CrossEncoder based on yoriis/GTE-tydi
This is a Cross Encoder model finetuned from yoriis/GTE-tydi 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: yoriis/GTE-tydi
- Maximum Sequence Length: 512 tokens
- Number of Output Labels: 1 label
Model Sources
- Documentation: Sentence Transformers Documentation
- Documentation: Cross Encoder Documentation
- Repository: Sentence Transformers on GitHub
- Hugging Face: Cross Encoders on Hugging Face
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 ๐ค Hub
model = CrossEncoder("yoriis/GTE-tydi-tafseer-quqa-haqa")
# Get scores for pairs of texts
pairs = [
['ูู ุชุฑู ุงูุตูุงุฉ ุชูุงููุง ููุณูุง ูุจูุฑุฉ ู
ู ุงููุจุงุฆุฑุ ูู
ู ุงูุนูู
ุงุก ู
ู ูุงู ุจููุฑูุ ูู ูุฐุง ุงูุญูู
ูู ุชูุฌููู ู
ู ุงูุณูุฉ ุงููุจููุฉุ', 'ุญุฏูุซ ุทูุงุฑููู ุจููู ุดูููุงุจู ุฑุถู ุงููู ุนููุ ุนููู ุงููููุจูููู ๏ทบ ููุงูู: ยซุงูุฌูู
ูุนูุฉู ุญูููู ููุงุฌูุจู ุนูููู ููููู ู
ูุณูููู
ู ููู ุฌูู
ูุงุนูุฉู ุฅููููุง ุฃูุฑูุจูุนูุฉู: ุนูุจูุฏู ู
ูู
ููููููุ ุฃููู ุงู
ูุฑูุฃูุฉูุ ุฃููู ุตูุจููููุ ุฃููู ู
ูุฑููุถูยป. ุฑูุงู ุฃุจู ุฏุงูุฏ (1067)ุ ูุตุญุญู ุงูุฃูุจุงูู ูู ุฅุฑูุงุก ุงูุบููู (592)ุ ูุงููุงุฏุนู ูู ุงูุตุญูุญ ุงูู
ุณูุฏ (517) .'],
['ู
ู ูู ุงููุจู ุงูุฐู ูุงู ูุนู
ู ูุฌุงุฑุง ุ', 'ุนู ุฃุจู ุจู ูุนุจ ุฑุถู ุงููู ุนูู ูุงู: ยซุฅู ุฑุณูู ุงููู ๏ทบ ูุงู ููุชุฑ ููููุช ูุจู ุงูุฑููุนยป. ุฃุฎุฑุฌู ุงุจู ู
ุงุฌู.'],
['ู
ุง ุณุจุจ ูุฑุงููุฉ ุงูุตูุงุฉ ุนูู ุงูุณุฌูุงุฏ ุงูู
ุฒุฎุฑูุ', 'ุงุจู ุนุจุงุณ ุฑุถู ุงููู ุนูู ุนู ุงููุจู ๏ทบ ุฃูู ูุงู: (ู
ู ุณู
ุน ุงููุฏุงุก ููู
ูุฃุชูุ ููุง ุตูุงุฉ ูู ุฅูุง ู
ู ุนุฐุฑ). ุฃุฎุฑุฌู ุงุจู ู
ุงุฌู'],
['ู
ู ูู ุงูุตุญุงุจู ุงูุฐู ูุงู ููู ุงููุจู ๏ทบ: ยซู
ู ุฎูุฑ ุฐู ูู
ู ูุนูู ูุฌูู ู
ุณุญุฉ ู
ููยป ุ', 'ุญุฏูุซ ุฌูุฑููุฑ ุจูู ุนูุจูุฏู ุงููู ุงูุจูุฌูููููู ุฑุถู ุงููู ุนููุ ู
ูุง ุฑูุขููู ุฑูุณูููู ุงููู ๏ทบ ููุทูู ุฅููููุง ุชูุจูุณููู
ู ููู ููุฌูููู ููุงูู: ููููุงูู ุฑูุณูููู ุงููู ๏ทบ: ยซููุทูููุนู ุนูููููููู
ู ู
ููู ููุฐูุง ุงูุจูุงุจู ุฑูุฌููู ู
ููู ุฎูููุฑู ุฐูู ููู
ูููุ ุนูููู ููุฌููููู ู
ูุณูุญูุฉู ู
ูููููุ ููุทูููุนู ุฌูุฑููุฑู ุจููู ุนูุจูุฏู ุงูููยป. ููู ูู ู
ุณูุฏ ุงูุฅู
ุงู
ุฃุญู
ุฏ (19179)ุ ููู ูู ุงูุตุญูุญุฉ (3193)ุ ููู ุงูุตุญูุญ ุงูู
ุณูุฏ (262).'],
['ู
ุง ูุถู ุตูุงุฉ ุงููููุ', 'ุนููู ุฃูุจูู ููุฑูููุฑูุฉู ุฑุถู ุงููู ุนููุ ุฃูููู ุฑูุณูููู ุงููู ๏ทบ ููุงูู: ยซููููุณู ุงูุดููุฏููุฏู ุจูุงูุตููุฑูุนูุฉู ุฅููููู
ูุง ุงูุดููุฏููุฏู ุงูููุฐูู ููู
ููููู ููููุณููู ุนูููุฏู ุงูุบูุถูุจูยป. ุฑูุงู ุงูุจุฎุงุฑู (6114)ุ ูู
ุณูู
(2609).'],
]
scores = model.predict(pairs)
print(scores.shape)
# (5,)
# Or rank different texts based on similarity to a single text
ranks = model.rank(
'ูู ุชุฑู ุงูุตูุงุฉ ุชูุงููุง ููุณูุง ูุจูุฑุฉ ู
ู ุงููุจุงุฆุฑุ ูู
ู ุงูุนูู
ุงุก ู
ู ูุงู ุจููุฑูุ ูู ูุฐุง ุงูุญูู
ูู ุชูุฌููู ู
ู ุงูุณูุฉ ุงููุจููุฉุ',
[
'ุญุฏูุซ ุทูุงุฑููู ุจููู ุดูููุงุจู ุฑุถู ุงููู ุนููุ ุนููู ุงููููุจูููู ๏ทบ ููุงูู: ยซุงูุฌูู
ูุนูุฉู ุญูููู ููุงุฌูุจู ุนูููู ููููู ู
ูุณูููู
ู ููู ุฌูู
ูุงุนูุฉู ุฅููููุง ุฃูุฑูุจูุนูุฉู: ุนูุจูุฏู ู
ูู
ููููููุ ุฃููู ุงู
ูุฑูุฃูุฉูุ ุฃููู ุตูุจููููุ ุฃููู ู
ูุฑููุถูยป. ุฑูุงู ุฃุจู ุฏุงูุฏ (1067)ุ ูุตุญุญู ุงูุฃูุจุงูู ูู ุฅุฑูุงุก ุงูุบููู (592)ุ ูุงููุงุฏุนู ูู ุงูุตุญูุญ ุงูู
ุณูุฏ (517) .',
'ุนู ุฃุจู ุจู ูุนุจ ุฑุถู ุงููู ุนูู ูุงู: ยซุฅู ุฑุณูู ุงููู ๏ทบ ูุงู ููุชุฑ ููููุช ูุจู ุงูุฑููุนยป. ุฃุฎุฑุฌู ุงุจู ู
ุงุฌู.',
'ุงุจู ุนุจุงุณ ุฑุถู ุงููู ุนูู ุนู ุงููุจู ๏ทบ ุฃูู ูุงู: (ู
ู ุณู
ุน ุงููุฏุงุก ููู
ูุฃุชูุ ููุง ุตูุงุฉ ูู ุฅูุง ู
ู ุนุฐุฑ). ุฃุฎุฑุฌู ุงุจู ู
ุงุฌู',
'ุญุฏูุซ ุฌูุฑููุฑ ุจูู ุนูุจูุฏู ุงููู ุงูุจูุฌูููููู ุฑุถู ุงููู ุนููุ ู
ูุง ุฑูุขููู ุฑูุณูููู ุงููู ๏ทบ ููุทูู ุฅููููุง ุชูุจูุณููู
ู ููู ููุฌูููู ููุงูู: ููููุงูู ุฑูุณูููู ุงููู ๏ทบ: ยซููุทูููุนู ุนูููููููู
ู ู
ููู ููุฐูุง ุงูุจูุงุจู ุฑูุฌููู ู
ููู ุฎูููุฑู ุฐูู ููู
ูููุ ุนูููู ููุฌููููู ู
ูุณูุญูุฉู ู
ูููููุ ููุทูููุนู ุฌูุฑููุฑู ุจููู ุนูุจูุฏู ุงูููยป. ููู ูู ู
ุณูุฏ ุงูุฅู
ุงู
ุฃุญู
ุฏ (19179)ุ ููู ูู ุงูุตุญูุญุฉ (3193)ุ ููู ุงูุตุญูุญ ุงูู
ุณูุฏ (262).',
'ุนููู ุฃูุจูู ููุฑูููุฑูุฉู ุฑุถู ุงููู ุนููุ ุฃูููู ุฑูุณูููู ุงููู ๏ทบ ููุงูู: ยซููููุณู ุงูุดููุฏููุฏู ุจูุงูุตููุฑูุนูุฉู ุฅููููู
ูุง ุงูุดููุฏููุฏู ุงูููุฐูู ููู
ููููู ููููุณููู ุนูููุฏู ุงูุบูุถูุจูยป. ุฑูุงู ุงูุจุฎุงุฑู (6114)ุ ูู
ุณูู
(2609).',
]
)
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]
Evaluation
Metrics
Cross Encoder Classification
- Dataset:
eval - Evaluated with
CrossEncoderClassificationEvaluator
| Metric | Value |
|---|---|
| accuracy | 1.0 |
| accuracy_threshold | 0.8513 |
| f1 | 1.0 |
| f1_threshold | 0.8513 |
| precision | 1.0 |
| recall | 1.0 |
| average_precision | 1.0 |
Cross Encoder Classification
- Dataset:
eval - Evaluated with
CrossEncoderClassificationEvaluator
| Metric | Value |
|---|---|
| accuracy | 0.9362 |
| accuracy_threshold | 0.401 |
| f1 | 0.8677 |
| f1_threshold | 0.2964 |
| precision | 0.901 |
| recall | 0.8368 |
| average_precision | 0.9243 |
Cross Encoder Classification
- Dataset:
eval - Evaluated with
CrossEncoderClassificationEvaluator
| Metric | Value |
|---|---|
| accuracy | 0.8655 |
| accuracy_threshold | 0.8725 |
| f1 | 0.3968 |
| f1_threshold | 0.1597 |
| precision | 0.5435 |
| recall | 0.3125 |
| average_precision | 0.4704 |
Training Details
Training Dataset
Unnamed Dataset
- Size: 8,623 training samples
- Columns:
sentence_0,sentence_1, andlabel - Approximate statistics based on the first 1000 samples:
sentence_0 sentence_1 label type string string float details - min: 9 characters
- mean: 35.96 characters
- max: 132 characters
- min: 39 characters
- mean: 286.62 characters
- max: 12356 characters
- min: 0.0
- mean: 0.16
- max: 1.0
- Samples:
sentence_0 sentence_1 label ูู ุชุฑู ุงูุตูุงุฉ ุชูุงููุง ููุณูุง ูุจูุฑุฉ ู ู ุงููุจุงุฆุฑุ ูู ู ุงูุนูู ุงุก ู ู ูุงู ุจููุฑูุ ูู ูุฐุง ุงูุญูู ูู ุชูุฌููู ู ู ุงูุณูุฉ ุงููุจููุฉุุญุฏูุซ ุทูุงุฑููู ุจููู ุดูููุงุจู ุฑุถู ุงููู ุนููุ ุนููู ุงููููุจูููู ๏ทบ ููุงูู: ยซุงูุฌูู ูุนูุฉู ุญูููู ููุงุฌูุจู ุนูููู ููููู ู ูุณูููู ู ููู ุฌูู ูุงุนูุฉู ุฅููููุง ุฃูุฑูุจูุนูุฉู: ุนูุจูุฏู ู ูู ููููููุ ุฃููู ุงู ูุฑูุฃูุฉูุ ุฃููู ุตูุจููููุ ุฃููู ู ูุฑููุถูยป. ุฑูุงู ุฃุจู ุฏุงูุฏ (1067)ุ ูุตุญุญู ุงูุฃูุจุงูู ูู ุฅุฑูุงุก ุงูุบููู (592)ุ ูุงููุงุฏุนู ูู ุงูุตุญูุญ ุงูู ุณูุฏ (517) .0.0ู ู ูู ุงููุจู ุงูุฐู ูุงู ูุนู ู ูุฌุงุฑุง ุุนู ุฃุจู ุจู ูุนุจ ุฑุถู ุงููู ุนูู ูุงู: ยซุฅู ุฑุณูู ุงููู ๏ทบ ูุงู ููุชุฑ ููููุช ูุจู ุงูุฑููุนยป. ุฃุฎุฑุฌู ุงุจู ู ุงุฌู.0.0ู ุง ุณุจุจ ูุฑุงููุฉ ุงูุตูุงุฉ ุนูู ุงูุณุฌูุงุฏ ุงูู ุฒุฎุฑูุุงุจู ุนุจุงุณ ุฑุถู ุงููู ุนูู ุนู ุงููุจู ๏ทบ ุฃูู ูุงู: (ู ู ุณู ุน ุงููุฏุงุก ููู ูุฃุชูุ ููุง ุตูุงุฉ ูู ุฅูุง ู ู ุนุฐุฑ). ุฃุฎุฑุฌู ุงุจู ู ุงุฌู0.0 - Loss:
BinaryCrossEntropyLosswith these parameters:{ "activation_fn": "torch.nn.modules.linear.Identity", "pos_weight": null }
Training Hyperparameters
Non-Default Hyperparameters
eval_strategy: stepsnum_train_epochs: 4fp16: True
All Hyperparameters
Click to expand
overwrite_output_dir: Falsedo_predict: Falseeval_strategy: stepsprediction_loss_only: Trueper_device_train_batch_size: 8per_device_eval_batch_size: 8per_gpu_train_batch_size: Noneper_gpu_eval_batch_size: Nonegradient_accumulation_steps: 1eval_accumulation_steps: Nonetorch_empty_cache_steps: Nonelearning_rate: 5e-05weight_decay: 0.0adam_beta1: 0.9adam_beta2: 0.999adam_epsilon: 1e-08max_grad_norm: 1num_train_epochs: 4max_steps: -1lr_scheduler_type: linearlr_scheduler_kwargs: {}warmup_ratio: 0.0warmup_steps: 0log_level: passivelog_level_replica: warninglog_on_each_node: Truelogging_nan_inf_filter: Truesave_safetensors: Truesave_on_each_node: Falsesave_only_model: Falserestore_callback_states_from_checkpoint: Falseno_cuda: Falseuse_cpu: Falseuse_mps_device: Falseseed: 42data_seed: Nonejit_mode_eval: Falseuse_ipex: Falsebf16: Falsefp16: Truefp16_opt_level: O1half_precision_backend: autobf16_full_eval: Falsefp16_full_eval: Falsetf32: Nonelocal_rank: 0ddp_backend: Nonetpu_num_cores: Nonetpu_metrics_debug: Falsedebug: []dataloader_drop_last: Falsedataloader_num_workers: 0dataloader_prefetch_factor: Nonepast_index: -1disable_tqdm: Falseremove_unused_columns: Truelabel_names: Noneload_best_model_at_end: Falseignore_data_skip: Falsefsdp: []fsdp_min_num_params: 0fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}fsdp_transformer_layer_cls_to_wrap: Noneaccelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}deepspeed: Nonelabel_smoothing_factor: 0.0optim: adamw_torchoptim_args: Noneadafactor: Falsegroup_by_length: Falselength_column_name: lengthddp_find_unused_parameters: Noneddp_bucket_cap_mb: Noneddp_broadcast_buffers: Falsedataloader_pin_memory: Truedataloader_persistent_workers: Falseskip_memory_metrics: Trueuse_legacy_prediction_loop: Falsepush_to_hub: Falseresume_from_checkpoint: Nonehub_model_id: Nonehub_strategy: every_savehub_private_repo: Nonehub_always_push: Falsehub_revision: Nonegradient_checkpointing: Falsegradient_checkpointing_kwargs: Noneinclude_inputs_for_metrics: Falseinclude_for_metrics: []eval_do_concat_batches: Truefp16_backend: autopush_to_hub_model_id: Nonepush_to_hub_organization: Nonemp_parameters:auto_find_batch_size: Falsefull_determinism: Falsetorchdynamo: Noneray_scope: lastddp_timeout: 1800torch_compile: Falsetorch_compile_backend: Nonetorch_compile_mode: Noneinclude_tokens_per_second: Falseinclude_num_input_tokens_seen: Falseneftune_noise_alpha: Noneoptim_target_modules: Nonebatch_eval_metrics: Falseeval_on_start: Falseuse_liger_kernel: Falseliger_kernel_config: Noneeval_use_gather_object: Falseaverage_tokens_across_devices: Falseprompts: Nonebatch_sampler: batch_samplermulti_dataset_batch_sampler: proportionalrouter_mapping: {}learning_rate_mapping: {}
Training Logs
| Epoch | Step | Training Loss | eval_average_precision |
|---|---|---|---|
| 0.4386 | 500 | 0.1057 | 1.0 |
| 0.8772 | 1000 | 0.001 | 1.0000 |
| 1.0 | 1140 | - | 1.0 |
| 1.3158 | 1500 | 0.0008 | 1.0000 |
| 1.7544 | 2000 | 0.0005 | 1.0000 |
| 2.0 | 2280 | - | 1.0000 |
| 2.1930 | 2500 | 0.0005 | 1.0 |
| 2.6316 | 3000 | 0.0004 | 1.0 |
| 3.0 | 3420 | - | 1.0000 |
| 3.0702 | 3500 | 0.0004 | 1.0 |
| 3.5088 | 4000 | 0.0004 | 1.0000 |
| 3.9474 | 4500 | 0.0004 | 1.0 |
| 4.0 | 4560 | - | 1.0 |
| 0.3298 | 500 | 0.4486 | 0.9037 |
| 0.6596 | 1000 | 0.3242 | 0.9110 |
| 0.9894 | 1500 | 0.3305 | 0.9150 |
| 1.0 | 1516 | - | 0.9149 |
| 1.3193 | 2000 | 0.2919 | 0.9185 |
| 1.6491 | 2500 | 0.2892 | 0.9198 |
| 1.9789 | 3000 | 0.2665 | 0.9209 |
| 2.0 | 3032 | - | 0.9208 |
| 2.3087 | 3500 | 0.2782 | 0.9219 |
| 2.6385 | 4000 | 0.2888 | 0.9229 |
| 2.9683 | 4500 | 0.2502 | 0.9234 |
| 3.0 | 4548 | - | 0.9235 |
| 3.2982 | 5000 | 0.2584 | 0.9237 |
| 3.6280 | 5500 | 0.2487 | 0.9241 |
| 3.9578 | 6000 | 0.2701 | 0.9243 |
| 4.0 | 6064 | - | 0.9243 |
| 0.4638 | 500 | 0.6039 | 0.4515 |
| 0.9276 | 1000 | 0.4031 | 0.4523 |
| 1.0 | 1078 | - | 0.4551 |
| 1.3915 | 1500 | 0.3894 | 0.4598 |
| 1.8553 | 2000 | 0.3705 | 0.4625 |
| 2.0 | 2156 | - | 0.4642 |
| 2.3191 | 2500 | 0.3993 | 0.4681 |
| 2.7829 | 3000 | 0.3585 | 0.4680 |
| 3.0 | 3234 | - | 0.4688 |
| 3.2468 | 3500 | 0.3656 | 0.4679 |
| 3.7106 | 4000 | 0.3556 | 0.4706 |
| 4.0 | 4312 | - | 0.4704 |
Framework Versions
- Python: 3.11.13
- Sentence Transformers: 5.0.0
- Transformers: 4.55.0
- PyTorch: 2.6.0+cu124
- Accelerate: 1.9.0
- Datasets: 4.0.0
- Tokenizers: 0.21.4
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",
}
- Downloads last month
- 9
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
๐
Ask for provider support
Model tree for yoriis/GTE-tydi-tafseer-quqa-haqa
Base model
aubmindlab/bert-base-arabertv02
Finetuned
NAMAA-Space/GATE-Reranker-V1
Finetuned
yoriis/GTE-tydi
Evaluation results
- Accuracy on evalself-reported1.000
- Accuracy Threshold on evalself-reported0.851
- F1 on evalself-reported1.000
- F1 Threshold on evalself-reported0.851
- Precision on evalself-reported1.000
- Recall on evalself-reported1.000
- Average Precision on evalself-reported1.000
- Accuracy on evalself-reported0.936
- Accuracy Threshold on evalself-reported0.401
- F1 on evalself-reported0.868