bge-reranker-v2-m3-amazon

CrossEncoder based on BAAI/bge-reranker-v2-m3

This is a Cross Encoder model finetuned from BAAI/bge-reranker-v2-m3 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: BAAI/bge-reranker-v2-m3 <!-- at revision 953dc6f6f85a1b2dbfca4c34a2796e7dde08d41e -->
• Maximum Sequence Length: 512 tokens
• Number of Output Labels: 1 label

<!-- - **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

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("steerrec/bge-reranker-v2-m3-amazon")
# Get scores for pairs of texts
pairs = [
    ["I want something emotional and heartfelt, but not boring. I don't want another slow, dull show.", 'Civil Love Product description Civil Love Review Every so often you come across a movie you really enjoy. For me, this was it. This film contains everything a good movie needs: a good story, fine acting, direction, and a purpose. The theme of this film is that we are too quick to judge people sometimes and that people can occasionally surprise us. --Edwin L. Carpenter, Dove Foundation Movies & TV Genre for Featured Categories Drama'],
    ["I want something emotional and heartfelt, but not boring. I don't want another slow, dull show.", 'Surprised by Love A young businesswoman tries to convince her uptight parents to accept her boyfriend, but then she falls for an old high-school flame. Stars Hilarie Burton, Paul Campbell, and Tim Conway. IMDb 6.7 1 h 24 min 2015 7+ Drama Cheerful Passionate'],
    ["I want something emotional and heartfelt, but not boring. I don't want another slow, dull show.", 'All I Want for Christmas Tis the season for making dreams true. If everything goes according to plan for one young boy, he just may be sharing this Christmas with a new dad. Ever since her husband died, Sarah Armstrong has divided her time between working at a community center and caring for her nine-year-old son, Jesse. When Jesse wins the All I Want for Christmas contest sponsored by a toy company, his wish comes as no surprise to find a new dad. Just in time for the holidays, All I Want for Christmas is a surprise romantic treat for anyone who believes in the magic of love, friendship, and family. Movies & TV Holidays & Seasonal Christmas'],
    ["I just finished a few really touching movies and shows that left me feeling deeply moved and emotionally invested. I'm now looking for something that keeps that same heartfelt, character-driven vibe but with a bit more depth and complexity. I want to watch something that's a mix of drama and drama, maybe with some drama or drama, but it's hard to say. I'm looking for something that combines the elements of a story, a character, and the setting of the characters. It's like a movie where the plot is driven by the people involved, not just the events. I'm craving something that's not too fast-paced, but still has enough substance to keep me engaged. Maybe something that's a little more complex than your average film, but not so much that it feels overwhelming. I'm also interested in something that's not too dark, but still has some emotional weight. I want to feel connected to the characters and their journeys, even if they're not the most straightforward. I'm in the mood for something that's a bit more than just a movie. I need something that's a bit more intricate, with a strong narrative that's not just about the characters but the world they inhabit. I'm looking for a show that's not just a collection of characters but a full, immersive experience. I'm not sure what exactly I", "The Guardian Action-packed drama that takes you inside the never-before-seen world of the elite Coast Guard Rescue Swimmers. Reeling with grief from a mission gone tragically wrong, a legendary swimmer is given a mission he doesn't want -- training raw recruits. IMDb 6.9 2 h 19 min 2006 X-Ray PG-13 Drama Adventure Compelling Inspiring"],
    ["I just finished a few really touching movies and shows that left me feeling deeply moved and emotionally invested. I'm now looking for something that keeps that same heartfelt, character-driven vibe but with a bit more depth and complexity. I want to watch something that's a mix of drama and drama, maybe with some drama or drama, but it's hard to say. I'm looking for something that combines the elements of a story, a character, and the setting of the characters. It's like a movie where the plot is driven by the people involved, not just the events. I'm craving something that's not too fast-paced, but still has enough substance to keep me engaged. Maybe something that's a little more complex than your average film, but not so much that it feels overwhelming. I'm also interested in something that's not too dark, but still has some emotional weight. I want to feel connected to the characters and their journeys, even if they're not the most straightforward. I'm in the mood for something that's a bit more than just a movie. I need something that's a bit more intricate, with a strong narrative that's not just about the characters but the world they inhabit. I'm looking for a show that's not just a collection of characters but a full, immersive experience. I'm not sure what exactly I", 'Magnolia [VHS] An intriguing and entertaining study in characters going through varying levels of crisis and introspection. This psychological drama leads you in several different directions, weaving and intersecting various subplots and characters, from a brilliant Tom Cruise, as a self-proclaimed pied-piper, to a child forced to go on a TV game show and the pressures he faces from a ruthless father. Movies & TV Genre for Featured Categories Drama'],
]
scores = model.predict(pairs)
print(scores.shape)
# (5,)

# Or rank different texts based on similarity to a single text
ranks = model.rank(
    "I want something emotional and heartfelt, but not boring. I don't want another slow, dull show.",
    [
        'Civil Love Product description Civil Love Review Every so often you come across a movie you really enjoy. For me, this was it. This film contains everything a good movie needs: a good story, fine acting, direction, and a purpose. The theme of this film is that we are too quick to judge people sometimes and that people can occasionally surprise us. --Edwin L. Carpenter, Dove Foundation Movies & TV Genre for Featured Categories Drama',
        'Surprised by Love A young businesswoman tries to convince her uptight parents to accept her boyfriend, but then she falls for an old high-school flame. Stars Hilarie Burton, Paul Campbell, and Tim Conway. IMDb 6.7 1 h 24 min 2015 7+ Drama Cheerful Passionate',
        'All I Want for Christmas Tis the season for making dreams true. If everything goes according to plan for one young boy, he just may be sharing this Christmas with a new dad. Ever since her husband died, Sarah Armstrong has divided her time between working at a community center and caring for her nine-year-old son, Jesse. When Jesse wins the All I Want for Christmas contest sponsored by a toy company, his wish comes as no surprise to find a new dad. Just in time for the holidays, All I Want for Christmas is a surprise romantic treat for anyone who believes in the magic of love, friendship, and family. Movies & TV Holidays & Seasonal Christmas',
        "The Guardian Action-packed drama that takes you inside the never-before-seen world of the elite Coast Guard Rescue Swimmers. Reeling with grief from a mission gone tragically wrong, a legendary swimmer is given a mission he doesn't want -- training raw recruits. IMDb 6.9 2 h 19 min 2006 X-Ray PG-13 Drama Adventure Compelling Inspiring",
        'Magnolia [VHS] An intriguing and entertaining study in characters going through varying levels of crisis and introspection. This psychological drama leads you in several different directions, weaving and intersecting various subplots and characters, from a brilliant Tom Cruise, as a self-proclaimed pied-piper, to a child forced to go on a TV game show and the pressures he faces from a ruthless father. Movies & TV Genre for Featured Categories Drama',
    ]
)
# [{'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.* -->

Evaluation

Metrics

Cross Encoder Reranking

• Datasets: amazon_test and amazon_val
• Evaluated with <code>CrossEncoderRerankingEvaluator</code> with these parameters:

  {
      "at_k": 10
  }
  

<!-- ## 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: 320,937 training samples
• Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	float
  details	<ul><li>min: 78 characters</li><li>mean: 537.26 characters</li><li>max: 1341 characters</li></ul>	<ul><li>min: 48 characters</li><li>mean: 1079.61 characters</li><li>max: 10645 characters</li></ul>	<ul><li>min: 0.0</li><li>mean: 0.33</li><li>max: 1.0</li></ul>

• Samples:

  sentence1	sentence2	label
  <code>I want something emotional and heartfelt, but not boring. I don't want another slow, dull show.</code>	<code>Civil Love Product description Civil Love Review Every so often you come across a movie you really enjoy. For me, this was it. This film contains everything a good movie needs: a good story, fine acting, direction, and a purpose. The theme of this film is that we are too quick to judge people sometimes and that people can occasionally surprise us. --Edwin L. Carpenter, Dove Foundation Movies & TV Genre for Featured Categories Drama</code>	<code>0.0</code>
  <code>I want something emotional and heartfelt, but not boring. I don't want another slow, dull show.</code>	<code>Surprised by Love A young businesswoman tries to convince her uptight parents to accept her boyfriend, but then she falls for an old high-school flame. Stars Hilarie Burton, Paul Campbell, and Tim Conway. IMDb 6.7 1 h 24 min 2015 7+ Drama Cheerful Passionate</code>	<code>0.0</code>
  <code>I want something emotional and heartfelt, but not boring. I don't want another slow, dull show.</code>	<code>All I Want for Christmas Tis the season for making dreams true. If everything goes according to plan for one young boy, he just may be sharing this Christmas with a new dad. Ever since her husband died, Sarah Armstrong has divided her time between working at a community center and caring for her nine-year-old son, Jesse. When Jesse wins the All I Want for Christmas contest sponsored by a toy company, his wish comes as no surprise to find a new dad. Just in time for the holidays, All I Want for Christmas is a surprise romantic treat for anyone who believes in the magic of love, friendship, and family. Movies & TV Holidays & Seasonal Christmas</code>	<code>0.0</code>

• Loss: <code>BinaryCrossEntropyLoss</code> with these parameters:

  {
      "activation_fn": "torch.nn.modules.linear.Identity",
      "pos_weight": null
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: epoch
• per_device_train_batch_size: 32
• learning_rate: 0.0001
• weight_decay: 0.01
• num_train_epochs: 1
• lr_scheduler_type: cosine
• warmup_ratio: 0.05
• seed: 3407
• bf16: True

All Hyperparameters

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

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: epoch
• prediction_loss_only: True
• per_device_train_batch_size: 32
• 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: 0.0001
• weight_decay: 0.01
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1.0
• num_train_epochs: 1
• max_steps: -1
• lr_scheduler_type: cosine
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.05
• 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: 3407
• data_seed: None
• jit_mode_eval: False
• use_ipex: False
• bf16: True
• 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: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
• fsdp_transformer_layer_cls_to_wrap: None
• accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
• parallelism_config: None
• deepspeed: None
• label_smoothing_factor: 0.0
• optim: adamw_torch_fused
• optim_args: None
• adafactor: False
• group_by_length: False
• length_column_name: length
• 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: False
• 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: False
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

</details>

Training Logs

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

Framework Versions

• Python: 3.12.3
• Sentence Transformers: 5.3.0
• Transformers: 4.56.2
• PyTorch: 2.11.0+cu128
• Accelerate: 1.13.0
• Datasets: 4.3.0
• Tokenizers: 0.22.2

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.* -->