Qwen3-Embedding-8B-GIR-1

SentenceTransformer based on Qwen/Qwen3-Embedding-8B

This is a sentence-transformers model finetuned from Qwen/Qwen3-Embedding-8B. It maps sentences & paragraphs to a 4096-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-8B <!-- at revision 1d8ad4ca9b3dd8059ad90a75d4983776a23d44af -->
• Maximum Sequence Length: 40960 tokens
• Output Dimensionality: 4096 dimensions
• Similarity Function: Cosine Similarity

<!-- - **Training Dataset:** Unknown --> <!-- - **Language:** Unknown --> <!-- - **License:** Unknown -->

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': 4096, '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("JacobLinCool/Qwen3-Embedding-8B-GIR-1")
# Run inference
queries = [
    "Generates samples of text from the provided vocabulary.\n\n  Args:\n    plain_vocab: vocabulary.\n    distribution: distribution.\n    train_samples: samples for training.\n    length: length.\n\n  Returns:\n    train_indices (np.array of Integers): random integers for training.\n      shape = [num_samples, length]\n    test_indices (np.array of Integers): random integers for testing.\n      shape = [num_samples, length]\n    plain_vocab   (list of Integers): unique vocabularies.",
]
documents = [
    'def generate_plaintext_random(plain_vocab, distribution, train_samples,\n                              length):\n  \n  if distribution is not None:\n    assert len(distribution) == len(plain_vocab)\n\n  train_indices = np.random.choice(\n      range(len(plain_vocab)), (train_samples, length), p=distribution)\n\n  return train_indices',
    'def switch(self, name):\n        \n        try:\n            switch = self.storage[self.__namespaced(name)]\n        except KeyError:\n            if not self.autocreate:\n                raise ValueError("No switch named  registered in " % (name, self.namespace))\n\n            switch = self.__create_and_register_disabled_switch(name)\n\n        switch.manager = self\n        return switch',
    'def late_filling(target, pressure=,\n                 Pc_star=,\n                 Swp_star=0.2, eta=3):\n    r\n    element = pressure.split()[0]\n    network = target.project.network\n    phase = target.project.find_phase(target)\n    pc_star = phase[Pc_star]\n    Pc = phase[pressure]\n    \n        Ts = network.map_throats(throats=target.Ts, origin=target)\n        values = values[Ts]\n    else:\n        Ps = network.map_pores(pores=target.Ps, origin=target)\n        values = values[Ps]\n    return values',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 4096] [3, 4096]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[0.8604, 0.0206, 0.1070]])

<!-- ### Direct Usage (Transformers) <details><summary>Click to see the direct usage in Transformers</summary> </details> --> <!-- ### Downstream Usage (Sentence Transformers) You can finetune this model on your own dataset. <details><summary>Click to expand</summary> </details> --> <!-- ### Out-of-Scope Use *List how the model may foreseeably be misused and address what users ought not to do with the model.* -->

Evaluation

Metrics

Information Retrieval

• Evaluated with <code>InformationRetrievalEvaluator</code>

<!-- ## Bias, Risks and Limitations *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* --> <!-- ### Recommendations *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* -->

Training Details

Training Dataset

Unnamed Dataset

• Size: 400 training samples
• Columns: <code>query</code> and <code>code</code>
• Approximate statistics based on the first 400 samples:

  	query	code
  type	string	string
  details	<ul><li>min: 2 tokens</li><li>mean: 67.12 tokens</li><li>max: 3156 tokens</li></ul>	<ul><li>min: 24 tokens</li><li>mean: 126.98 tokens</li><li>max: 1236 tokens</li></ul>

• Samples:

  query	code
  <code>For memory actions, get a list of addresses it operates on.<br><br> :param SimAction action: The action object to work with.<br> :return: A list of addresses that are accessed with that action.<br> :rtype: list</code>	<code>def _get_actual_addrs(action, state):<br> <br><br> if action.actual_addrs is None:<br> <br> addr_list = {0x60000000} <br> else:<br> addr_list = set(action.actual_addrs)<br><br> return addr_list</code>
  <code>Construct the input file of the calculation.</code>	<code>def make_input(self, with_header=False):<br> <br> s = str(self.input)<br> if with_header: s = str(self) + "\n" + s<br> return s</code>
  <code>Check worker status route</code>	<code>def check_worker_status():<br> <br> if not in request.args:<br> resp = {"status": "bad request"}<br> return jsonify(**resp)<br> else:<br> worker_id = request.args[]<br> assignment_id = request.args[]<br> allow_repeats = CONFIG.getboolean(, )<br> if allow_repeats: <br> try:<br> part = Participant.query.<br> filter(Participant.workerid == worker_id).<br> filter(Participant.assignmentid == assignment_id).one()<br> status = part.status<br> except exc.SQLAlchemyError:<br> status = NOT_ACCEPTED<br> else: <br> try:<br> matches = Participant.query.<br> filter(Participant.workerid == worker_id).all()<br> numrecs = len(matches)<br> if numrecs==0: <br> status = NOT_ACCEPTED<br> else:<br> status = max([record.status for record in matches])<br> except exc.SQLAlchemyError:<br> ...</code>

• Loss: <code>CachedMultipleNegativesRankingLoss</code> with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "mini_batch_size": 1,
      "gather_across_devices": false
  }
  

Evaluation Dataset

Unnamed Dataset

• Size: 100 evaluation samples
• Columns: <code>query</code> and <code>code</code>
• Approximate statistics based on the first 100 samples:

  	query	code
  type	string	string
  details	<ul><li>min: 5 tokens</li><li>mean: 66.56 tokens</li><li>max: 548 tokens</li></ul>	<ul><li>min: 24 tokens</li><li>mean: 142.11 tokens</li><li>max: 901 tokens</li></ul>

• Samples:

  query	code
  <code>Return the value of the android prefixed attribute in a specific tag.<br><br> This function will always try to get the attribute with a android: prefix first,<br> and will try to return the attribute without the prefix, if the attribute could not be found.<br> This is useful for some broken AndroidManifest.xml, where no android namespace is set,<br> but could also indicate malicious activity (i.e. wrongly repackaged files).<br> A warning is printed if the attribute is found without a namespace prefix.<br><br> If you require to get the exact result you need to query the tag directly:<br><br> example::<br> >>> from lxml.etree import Element<br> >>> tag = Element('bar', nsmap={'android': 'http://schemas.android.com/apk/res/android'})<br> >>> tag.set('{http://schemas.android.com/apk/res/android}foobar', 'barfoo')<br> >>> tag.set('name', 'baz')<br> # Assume that a is some APK object<br> >>> a.get_value_from_tag(tag, 'name'...</code>	<code>def get_value_from_tag(self, tag, attribute):<br> <br><br> <br> <br> value = tag.get(self._ns(attribute))<br> if value is None:<br> value = tag.get(attribute)<br><br> if value:<br> <br> log.warning("Failed to get the attribute on tag with namespace. "<br> "But found the same attribute without namespace!".format(attribute, tag.tag))<br> return value</code>
  <code>Get information about this object as a dictionary. Used by WebSocket interface to pass some<br> relevant information to client applications.</code>	<code>def get_as_datadict(self):<br> <br> return dict(type=self.class.name, tags=list(self.tags))</code>
  <code>Makes forecast with the estimated model<br><br> Parameters<br> ----------<br> h : int (default : 5)<br> How many steps ahead would you like to forecast?<br><br> past_values : int (default : 20)<br> How many past observations to show on the forecast graph?<br><br> intervals : Boolean<br> Would you like to show 95% prediction intervals for the forecast?<br><br> Returns<br> ----------<br> - Plot of the forecast</code>	<code>def plot_predict(self,h=5,past_values=20,intervals=True,**kwargs): <br> <br> import matplotlib.pyplot as plt<br> import seaborn as sns<br><br> figsize = kwargs.get(,(10,7))<br><br> if self.latent_variables.estimated is False:<br> raise Exception("No latent variables estimated!")<br> else:<br> <br> scale, shape, skewness = self._get_scale_and_shape(self.latent_variables.get_z_values(transformed=True))<br> previous_value = self.data[-1] <br> forecasted_values = np.ones(h)*self.states[-1] <br> date_index = self.shift_dates(h)<br> simulations = 10000<br> sim_vector = np.zeros([simulations,h])<br> t_params = self.transform_z()<br><br> for n in range(0,simulations): <br> rnd_q = np.random.normal(0,np.sqrt(self.latent_variables.get_z_values(transformed=True)[0]),h) <br> exp = forecasted_values.copy()<br><br> for t in range(0,h):<br> if t == 0:...</code>

• Loss: <code>CachedMultipleNegativesRankingLoss</code> with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "mini_batch_size": 1,
      "gather_across_devices": false
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: epoch
• per_device_train_batch_size: 64
• per_device_eval_batch_size: 64
• learning_rate: 2e-05
• num_train_epochs: 5
• warmup_ratio: 0.1
• seed: 2025
• bf16: True
• load_best_model_at_end: True
• optim: paged_adamw_8bit
• push_to_hub: True
• hub_model_id: JacobLinCool/Qwen3-Embedding-8B-GIR-1
• hub_private_repo: False
• gradient_checkpointing: True
• eval_on_start: True
• batch_sampler: no_duplicates

All Hyperparameters

<details><summary>Click to expand</summary>

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: epoch
• prediction_loss_only: True
• per_device_train_batch_size: 64
• per_device_eval_batch_size: 64
• 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: 2e-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: 5
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.1
• 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: 2025
• data_seed: None
• jit_mode_eval: False
• use_ipex: False
• bf16: True
• 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: True
• 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: paged_adamw_8bit
• 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: True
• resume_from_checkpoint: None
• hub_model_id: JacobLinCool/Qwen3-Embedding-8B-GIR-1
• hub_strategy: every_save
• hub_private_repo: False
• hub_always_push: False
• hub_revision: None
• gradient_checkpointing: True
• 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: True
• use_liger_kernel: False
• liger_kernel_config: None
• eval_use_gather_object: False
• average_tokens_across_devices: False
• prompts: None
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

</details>

Training Logs

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.11.11
• 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",
}

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}
}

<!-- ## Glossary *Clearly define terms in order to be accessible across audiences.* --> <!-- ## Model Card Authors *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.* --> <!-- ## Model Card Contact *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.* -->