Downloads · 30 days
0
boyes-boys-clef-2026/bge-m3-checkthat-finetuned
bge-m3-checkthat-finetuned is a sentence similarity model from boyes-boys-clef-2026. Use it when you need a score for how close two texts are. It is set up for sentence-transformers.
This is a sentence-transformers model finetuned from BAAI/bge-m3 on the json dataset. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic s…
Downloads · 30 days
0
Access
Public
Updated Apr 6, 2026
Repo size
21.9 MB
Likes
0
Public
Click a slice to open those files.
.json17.1 MB · 78%
From the Hugging Face model README
This is a sentence-transformers model finetuned from BAAI/bge-m3 on the json dataset. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
SentenceTransformer(
(0): Transformer({'max_seq_length': 1024, 'do_lower_case': False, 'architecture': 'XLMRobertaModel'})
(1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
(2): Normalize()
)
First install the Sentence Transformers library:
pip install -U sentence-transformers
Then you can load this model and run inference.
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("sentence_transformers_model_id")
# Run inference
sentences = [
"Title: Ocean Warming and Species Migration\nAbstract: This study demonstrates how rising global ocean temperatures are forcing marine species to migrate towards the poles, drastically altering coastal biodiversity.",
"Title: The Fall of the Roman Empire\nAbstract: A historical overview of the political instability and economic decline that led to the collapse of ancient Rome."
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[ 1.0000, 0.3432, 0.0684],
# [ 0.3432, 1.0000, -0.0791],
# [ 0.0684, -0.0791, 1.0000]])
<!--
### 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.*
-->
multilingual_dev| Metric | Value |
|---|---|
| cosine_accuracy@1 | 0.4849 |
| cosine_accuracy@3 | 0.6247 |
| cosine_accuracy@5 | 0.6701 |
| cosine_accuracy@10 | 0.727 |
| cosine_precision@1 | 0.4849 |
| cosine_precision@3 | 0.2082 |
| cosine_precision@5 | 0.134 |
| cosine_precision@10 | 0.0727 |
| cosine_recall@1 | 0.4849 |
| cosine_recall@3 | 0.6247 |
| cosine_recall@5 | 0.6701 |
| cosine_recall@10 | 0.727 |
| cosine_ndcg@10 | 0.6042 |
| cosine_mrr@10 | 0.5652 |
| cosine_map@100 | 0.5714 |
| anchor | positive | negative | |
|---|---|---|---|
| type | string | string | string |
| details | <ul><li>min: 16 tokens</li><li>mean: 54.8 tokens</li><li>max: 131 tokens</li></ul> | <ul><li>min: 20 tokens</li><li>mean: 376.81 tokens</li><li>max: 1024 tokens</li></ul> | <ul><li>min: 34 tokens</li><li>mean: 493.4 tokens</li><li>max: 1024 tokens</li></ul> |
{
"scale": 20.0,
"similarity_fct": "cos_sim",
"gather_across_devices": false,
"directions": [
"query_to_doc"
],
"partition_mode": "joint",
"hardness_mode": null,
"hardness_strength": 0.0
}
per_device_train_batch_size: 256learning_rate: 0.0002warmup_steps: 0.1bf16: Truegradient_checkpointing: Trueauto_find_batch_size: Trueeval_strategy: epochload_best_model_at_end: Trueper_device_train_batch_size: 256num_train_epochs: 3max_steps: -1learning_rate: 0.0002lr_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: 1average_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: 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: Truelog_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: epochper_device_eval_batch_size: 8prediction_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: 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: 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: Nonebatch_sampler: batch_samplermulti_dataset_batch_sampler: proportionalrouter_mapping: {}learning_rate_mapping: {}| Epoch | Step | Training Loss | multilingual_dev_cosine_ndcg@10 |
|---|---|---|---|
| 0.2591 | 50 | 2.7015 | - |
| 0.5181 | 100 | 1.8153 | - |
| 0.7772 | 150 | 1.6928 | - |
| 1.0 | 193 | - | 0.5955 |
| 1.0363 | 200 | 1.5920 | - |
| 1.2953 | 250 | 1.5472 | - |
| 1.5544 | 300 | 1.5706 | - |
| 1.8135 | 350 | 1.5373 | - |
| 2.0 | 386 | - | 0.6031 |
| 2.0725 | 400 | 1.5254 | - |
| 2.3316 | 450 | 1.4881 | - |
| 2.5907 | 500 | 1.4739 | - |
| 2.8497 | 550 | 1.4972 | - |
| 3.0 | 579 | - | 0.6042 |
@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",
}
@misc{oord2019representationlearningcontrastivepredictive,
title={Representation Learning with Contrastive Predictive Coding},
author={Aaron van den Oord and Yazhe Li and Oriol Vinyals},
year={2019},
eprint={1807.03748},
archivePrefix={arXiv},
primaryClass={cs.LG},
url={https://arxiv.org/abs/1807.03748},
}
<!--
## 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.*
-->