SentenceTransformer based on Qwen/Qwen3-Embedding-4B

This is a sentence-transformers model finetuned from Qwen/Qwen3-Embedding-4B. It maps sentences & paragraphs to a 2560-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

• Model Type: Sentence Transformer
• Base model: Qwen/Qwen3-Embedding-4B
• Maximum Sequence Length: 40960 tokens
• Output Dimensionality: 2560 dimensions
• Similarity Function: Cosine Similarity

Model Sources

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

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 40960, 'do_lower_case': False, 'architecture': 'Qwen3Model'})
  (1): Pooling({'word_embedding_dimension': 2560, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': True, '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("TakalaWang/qwen3-embedding-4B-code-search")
# Run inference
queries = [
    "list[VolumeExtent]: sections.",
]
documents = [
    'def equals(self, other):\n        \n        self._run(unittest_case.assertEqual, (self._subject, other))\n        return ChainInspector(self._subject)',
    'def cast_to_a1_notation(method):\n    \n    @wraps(method)\n    def wrapper(self, *args, **kwargs):\n        try:\n            if len(args):\n                int(args[0])\n\n            \n            range_start = rowcol_to_a1(*args[:2])\n            range_end = rowcol_to_a1(*args[-2:])\n            range_name = .join((range_start, range_end))\n\n            args = (range_name,) + args[4:]\n        except ValueError:\n            pass\n\n        return method(self, *args, **kwargs)\n\n    return wrapper',
    'def readfmt(self, fmt):\n        \n        size = struct.calcsize(fmt)\n        blob = self.read(size)\n        obj, = struct.unpack(fmt, blob)\n        return obj',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 2560] [3, 2560]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[1., 1., 1.]], dtype=torch.float16)

Training Details

Training Dataset

Unnamed Dataset

• Size: 800 training samples
• Columns: sentence_0, sentence_1, and label
• Approximate statistics based on the first 800 samples:

  	sentence_0	sentence_1	label
  type	string	string	float
  details	min: 2 tokensmean: 65.92 tokensmax: 3156 tokens	min: 21 tokensmean: 132.37 tokensmax: 1236 tokens	min: 0.0mean: 0.5max: 1.0

• Samples:

  sentence_0	sentence_1	label
  Go through a stream and print out anything not in observed set	def t_VAR(self, t): r t.type = self.reserved.get(t.value.lower(), ) return t	0.0
  Move a page to before some other page of the document. Specify 'to = -1' to move after last page.	def movePage(self, pno, to = -1): pl = list(range(len(self))) if pno < 0 or pno > pl[-1]: raise ValueError(" page number out of range") if to < -1 or to > pl[-1]: raise ValueError(" page number out of range") pl.remove(pno) if to == -1: pl.append(pno) else: pl.insert(to-1, pno) return self.select(pl)	1.0
  Create an empty dataset in the current repo.	def libvlc_media_player_set_agl(p_mi, drawable): f = _Cfunctions.get(, None) or <br> _Cfunction(, ((1,), (1,),), None, None, MediaPlayer, ctypes.c_uint32) return f(p_mi, drawable)	0.0

• Loss: ContrastiveLoss with these parameters:

  {
      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
      "margin": 0.5,
      "size_average": true
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 1
• per_device_eval_batch_size: 1
• num_train_epochs: 2
• multi_dataset_batch_sampler: round_robin

All Hyperparameters

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: no
• prediction_loss_only: True
• per_device_train_batch_size: 1
• per_device_eval_batch_size: 1
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 1
• eval_accumulation_steps: None
• torch_empty_cache_steps: None
• learning_rate: 5e-05
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1.0
• num_train_epochs: 2
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.0
• warmup_steps: 0
• log_level: passive
• log_level_replica: warning
• log_on_each_node: True
• logging_nan_inf_filter: True
• save_safetensors: True
• save_on_each_node: False
• save_only_model: False
• restore_callback_states_from_checkpoint: False
• no_cuda: False
• use_cpu: False
• use_mps_device: False
• seed: 42
• data_seed: None
• jit_mode_eval: False
• use_ipex: False
• bf16: False
• fp16: False
• fp16_opt_level: O1
• half_precision_backend: auto
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: None
• local_rank: 0
• ddp_backend: None
• tpu_num_cores: None
• tpu_metrics_debug: False
• debug: []
• dataloader_drop_last: False
• dataloader_num_workers: 0
• dataloader_prefetch_factor: None
• past_index: -1
• disable_tqdm: False
• remove_unused_columns: True
• label_names: None
• load_best_model_at_end: False
• ignore_data_skip: False
• fsdp: []
• fsdp_min_num_params: 0
• fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
• fsdp_transformer_layer_cls_to_wrap: None
• 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
• adafactor: False
• group_by_length: False
• length_column_name: length
• 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
• use_legacy_prediction_loop: False
• 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: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• include_for_metrics: []
• eval_do_concat_batches: True
• fp16_backend: auto
• push_to_hub_model_id: None
• push_to_hub_organization: None
• mp_parameters:
• auto_find_batch_size: False
• full_determinism: False
• torchdynamo: None
• ray_scope: last
• ddp_timeout: 1800
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• include_tokens_per_second: False
• include_num_input_tokens_seen: False
• 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: False
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: round_robin
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Framework Versions

• Python: 3.13.7
• Sentence Transformers: 5.1.1
• Transformers: 4.56.2
• PyTorch: 2.8.0+cu128
• Accelerate: 1.10.1
• Datasets: 4.1.1
• Tokenizers: 0.22.1

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",
}

ContrastiveLoss

@inproceedings{hadsell2006dimensionality,
    author={Hadsell, R. and Chopra, S. and LeCun, Y.},
    booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
    title={Dimensionality Reduction by Learning an Invariant Mapping},
    year={2006},
    volume={2},
    number={},
    pages={1735-1742},
    doi={10.1109/CVPR.2006.100}
}