Qwen3-VL-Reranker-8B-vdr-lora

Qwen3-VL-Reranker-8B LoRA adapter trained on Visual Document Retrieval query-document screenshot pairs

This is a Cross Encoder model finetuned from Qwen/Qwen3-VL-Reranker-8B on the llamaindex-vdr-en-train-preprocessed dataset using the sentence-transformers library. It computes scores for pairs of texts, which can be used for text reranking and semantic search.

Model Details

Model Description

• Model Type: Cross Encoder
• Base model: Qwen/Qwen3-VL-Reranker-8B <!-- at revision b212dc8c91a8164aef1ea2de9c1a867611e75c04 -->
• Maximum Sequence Length: 262144 tokens
• Number of Output Labels: 1 label
• Supported Modalities: Text, Image, Video, Message
• Training Dataset:
  • llamaindex-vdr-en-train-preprocessed
• Language: en
• License: apache-2.0

Model Sources

• Documentation: Sentence Transformers Documentation
• Documentation: Cross Encoder Documentation
• Repository: Sentence Transformers on GitHub
• Hugging Face: Cross Encoders on Hugging Face

Full Model Architecture

CrossEncoder(
  (0): Transformer({'transformer_task': 'any-to-any', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'logits'}, 'image': {'method': 'forward', 'method_output_name': 'logits'}, 'video': {'method': 'forward', 'method_output_name': 'logits'}, 'message': {'method': 'forward', 'method_output_name': 'logits', 'format': 'structured'}}, 'module_output_name': 'causal_logits', 'processing_kwargs': {'chat_template': {'chat_template': 'reranker', 'add_generation_prompt': True}}, 'architecture': 'Qwen3VLForConditionalGeneration'})
  (1): LogitScore({'true_token_id': 9693, 'false_token_id': 2152, 'module_input_name': 'causal_logits'})
)

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 CrossEncoder

# Download from the 🤗 Hub
model = CrossEncoder("yaobaishen/Qwen3-VL-Reranker-8B-vdr-lora")
# Get scores for pairs of inputs
pairs = [
    ['What are the new anthropological perspectives on development as discussed by Quarles Van Ufford and Giri in 2003?', 'https://huggingface.co/yaobaishen/Qwen3-VL-Reranker-8B-vdr-lora/resolve/main/assets/image_0.jpg'],
    ['What are the new anthropological perspectives on development as discussed by Quarles Van Ufford and Giri in 2003?', 'https://huggingface.co/yaobaishen/Qwen3-VL-Reranker-8B-vdr-lora/resolve/main/assets/image_1.jpg'],
    ['What are the three main positions anthropologists have taken in relation to development, as discussed by David Lewis?', 'https://huggingface.co/yaobaishen/Qwen3-VL-Reranker-8B-vdr-lora/resolve/main/assets/image_2.jpg'],
    ['What are the three main positions anthropologists have taken in relation to development, as discussed by David Lewis?', 'https://huggingface.co/yaobaishen/Qwen3-VL-Reranker-8B-vdr-lora/resolve/main/assets/image_1.jpg'],
    ['Who are the three sisters known as the Fates in Greek mythology?', 'https://huggingface.co/yaobaishen/Qwen3-VL-Reranker-8B-vdr-lora/resolve/main/assets/image_4.jpg'],
]
scores = model.predict(pairs)
print(scores)
# [ 4.8125 -5.625   4.875  -4.75    3.375 ]

<!-- ### 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

Cross Encoder Reranking

• Dataset: vdr-eval-hard
• Evaluated with <code>CrossEncoderRerankingEvaluator</code> with these parameters:

  {
      "at_k": 10
  }
  

<!-- ## 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

llamaindex-vdr-en-train-preprocessed

• Dataset: llamaindex-vdr-en-train-preprocessed
• Size: 20,000 training samples
• Columns: <code>query</code>, <code>document</code>, and <code>label</code>
• Approximate statistics based on the first 100 samples:

  	query	document	label
  type	string	image	int
  modality	text	image
  details	<ul><li>min: 66 tokens</li><li>mean: 66.0 tokens</li><li>max: 66 tokens</li></ul>	<ul><li>min: 1000x1125 px</li><li>mean: 1438x1653 px</li><li>max: 2044x1851 px</li></ul>	<ul><li>0: ~50.00%</li><li>1: ~50.00%</li></ul>

• Samples:

  query	document	label
  <code>What are the new anthropological perspectives on development as discussed by Quarles Van Ufford and Giri in 2003?</code>	<img src="https://huggingface.co/yaobaishen/Qwen3-VL-Reranker-8B-vdr-lora/resolve/main/assets/image_0.jpg" width="200">	<code>1</code>
  <code>What are the new anthropological perspectives on development as discussed by Quarles Van Ufford and Giri in 2003?</code>	<img src="https://huggingface.co/yaobaishen/Qwen3-VL-Reranker-8B-vdr-lora/resolve/main/assets/image_1.jpg" width="200">	<code>0</code>
  <code>What are the three main positions anthropologists have taken in relation to development, as discussed by David Lewis?</code>	<img src="https://huggingface.co/yaobaishen/Qwen3-VL-Reranker-8B-vdr-lora/resolve/main/assets/image_2.jpg" width="200">	<code>1</code>

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

  {
      "activation_fn": "torch.nn.modules.linear.Identity",
      "pos_weight": null
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 1
• num_train_epochs: 1
• warmup_steps: 0.1
• gradient_accumulation_steps: 8
• bf16: True
• gradient_checkpointing: True
• gradient_checkpointing_kwargs: {'use_reentrant': False}
• per_device_eval_batch_size: 1
• save_only_model: True
• load_best_model_at_end: True

All Hyperparameters

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

• per_device_train_batch_size: 1
• num_train_epochs: 1
• max_steps: -1
• learning_rate: 5e-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: 8
• average_tokens_across_devices: True
• max_grad_norm: 1.0
• label_smoothing_factor: 0.0
• bf16: True
• fp16: False
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: None
• gradient_checkpointing: True
• gradient_checkpointing_kwargs: {'use_reentrant': False}
• 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: 1
• 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: True
• 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: True
• 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
• dataloader_multiprocessing_context: None
• dataloader_in_order: True
• 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
• local_rank: -1
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}
• warmup_ratio: None

</details>

Training Logs

• The bold row denotes the saved checkpoint.

Training Time

• Training: 2.8 hours
• Evaluation: 27.8 minutes
• Total: 3.3 hours

Framework Versions

• Python: 3.11.13
• Sentence Transformers: 6.1.0.dev0
• Transformers: 5.15.1
• PyTorch: 2.8.0+cu128
• Accelerate: 1.14.0
• Datasets: 5.0.1
• Tokenizers: 0.22.2

Additional Resources

• Training and Finetuning Reranker Models with Sentence Transformers: the end-to-end guide for training or finetuning Cross Encoder (reranker) models.
• Multimodal Embedding & Reranker Models with Sentence Transformers: use text, image, audio, and video reranker models through the same API.
• Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers: training multimodal Cross Encoders.

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",
}

<!-- ## 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.* -->