Downloads · 30 days
77
27% of all-time downloads
tomaarsen/reranker-Qwen3.5-0.8B-doodles-image-text-to-text-causal-score-head
reranker-Qwen3.5-0.8B-doodles-image-text-to-text-causal-score-head is a text ranking model from tomaarsen. Use it for the text ranking task on the model card, and read the license before you ship it in a product. It is set up for sentence-transformers.
This is a Cross Encoder model finetuned from Qwen/Qwen3.5-0.8B on the imagetotext and texttoimage datasets using the sentence-transformers library. It computes scores for pairs of texts, which can be used for text rer…
Downloads · 30 days
77
27% of all-time downloads
All-time downloads
285
Public
Parameters
853M
1.7 GB on disk
Likes
12
Public
Click a slice to open those files.
.safetensors1.7 GB · 99%
From the Hugging Face model README
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.
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'}}, 'module_output_name': 'causal_logits', 'message_format': 'auto', 'processing_kwargs': {'chat_template': {'add_generation_prompt': True}}, 'architecture': 'Qwen3_5ForConditionalGeneration'})
(1): CausalScoreHead({'true_token_id': 16, 'false_token_id': 15})
)
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("tomaarsen/reranker-Qwen3.5-0.8B-doodles-image-text-to-text-causal-score-head")
# Get scores for pairs of inputs
pairs = [
['https://huggingface.co/tomaarsen/reranker-Qwen3.5-0.8B-doodles-image-text-to-text-causal-score-head/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/tomaarsen/reranker-Qwen3.5-0.8B-doodles-image-text-to-text-causal-score-head/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/tomaarsen/reranker-Qwen3.5-0.8B-doodles-image-text-to-text-causal-score-head/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/tomaarsen/reranker-Qwen3.5-0.8B-doodles-image-text-to-text-causal-score-head/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/tomaarsen/reranker-Qwen3.5-0.8B-doodles-image-text-to-text-causal-score-head/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)
# [ 0.75 -0.3125 -0.1875 0.0625 -0.3125]
<!--
### 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.*
-->
doodles-image-to-text-eval and doodles-text-to-image-eval{
"at_k": 10
}
| Metric | doodles-image-to-text-eval | doodles-text-to-image-eval |
|---|---|---|
| map | 0.9933 | 0.9303 |
| mrr@10 | 0.9933 | 0.9295 |
| ndcg@10 | 0.995 | 0.9468 |
| image | text | label | |
|---|---|---|---|
| type | image | string | int |
| details | <ul><li>min: 128x128 px</li><li>mean: 128x128 px</li><li>max: 128x128 px</li></ul> | <ul><li>min: 29 tokens</li><li>mean: 33.45 tokens</li><li>max: 40 tokens</li></ul> | <ul><li>0: ~80.00%</li><li>1: ~20.00%</li></ul> |
| image | text | label |
|---|---|---|
| <img src="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="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="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> |
{
"activation_fn": "torch.nn.modules.linear.Identity",
"pos_weight": null
}
| text | image | label | |
|---|---|---|---|
| type | string | image | int |
| details | <ul><li>min: 29 tokens</li><li>mean: 33.51 tokens</li><li>max: 40 tokens</li></ul> | <ul><li>min: 128x128 px</li><li>mean: 128x128 px</li><li>max: 128x128 px</li></ul> | <ul><li>0: ~80.00%</li><li>1: ~20.00%</li></ul> |
| 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="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="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="assets/example_image_2.jpg" width="200"> | <code>0</code> |
{
"activation_fn": "torch.nn.modules.linear.Identity",
"pos_weight": null
}
| image | text | label | |
|---|---|---|---|
| type | image | string | int |
| 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: 33.05 tokens</li><li>max: 38 tokens</li></ul> | <ul><li>0: ~80.00%</li><li>1: ~20.00%</li></ul> |
| image | text | label |
|---|---|---|
| <img src="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="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="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> |
{
"activation_fn": "torch.nn.modules.linear.Identity",
"pos_weight": null
}
| text | image | label | |
|---|---|---|---|
| type | string | image | int |
| details | <ul><li>min: 27 tokens</li><li>mean: 33.21 tokens</li><li>max: 38 tokens</li></ul> | <ul><li>min: 128x128 px</li><li>mean: 128x128 px</li><li>max: 128x128 px</li></ul> | <ul><li>0: ~80.00%</li><li>1: ~20.00%</li></ul> |
| text | image | label |
|---|---|---|
| <code>a content character with a tan head and purple puffballs hair wearing a blue fleece, green background</code> | <img src="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="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="assets/example_image_4.jpg" width="200"> | <code>0</code> |
{
"activation_fn": "torch.nn.modules.linear.Identity",
"pos_weight": null
}
num_train_epochs: 1learning_rate: 5e-06warmup_steps: 0.1gradient_accumulation_steps: 4bf16: Trueeval_strategy: stepsper_device_eval_batch_size: 32prompts: {'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."}per_device_train_batch_size: 8num_train_epochs: 1max_steps: -1learning_rate: 5e-06lr_scheduler_type: linearlr_scheduler_kwargs: Nonewarmup_steps: 0.1optim: adamw_torch_fusedoptim_args: Noneweight_decay: 0.0adam_beta1: 0.9adam_beta2: 0.999adam_epsilon: 1e-08optim_target_modules: Nonegradient_accumulation_steps: 4average_tokens_across_devices: Truemax_grad_norm: 1.0label_smoothing_factor: 0.0bf16: Truefp16: Falsebf16_full_eval: Falsefp16_full_eval: Falsetf32: Nonegradient_checkpointing: Falsegradient_checkpointing_kwargs: Nonetorch_compile: Falsetorch_compile_backend: Nonetorch_compile_mode: Noneuse_liger_kernel: Falseliger_kernel_config: Noneuse_cache: Falseneftune_noise_alpha: Nonetorch_empty_cache_steps: Noneauto_find_batch_size: Falselog_on_each_node: Truelogging_nan_inf_filter: Trueinclude_num_input_tokens_seen: nolog_level: passivelog_level_replica: warningdisable_tqdm: Falseproject: huggingfacetrackio_space_id: trackioeval_strategy: stepsper_device_eval_batch_size: 32prediction_loss_only: Trueeval_on_start: Falseeval_do_concat_batches: Trueeval_use_gather_object: Falseeval_accumulation_steps: Noneinclude_for_metrics: []batch_eval_metrics: Falsesave_only_model: Falsesave_on_each_node: Falseenable_jit_checkpoint: Falsepush_to_hub: Falsehub_private_repo: Nonehub_model_id: Nonehub_strategy: every_savehub_always_push: Falsehub_revision: Noneload_best_model_at_end: Falseignore_data_skip: Falserestore_callback_states_from_checkpoint: Falsefull_determinism: Falseseed: 42data_seed: Noneuse_cpu: Falseaccelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}parallelism_config: Nonedataloader_drop_last: Falsedataloader_num_workers: 0dataloader_pin_memory: Truedataloader_persistent_workers: Falsedataloader_prefetch_factor: Noneremove_unused_columns: Truelabel_names: Nonetrain_sampling_strategy: randomlength_column_name: lengthddp_find_unused_parameters: Noneddp_bucket_cap_mb: Noneddp_broadcast_buffers: Falseddp_backend: Noneddp_timeout: 1800fsdp: []fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}deepspeed: Nonedebug: []skip_memory_metrics: Truedo_predict: Falseresume_from_checkpoint: Nonewarmup_ratio: Nonelocal_rank: -1prompts: {'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_samplermulti_dataset_batch_sampler: proportionalrouter_mapping: {}learning_rate_mapping: {}| Epoch | Step | Training Loss | image to text loss | text to image loss | doodles-image-to-text-eval_ndcg@10 | doodles-text-to-image-eval_ndcg@10 |
|---|---|---|---|---|---|---|
| -1 | -1 | - | - | - | 0.8246 | 0.4697 |
| 0.1030 | 29 | 0.2991 | - | - | - | - |
| 0.2060 | 58 | 0.2055 | - | - | - | - |
| 0.2522 | 71 | - | 0.0725 | 0.2936 | 0.9717 | 0.8622 |
| 0.3091 | 87 | 0.1365 | - | - | - | - |
| 0.4121 | 116 | 0.1005 | - | - | - | - |
| 0.5044 | 142 | - | 0.0534 | 0.0566 | 0.995 | 0.9415 |
| 0.5151 | 145 | 0.0528 | - | - | - | - |
| 0.6181 | 174 | 0.0752 | - | - | - | - |
| 0.7211 | 203 | 0.0750 | - | - | - | - |
| 0.7567 | 213 | - | 0.0467 | 0.0389 | 0.995 | 0.9473 |
| 0.8242 | 232 | 0.0691 | - | - | - | - |
| 0.9272 | 261 | 0.0758 | - | - | - | - |
| -1 | -1 | - | - | - | 0.995 | 0.9468 |
Carbon emissions were measured using CodeCarbon.
@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.*
-->