive
  Instruct: Given an Arabic e-commerce search query, retrieve the product that best matches itQuery: نحب تشيبس حارة	شيبس التوابل الحارة - Doritos Storm
  Instruct: Given an Arabic e-commerce search query, retrieve the product that best matches itQuery: دوريستوس طوفان توابل	شيبس التوابل الحارة - Doritos Storm
  Instruct: Given an Arabic e-commerce search query, retrieve the product that best matches itQuery: 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 tokensmean: 28.74 tokensmax: 39 tokens	min: 5 tokensmean: 13.51 tokensmax: 27 tokens	min: 4 tokensmean: 12.81 tokensmax: 30 tokens

• Samples:

  anchor	positive	negative
  Instruct: Given an Arabic e-commerce search query, retrieve the product that best matches itQuery: 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 itQuery: 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 itQuery: 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

• 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

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}
}