reranker-Qwen3.5-0.8B-doodles-feature-extraction

CrossEncoder based on Qwen/Qwen3.5-0.8B

This is a Cross Encoder model finetuned from Qwen/Qwen3.5-0.8B on the image_to_text and text_to_image datasets 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/Qwen3.5-0.8B <!-- at revision 2fc06364715b967f1860aea9cf38778875588b17 -->
• Maximum Sequence Length: 262144 tokens
• Number of Output Labels: 1 label
• Supported Modalities: Text, Image, Video, Message
• Training Datasets:
  • image_to_text
  • text_to_image

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

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': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}, 'image': {'method': 'forward', 'method_output_name': 'last_hidden_state'}, 'video': {'method': 'forward', 'method_output_name': 'last_hidden_state'}, 'message': {'method': 'forward', 'method_output_name': 'last_hidden_state', 'format': 'structured'}}, 'module_output_name': 'token_embeddings', 'processing_kwargs': {'chat_template': {'add_generation_prompt': True}}, 'architecture': 'Qwen3_5Model'})
  (1): Pooling({'embedding_dimension': 1024, 'pooling_mode': 'lasttoken', 'include_prompt': True})
  (2): Dense({'in_features': 1024, 'out_features': 1, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity', 'module_input_name': 'sentence_embedding', 'module_output_name': 'scores'})
)

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("kwondw/reranker-Qwen3.5-0.8B-doodles-feature-extraction")
# Get scores for pairs of inputs
pairs = [
    ['https://huggingface.co/kwondw/reranker-Qwen3.5-0.8B-doodles-feature-extraction/resolve/main/assets/image_0.jpg', 'a content character with a tan head and purple puffballs hair wearing a blue fleece, green background'],
    ['https://huggingface.co/kwondw/reranker-Qwen3.5-0.8B-doodles-feature-extraction/resolve/main/assets/image_0.jpg', 'a grumpy character with a green head and pink hair wearing a light blue puffer, iridescent background'],
    ['https://huggingface.co/kwondw/reranker-Qwen3.5-0.8B-doodles-feature-extraction/resolve/main/assets/image_0.jpg', 'a surprised character with a pale head and green mullet hair wearing a blue backpack, purple background'],
    ['https://huggingface.co/kwondw/reranker-Qwen3.5-0.8B-doodles-feature-extraction/resolve/main/assets/image_0.jpg', 'a default character with a med head and green brushcut hair wearing a holographic sweater, gradient 4 background'],
    ['https://huggingface.co/kwondw/reranker-Qwen3.5-0.8B-doodles-feature-extraction/resolve/main/assets/image_0.jpg', 'a sunglasses character with a orange head and pink hair wearing a green hoodie, grey background'],
]
scores = model.predict(pairs)
print(scores)
# [0.8436 0.8401 0.8376 0.5936 0.807 ]

<!-- ### 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

• Datasets: doodles-image-to-text-eval and doodles-text-to-image-eval
• 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 Datasets

image_to_text

• Dataset: image_to_text at a575ac6
• Size: 4,500 training samples
• Columns: <code>image</code>, <code>text</code>, and <code>label</code>
• Approximate statistics based on the first 100 samples:

  	image	text	label
  type	image	string	int
  modality	image	text
  details	<ul><li>min: 128x128 px</li><li>mean: 128x128 px</li><li>max: 128x128 px</li></ul>	<ul><li>min: 30 tokens</li><li>mean: 33.48 tokens</li><li>max: 37 tokens</li></ul>	<ul><li>0: ~79.81%</li><li>1: ~20.19%</li></ul>

• Samples:

  image	text	label
  <img src="https://huggingface.co/kwondw/reranker-Qwen3.5-0.8B-doodles-feature-extraction/resolve/main/assets/example_image_0.jpg" width="200">	<code>a cobain glasses character with a gradient 2 head and purple puffballs hair wearing a white sweater, gradient 4 background</code>	<code>1</code>
  <img src="https://huggingface.co/kwondw/reranker-Qwen3.5-0.8B-doodles-feature-extraction/resolve/main/assets/example_image_0.jpg" width="200">	<code>a content character with a orange head and purple long hair wearing a striped sweater, yellow background</code>	<code>0</code>
  <img src="https://huggingface.co/kwondw/reranker-Qwen3.5-0.8B-doodles-feature-extraction/resolve/main/assets/example_image_0.jpg" width="200">	<code>a neutral note character with a orange head and green puffballs hair wearing a combo 2 puffer, light blue background</code>	<code>0</code>

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

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

text_to_image

• Dataset: text_to_image at a575ac6
• Size: 4,500 training samples
• Columns: <code>text</code>, <code>image</code>, and <code>label</code>
• Approximate statistics based on the first 100 samples:

  	text	image	label
  type	string	image	int
  modality	text	image
  details	<ul><li>min: 30 tokens</li><li>mean: 33.13 tokens</li><li>max: 37 tokens</li></ul>	<ul><li>min: 128x128 px</li><li>mean: 128x128 px</li><li>max: 128x128 px</li></ul>	<ul><li>0: ~79.81%</li><li>1: ~20.19%</li></ul>

• Samples:

  text	image	label
  <code>a cobain glasses character with a gradient 2 head and purple puffballs hair wearing a white sweater, gradient 4 background</code>	<img src="https://huggingface.co/kwondw/reranker-Qwen3.5-0.8B-doodles-feature-extraction/resolve/main/assets/example_image_0.jpg" width="200">	<code>1</code>
  <code>a cobain glasses character with a gradient 2 head and purple puffballs hair wearing a white sweater, gradient 4 background</code>	<img src="https://huggingface.co/kwondw/reranker-Qwen3.5-0.8B-doodles-feature-extraction/resolve/main/assets/example_image_1.jpg" width="200">	<code>0</code>
  <code>a cobain glasses character with a gradient 2 head and purple puffballs hair wearing a white sweater, gradient 4 background</code>	<img src="https://huggingface.co/kwondw/reranker-Qwen3.5-0.8B-doodles-feature-extraction/resolve/main/assets/example_image_2.jpg" width="200">	<code>0</code>

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

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

Evaluation Datasets

image_to_text

• Dataset: image_to_text at a575ac6
• Size: 500 evaluation samples
• Columns: <code>image</code>, <code>text</code>, and <code>label</code>
• Approximate statistics based on the first 100 samples:

  	image	text	label
  type	image	string	int
  modality	image	text
  details	<ul><li>min: 128x128 px</li><li>mean: 128x128 px</li><li>max: 128x128 px</li></ul>	<ul><li>min: 27 tokens</li><li>mean: 32.86 tokens</li><li>max: 37 tokens</li></ul>	<ul><li>0: ~79.81%</li><li>1: ~20.19%</li></ul>

• Samples:

  image	text	label
  <img src="https://huggingface.co/kwondw/reranker-Qwen3.5-0.8B-doodles-feature-extraction/resolve/main/assets/image_0.jpg" width="200">	<code>a content character with a tan head and purple puffballs hair wearing a blue fleece, green background</code>	<code>1</code>
  <img src="https://huggingface.co/kwondw/reranker-Qwen3.5-0.8B-doodles-feature-extraction/resolve/main/assets/image_0.jpg" width="200">	<code>a grumpy character with a green head and pink hair wearing a light blue puffer, iridescent background</code>	<code>0</code>
  <img src="https://huggingface.co/kwondw/reranker-Qwen3.5-0.8B-doodles-feature-extraction/resolve/main/assets/image_0.jpg" width="200">	<code>a surprised character with a pale head and green mullet hair wearing a blue backpack, purple background</code>	<code>0</code>

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

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

text_to_image

• Dataset: text_to_image at a575ac6
• Size: 500 evaluation samples
• Columns: <code>text</code>, <code>image</code>, and <code>label</code>
• Approximate statistics based on the first 100 samples:

  	text	image	label
  type	string	image	int
  modality	text	image
  details	<ul><li>min: 29 tokens</li><li>mean: 32.73 tokens</li><li>max: 36 tokens</li></ul>	<ul><li>min: 128x128 px</li><li>mean: 128x128 px</li><li>max: 128x128 px</li></ul>	<ul><li>0: ~79.81%</li><li>1: ~20.19%</li></ul>

• Samples:

  text	image	label
  <code>a content character with a tan head and purple puffballs hair wearing a blue fleece, green background</code>	<img src="https://huggingface.co/kwondw/reranker-Qwen3.5-0.8B-doodles-feature-extraction/resolve/main/assets/image_0.jpg" width="200">	<code>1</code>
  <code>a content character with a tan head and purple puffballs hair wearing a blue fleece, green background</code>	<img src="https://huggingface.co/kwondw/reranker-Qwen3.5-0.8B-doodles-feature-extraction/resolve/main/assets/example_image_3.jpg" width="200">	<code>0</code>
  <code>a content character with a tan head and purple puffballs hair wearing a blue fleece, green background</code>	<img src="https://huggingface.co/kwondw/reranker-Qwen3.5-0.8B-doodles-feature-extraction/resolve/main/assets/example_image_4.jpg" width="200">	<code>0</code>

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

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

Training Hyperparameters

Non-Default Hyperparameters

• num_train_epochs: 1
• learning_rate: 5e-06
• warmup_steps: 0.1
• gradient_accumulation_steps: 4
• fp16: True
• prompts: {'image_to_text': "Given the image, judge whether the text matches it. Respond with 1 if they match, 0 if they don't.", 'text_to_image': "Given the text, judge whether the image matches it. Respond with 1 if they match, 0 if they don't."}

All Hyperparameters

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

• per_device_train_batch_size: 8
• num_train_epochs: 1
• max_steps: -1
• learning_rate: 5e-06
• 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: 4
• average_tokens_across_devices: True
• max_grad_norm: 1.0
• label_smoothing_factor: 0.0
• bf16: False
• fp16: True
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: None
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• 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: 8
• 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: False
• 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: False
• 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: {'image_to_text': "Given the image, judge whether the text matches it. Respond with 1 if they match, 0 if they don't.", 'text_to_image': "Given the text, judge whether the image matches it. Respond with 1 if they match, 0 if they don't."}
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}
• warmup_ratio: None

</details>

Training Logs

Training Time

• Training: 1.8 hours

Framework Versions

• Python: 3.12.13
• Sentence Transformers: 5.7.0
• Transformers: 5.15.0
• PyTorch: 2.11.0+cu128
• Accelerate: 1.14.0
• Datasets: 4.0.0
• 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.* -->