gefgu/modernbert-activity-aligner

CrossEncoder based on nomic-ai/modernbert-embed-base

This is a Cross Encoder model finetuned from nomic-ai/modernbert-embed-base using the sentence-transformers library. It computes scores for pairs of texts, which can be used for text reranking and semantic search.

CityBehavEx

This checkpoint is the micro-activity aligner (selects detailed POI/activity types within a schedule slot) in CityBehavEx, a scalable, empirically validated LLM-assisted urban mobility simulation platform. It is served alongside CityBehavEx's other CrossEncoder aligners by scripts/serve_aligners.py and referenced directly by repo id in scenario configs (e.g. schedule.alignment_model, activities.alignment_model, profiles.coherence_alignment_model, profiles.ownership_alignment_model, activities.poi_type_alignment_model).

If you use this model, please cite CityBehavEx:

@misc{santos2026citybehavex,
  title     = {CityBehavEx: A Scalable and Empirically Validated LLM-Assisted Urban Simulation Platform},
  author    = {Santos, Gustavo H. and Viana, Aline and Silva, Thiago H.},
  year      = {2026},
  eprint    = {2607.12086},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CL},
  url       = {https://arxiv.org/abs/2607.12086}
}

Model Details

Model Description

• —Model Type: Cross Encoder
• —Base model: nomic-ai/modernbert-embed-base <!-- at revision d556a88e332558790b210f7bdbe87da2fa94a8d8 -->
• —Maximum Sequence Length: 8192 tokens
• —Number of Output Labels: 1 label
• —Supported Modality: Text <!-- - Training Dataset: Unknown --> <!-- - 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': 'sequence-classification', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'logits'}}, 'module_output_name': 'scores', 'architecture': 'ModernBertForSequenceClassification'})
)

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("cross_encoder_model_id")
# Get scores for pairs of inputs
pairs = [
    ['John is a 33-year-old male working as a professional. They have secondary or less level education and very good health. They live as: living alone. They rely on public transport or walking.\nSchedule block: diary routine-025, block 1, OTHER from 09:00 to 11:00.\nPeriod group: OTHER blocks mostly in the 06-12 period.\nTransition/history context: previous micro-activity was paidwork: Working at the office or job site.\nScore which valid time-use activity best fits this person, block, time, and history.', 'eatdrink: Eating, drinking, coffee, lunch, and meal breaks'],
    ['Joseph is a 35-year-old male working as a technician or associate professional. They have bachelor level education and fair health. They live as: living alone. They own a bike.\nSchedule block: diary routine-023, block 1, OTHER from 08:00 to 10:00.\nPeriod group: OTHER blocks mostly in the 06-12 period.\nTransition/history context: previous micro-activity was cleanetc: Cleaning, laundry, and other domestic work.\nScore which valid time-use activity best fits this person, block, time, and history.', 'eatdrink: Eating, drinking, coffee, lunch, and meal breaks'],
    ['Océane is a 41-year-old female working as a agricultural or fishery worker. They have bachelor level education and good health. They live as: living alone. They own a car and a bike.\nSchedule block: diary routine-017, block 2, WORK from 08:00 to 17:00.\nPeriod group: WORK blocks mostly in the 12-18 period.\nTransition/history context: previous micro-activity was compint: Computer, internet, gaming, and online leisure.\nScore which valid time-use activity best fits this person, block, time, and history.', 'eatdrink: Eating, drinking, coffee, lunch, and meal breaks'],
    ['Alexandre is a 50-year-old male working as a service or sales worker. They have secondary or less level education and very good health. They live as: shared housing. They own a car and a bike.\nSchedule block: diary routine-022, block 4, HOME from 18:00 to 24:00.\nPeriod group: HOME blocks mostly in the 18-24 period.\nTransition/history context: previous micro-activity was missing: Unclassified or missing diary time; shown in comparisons only.\nScore which valid time-use activity best fits this person, block, time, and history.', 'tvradio: Watching TV, listening to radio, and passive media'],
    ['Alice is a 39-year-old female working as a manager. They have secondary or less level education and good health. They live as: single parent. They own a car.\nSchedule block: diary routine-016, block 1, WORK from 07:00 to 09:00.\nPeriod group: WORK blocks mostly in the 06-12 period.\nTransition/history context: previous micro-activity was maintain: Household maintenance, repairs, and administrative upkeep.\nScore which valid time-use activity best fits this person, block, time, and history.', 'paidwork: Working at the office or job site'],
]
scores = model.predict(pairs)
print(scores)
# [0.5471 0.5512 0.6221 0.8137 0.9003]

# Or rank different texts based on similarity to a single text
ranks = model.rank(
    'John is a 33-year-old male working as a professional. They have secondary or less level education and very good health. They live as: living alone. They rely on public transport or walking.\nSchedule block: diary routine-025, block 1, OTHER from 09:00 to 11:00.\nPeriod group: OTHER blocks mostly in the 06-12 period.\nTransition/history context: previous micro-activity was paidwork: Working at the office or job site.\nScore which valid time-use activity best fits this person, block, time, and history.',
    [
        'eatdrink: Eating, drinking, coffee, lunch, and meal breaks',
        'eatdrink: Eating, drinking, coffee, lunch, and meal breaks',
        'eatdrink: Eating, drinking, coffee, lunch, and meal breaks',
        'tvradio: Watching TV, listening to radio, and passive media',
        'paidwork: Working at the office or job site',
    ]
)
# [{'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. -->

<!--

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: 5,000 training samples
• —Columns: <code>sentence0</code>, <code>sentence1</code>, and <code>label</code>
• —Approximate statistics based on the first 100 samples: | | sentence0 | sentence1 | label | |:---------|:--------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:---------------------------------------------------------------| | type | string | string | float | | modality | text | text | | | details | <ul><li>min: 113 tokens</li><li>mean: 122.89 tokens</li><li>max: 130 tokens</li></ul> | <ul><li>min: 10 tokens</li><li>mean: 14.63 tokens</li><li>max: 17 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.42</li><li>max: 0.9</li></ul> |
• —Samples: | sentence0 | sentence1 | label | |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------|:-----------------| | <code>John is a 33-year-old male working as a professional. They have secondary or less level education and very good health. They live as: living alone. They rely on public transport or walking.<br>Schedule block: diary routine-025, block 1, OTHER from 09:00 to 11:00.<br>Period group: OTHER blocks mostly in the 06-12 period.<br>Transition/history context: previous micro-activity was paidwork: Working at the office or job site.<br>Score which valid time-use activity best fits this person, block, time, and history.</code> | <code>eatdrink: Eating, drinking, coffee, lunch, and meal breaks</code> | <code>0.7</code> | | <code>Joseph is a 35-year-old male working as a technician or associate professional. They have bachelor level education and fair health. They live as: living alone. They own a bike.<br>Schedule block: diary routine-023, block 1, OTHER from 08:00 to 10:00.<br>Period group: OTHER blocks mostly in the 06-12 period.<br>Transition/history context: previous micro-activity was cleanetc: Cleaning, laundry, and other domestic work.<br>Score which valid time-use activity best fits this person, block, time, and history.</code> | <code>eatdrink: Eating, drinking, coffee, lunch, and meal breaks</code> | <code>0.7</code> | | <code>Océane is a 41-year-old female working as a agricultural or fishery worker. They have bachelor level education and good health. They live as: living alone. They own a car and a bike.<br>Schedule block: diary routine-017, block 2, WORK from 08:00 to 17:00.<br>Period group: WORK blocks mostly in the 12-18 period.<br>Transition/history context: previous micro-activity was compint: Computer, internet, gaming, and online leisure.<br>Score which valid time-use activity best fits this person, block, time, and history.</code> | <code>eatdrink: Eating, drinking, coffee, lunch, and meal breaks</code> | <code>0.6</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

All Hyperparameters

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

• —overwrite_output_dir: False
• —do_predict: False
• —prediction_loss_only: True
• —per_device_train_batch_size: 8
• —per_device_eval_batch_size: 8
• —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: 5e-05
• —weight_decay: 0.0
• —adam_beta1: 0.9
• —adam_beta2: 0.999
• —adam_epsilon: 1e-08
• —max_grad_norm: 1
• —num_train_epochs: 1
• —max_steps: -1
• —lr_scheduler_type: linear
• —lr_scheduler_kwargs: None
• —warmup_ratio: 0.0
• —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: 42
• —data_seed: None
• —jit_mode_eval: False
• —bf16: False
• —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: False
• —ignore_data_skip: False
• —fsdp: []
• —fsdp_min_num_params: 0
• —fsdp_config: {'minnumparams': 0, 'xla': False, 'xlafsdpv2': False, 'xlafsdpgrad_ckpt': False}
• —fsdp_transformer_layer_cls_to_wrap: None
• —accelerator_config: {'splitbatches': False, 'dispatchbatches': None, 'evenbatches': True, 'useseedablesampler': True, 'nonblocking': False, 'gradientaccumulationkwargs': None}
• —parallelism_config: None
• —deepspeed: None
• —label_smoothing_factor: 0.0
• —optim: adamw_torch
• —optim_args: None
• —adafactor: False
• —group_by_length: False
• —length_column_name: length
• —project: huggingface
• —trackio_space_id: trackio
• —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: False
• —resume_from_checkpoint: None
• —hub_model_id: None
• —hub_strategy: every_save
• —hub_private_repo: None
• —hub_always_push: False
• —hub_revision: None
• —gradient_checkpointing: False
• —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: no
• —neftune_noise_alpha: None
• —optim_target_modules: None
• —batch_eval_metrics: False
• —eval_on_start: False
• —use_liger_kernel: False
• —liger_kernel_config: None
• —eval_use_gather_object: False
• —average_tokens_across_devices: True
• —prompts: None
• —batch_sampler: batch_sampler
• —multi_dataset_batch_sampler: proportional
• —router_mapping: {}
• —learning_rate_mapping: {}

</details>

Training Logs

Training Time

• —Training: 9.7 minutes

Framework Versions

• —Python: 3.12.13
• —Sentence Transformers: 5.6.0
• —Transformers: 4.57.6
• —PyTorch: 2.6.0+cu124
• —Accelerate: 1.14.0
• —Datasets: 5.0.0
• —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. -->