Downloads · 30 days
0
yaobaishen/Qwen3-VL-Reranker-8B-vehicle-reid-lora-20260910-092527
Qwen3-VL-Reranker-8B-vehicle-reid-lora-20260910-092527 is a text ranking model from yaobaishen. 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. The card lists the license as apache-2.0.
This is a Cross Encoder model finetuned from Qwen/Qwen3-VL-Reranker-8B using the sentence-transformers library. It computes scores for pairs of texts, which can be used for text reranking and semantic search.
Downloads · 30 days
0
Access
Public
Updated Sep 10, 2026
Repo size
167 MB
Likes
0
Public
Click a slice to open those files.
.safetensors156 MB · 93%
From the Hugging Face model README
This is a Cross Encoder model finetuned from Qwen/Qwen3-VL-Reranker-8B 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', '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'})
)
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-vehicle-reid-lora-20260910-092527")
# Get scores for pairs of inputs
pairs = [
['/mnt/smt_nas/huwei/test_data/genvict/qwen3_vl_reranker_8b_hard_negative_dataset_vehicleid/samples/sample_003546/query.jpg', '/mnt/smt_nas/huwei/test_data/genvict/qwen3_vl_reranker_8b_hard_negative_dataset_vehicleid/samples/sample_003546/positive_01.jpg'],
['/mnt/smt_nas/huwei/test_data/genvict/qwen3_vl_reranker_8b_hard_negative_dataset_vehicleid/samples/sample_003546/query.jpg', '/mnt/smt_nas/huwei/test_data/genvict/qwen3_vl_reranker_8b_hard_negative_dataset_vehicleid/samples/sample_003546/positive_02.jpg'],
['/mnt/smt_nas/huwei/test_data/genvict/qwen3_vl_reranker_8b_hard_negative_dataset_vehicleid/samples/sample_003546/query.jpg', '/mnt/smt_nas/huwei/test_data/genvict/qwen3_vl_reranker_8b_hard_negative_dataset_vehicleid/samples/sample_003546/positive_03.jpg'],
['/mnt/smt_nas/huwei/test_data/genvict/qwen3_vl_reranker_8b_hard_negative_dataset_vehicleid/samples/sample_003546/query.jpg', '/mnt/smt_nas/huwei/test_data/genvict/qwen3_vl_reranker_8b_hard_negative_dataset_vehicleid/samples/sample_003546/hard_negative_01.jpg'],
['/mnt/smt_nas/huwei/test_data/genvict/qwen3_vl_reranker_8b_hard_negative_dataset_vehicleid/samples/sample_003546/query.jpg', '/mnt/smt_nas/huwei/test_data/genvict/qwen3_vl_reranker_8b_hard_negative_dataset_vehicleid/samples/sample_003546/hard_negative_02.jpg'],
]
scores = model.predict(pairs)
print(scores)
# [-0.125 7.0625 4.9688 -4.25 -5.375 ]
# Or rank different texts based on similarity to a single text
ranks = model.rank(
'/mnt/smt_nas/huwei/test_data/genvict/qwen3_vl_reranker_8b_hard_negative_dataset_vehicleid/samples/sample_003546/query.jpg',
[
'/mnt/smt_nas/huwei/test_data/genvict/qwen3_vl_reranker_8b_hard_negative_dataset_vehicleid/samples/sample_003546/positive_01.jpg',
'/mnt/smt_nas/huwei/test_data/genvict/qwen3_vl_reranker_8b_hard_negative_dataset_vehicleid/samples/sample_003546/positive_02.jpg',
'/mnt/smt_nas/huwei/test_data/genvict/qwen3_vl_reranker_8b_hard_negative_dataset_vehicleid/samples/sample_003546/positive_03.jpg',
'/mnt/smt_nas/huwei/test_data/genvict/qwen3_vl_reranker_8b_hard_negative_dataset_vehicleid/samples/sample_003546/hard_negative_01.jpg',
'/mnt/smt_nas/huwei/test_data/genvict/qwen3_vl_reranker_8b_hard_negative_dataset_vehicleid/samples/sample_003546/hard_negative_02.jpg',
]
)
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]
<!--
### 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.*
-->
vehicle-reid-eval-hard{
"at_k": 10
}
| Metric | Value |
|---|---|
| map | 0.9292 |
| mrr@10 | 0.9598 |
| ndcg@10 | 0.9546 |
| query | document | label | |
|---|---|---|---|
| type | string | string | int |
| modality | image | image | |
| details | <ul><li>0: ~61.54%</li><li>1: ~38.46%</li></ul> |
| query | document | label |
|---|---|---|
| <code>/mnt/smt_nas/huwei/test_data/genvict/qwen3_vl_reranker_8b_hard_negative_dataset_vehicleid/samples/sample_003546/query.jpg</code> | <code>/mnt/smt_nas/huwei/test_data/genvict/qwen3_vl_reranker_8b_hard_negative_dataset_vehicleid/samples/sample_003546/positive_01.jpg</code> | <code>1</code> |
| <code>/mnt/smt_nas/huwei/test_data/genvict/qwen3_vl_reranker_8b_hard_negative_dataset_vehicleid/samples/sample_003546/query.jpg</code> | <code>/mnt/smt_nas/huwei/test_data/genvict/qwen3_vl_reranker_8b_hard_negative_dataset_vehicleid/samples/sample_003546/positive_02.jpg</code> | <code>1</code> |
| <code>/mnt/smt_nas/huwei/test_data/genvict/qwen3_vl_reranker_8b_hard_negative_dataset_vehicleid/samples/sample_003546/query.jpg</code> | <code>/mnt/smt_nas/huwei/test_data/genvict/qwen3_vl_reranker_8b_hard_negative_dataset_vehicleid/samples/sample_003546/positive_03.jpg</code> | <code>1</code> |
{
"activation_fn": "torch.nn.modules.linear.Identity",
"pos_weight": 4.44931173324585
}
per_device_train_batch_size: 1num_train_epochs: 2warmup_steps: 0.1gradient_accumulation_steps: 4bf16: Truegradient_checkpointing: Truegradient_checkpointing_kwargs: {'use_reentrant': False}per_device_eval_batch_size: 1save_only_model: Trueload_best_model_at_end: Trueddp_find_unused_parameters: Falseddp_static_graph: Trueddp_timeout: 7200per_device_train_batch_size: 1num_train_epochs: 2max_steps: -1learning_rate: 5e-05lr_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: Truegradient_checkpointing_kwargs: {'use_reentrant': False}torch_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: Nonetrackio_bucket_id: Nonetrackio_static_space_id: Noneper_device_eval_batch_size: 1prediction_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: Truesave_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: Trueignore_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: Truedataloader_num_workers: 0dataloader_pin_memory: Truedataloader_persistent_workers: Falsedataloader_prefetch_factor: Nonedataloader_multiprocessing_context: Nonedataloader_in_order: Trueremove_unused_columns: Truelabel_names: Nonetrain_sampling_strategy: randomlength_column_name: lengthddp_find_unused_parameters: Falseddp_bucket_cap_mb: Noneddp_broadcast_buffers: Falseddp_static_graph: Trueddp_backend: Noneddp_timeout: 7200fsdp: Nonefsdp_config: Nonedeepspeed: Nonedebug: []skip_memory_metrics: Truedo_predict: Falseresume_from_checkpoint: Nonelocal_rank: -1prompts: Nonebatch_sampler: batch_samplermulti_dataset_batch_sampler: proportionalrouter_mapping: {}learning_rate_mapping: {}warmup_ratio: None| Epoch | Step | Training Loss | vehicle-reid-eval-hard_ndcg@10 |
|---|---|---|---|
| 0.1001 | 436 | 1.0771 | - |
| 0.2003 | 872 | 1.0640 | - |
| 0.3004 | 1308 | 0.8828 | - |
| 0.4006 | 1744 | 0.7514 | - |
| 0.5007 | 2180 | 0.7234 | - |
| 0.6008 | 2616 | 0.6717 | - |
| 0.7010 | 3052 | 0.6169 | - |
| 0.8011 | 3488 | 0.5405 | - |
| 0.9012 | 3924 | 0.5566 | - |
| 1.0 | 4354 | - | 0.9546 |
| 1.0014 | 4360 | 0.5274 | - |
| 1.1015 | 4796 | 0.4834 | - |
| 1.2017 | 5232 | 0.4149 | - |
| 1.3018 | 5668 | 0.4737 | - |
| 1.4019 | 6104 | 0.3860 | - |
| 1.5021 | 6540 | 0.3309 | - |
| 1.6022 | 6976 | 0.4327 | - |
| 1.7023 | 7412 | 0.4297 | - |
| 1.8025 | 7848 | 0.3587 | - |
| 1.9026 | 8284 | 0.4150 | - |
| 2.0 | 8708 | - | 0.9514 |
| -1 | -1 | - | 0.9546 |
@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.*
-->