Reranker MiniLM L6 H384 Uncased Gooaq 5 Epoch 1995000
This is a cross-encoder model fine-tuned from nreimers/MiniLM-L6-H384-uncased, designed for computing scores of text pairs, suitable for text re-ranking and semantic search tasks.
Downloads 24
Release Time : 3/31/2025
Model Overview
This model is a cross-encoder specifically designed to compute similarity scores for text pairs, applicable in tasks such as information retrieval and question-answering systems for text re-ranking.
Model Features
Efficient Text Re-ranking
Accurately computes similarity scores for text pairs, effectively improving the ranking quality of retrieval systems.
Based on MiniLM Architecture
Utilizes the lightweight MiniLM architecture, enhancing inference efficiency while maintaining performance.
Multi-dataset Validation
Validated on multiple datasets (gooaq, NanoMSMARCO, etc.), demonstrating stable performance.
Model Capabilities
Text Similarity Calculation
Semantic Search
Question-Answering System Re-ranking
Information Retrieval Optimization
Use Cases
Information Retrieval
Search Engine Result Re-ranking
Re-ranks search engine results to improve the ranking of the most relevant results.
Achieved an NDCG@10 of 0.5149 on the gooaq development set.
Question-Answering Systems
Candidate Answer Ranking
Ranks multiple candidate answers generated by a question-answering system based on relevance.
Achieved an NDCG@10 of 0.4065 on the NanoNQ dataset.
đ CrossEncoder based on nreimers/MiniLM-L6-H384-uncased
This is a Cross Encoder model designed to compute scores for text pairs. These scores can be utilized for text reranking and semantic search. It's finetuned from nreimers/MiniLM-L6-H384-uncased using the sentence-transformers library.
đ Quick Start
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 đ¤ Hub
model = CrossEncoder("ayushexel/reranker-MiniLM-L6-H384-uncased-gooaq-5-epoch-1995000")
# Get scores for pairs of texts
pairs = [
['when is the 2020 democratic presidential debate?', 'Major candidates The nomination will be made official at the 2020 Democratic National Convention, tentatively scheduled for August 17â20, 2020 in Milwaukee, Wisconsin.'],
['when is the 2020 democratic presidential debate?', 'Major candidates As of June 8, 2020, former Vice President Joe Biden became the presumptive presidential nominee by amassing enough delegates to secure the nomination.'],
['when is the 2020 democratic presidential debate?', 'On March 5, 2019, Bloomberg announced that he would not run for president in 2020; instead he encouraged the Democratic Party to "nominate a Democrat who will be in the strongest position to defeat Donald Trump".'],
['when is the 2020 democratic presidential debate?', 'The electoral map for the 2020 election, based on populations from the 2010 Census. The 2020 United States presidential election is scheduled for Tuesday, November 3, 2020. It will be the 59th quadrennial presidential election.'],
['when is the 2020 democratic presidential debate?', 'There were a total of 29 major Democratic candidates. Of these, 23 candidates participated in at least one debate. Only Joe Biden and Bernie Sanders participated in all the debates; Pete Buttigieg, Amy Klobuchar, and Elizabeth Warren participated in all but one debate.'],
]
scores = model.predict(pairs)
print(scores.shape)
# (5,)
# Or rank different texts based on similarity to a single text
ranks = model.rank(
'when is the 2020 democratic presidential debate?',
[
'Major candidates The nomination will be made official at the 2020 Democratic National Convention, tentatively scheduled for August 17â20, 2020 in Milwaukee, Wisconsin.',
'Major candidates As of June 8, 2020, former Vice President Joe Biden became the presumptive presidential nominee by amassing enough delegates to secure the nomination.',
'On March 5, 2019, Bloomberg announced that he would not run for president in 2020; instead he encouraged the Democratic Party to "nominate a Democrat who will be in the strongest position to defeat Donald Trump".',
'The electoral map for the 2020 election, based on populations from the 2010 Census. The 2020 United States presidential election is scheduled for Tuesday, November 3, 2020. It will be the 59th quadrennial presidential election.',
'There were a total of 29 major Democratic candidates. Of these, 23 candidates participated in at least one debate. Only Joe Biden and Bernie Sanders participated in all the debates; Pete Buttigieg, Amy Klobuchar, and Elizabeth Warren participated in all but one debate.',
]
)
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]
⨠Features
- Text Reranking: Computes scores for pairs of texts, enabling effective text reranking.
- Semantic Search: Can be used for semantic search tasks, leveraging the computed text scores.
đ Documentation
Model Details
Model Description
Property | Details |
---|---|
Model Type | Cross Encoder |
Base model | nreimers/MiniLM-L6-H384-uncased |
Maximum Sequence Length | 512 tokens |
Number of Output Labels | 1 label |
Language | en |
License | apache-2.0 |
Model Sources
- Documentation: Sentence Transformers Documentation
- Documentation: Cross Encoder Documentation
- Repository: Sentence Transformers on GitHub
- Hugging Face: Cross Encoders on Hugging Face
Evaluation
Metrics
Cross Encoder Reranking (gooaq-dev
)
Evaluated with CrossEncoderRerankingEvaluator
with these parameters:
{
"at_k": 10,
"always_rerank_positives": false
}
Metric | Value |
---|---|
map | 0.4719 (+0.2021) |
mrr@10 | 0.4714 (+0.2125) |
ndcg@10 | 0.5149 (+0.2052) |
Cross Encoder Reranking (NanoMSMARCO_R100
, NanoNFCorpus_R100
, NanoNQ_R100
)
Evaluated with CrossEncoderRerankingEvaluator
with these parameters:
{
"at_k": 10,
"always_rerank_positives": true
}
Metric | NanoMSMARCO_R100 | NanoNFCorpus_R100 | NanoNQ_R100 |
---|---|---|---|
map | 0.3405 (-0.1491) | 0.3375 (+0.0765) | 0.3251 (-0.0945) |
mrr@10 | 0.3251 (-0.1524) | 0.5157 (+0.0159) | 0.3406 (-0.0861) |
ndcg@10 | 0.4090 (-0.1314) | 0.3596 (+0.0346) | 0.4065 (-0.0942) |
Cross Encoder Nano BEIR (NanoBEIR_R100_mean
)
Evaluated with CrossEncoderNanoBEIREvaluator
with these parameters:
{
"dataset_names": [
"msmarco",
"nfcorpus",
"nq"
],
"rerank_k": 100,
"at_k": 10,
"always_rerank_positives": true
}
Metric | Value |
---|---|
map | 0.3344 (-0.0557) |
mrr@10 | 0.3938 (-0.0742) |
ndcg@10 | 0.3917 (-0.0637) |
Training Details
Training Dataset
Unnamed Dataset
- Size: 11,456,701 training samples
- Columns:
question
,answer
, andlabel
- Approximate statistics based on the first 1000 samples:
| | question | answer | label |
|----|------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------|------------------------------------------------|
| type | string | string | int |
| details |
- min: 18 characters
- mean: 43.15 characters
- max: 83 characters
- min: 59 characters
- mean: 257.34 characters
- max: 388 characters
- 0: ~82.40%
- 1: ~17.60%
- Samples:
| question | answer | label |
|-------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------|
|
when is the 2020 democratic presidential debate?
|Major candidates The nomination will be made official at the 2020 Democratic National Convention, tentatively scheduled for August 17â20, 2020 in Milwaukee, Wisconsin.
|1
| |when is the 2020 democratic presidential debate?
|Major candidates As of June 8, 2020, former Vice President Joe Biden became the presumptive presidential nominee by amassing enough delegates to secure the nomination.
|0
| |when is the 2020 democratic presidential debate?
|On March 5, 2019, Bloomberg announced that he would not run for president in 2020; instead he encouraged the Democratic Party to "nominate a Democrat who will be in the strongest position to defeat Donald Trump".
|0
| - Loss:
BinaryCrossEntropyLoss
with these parameters:
{
"activation_fn": "torch.nn.modules.linear.Identity",
"pos_weight": 5
}
Training Hyperparameters
Non-Default Hyperparameters
eval_strategy
: stepsper_device_train_batch_size
: 256per_device_eval_batch_size
: 256learning_rate
: 2e-05num_train_epochs
: 5warmup_ratio
: 0.1seed
: 12bf16
: Truedataloader_num_workers
: 12load_best_model_at_end
: True
All Hyperparameters
Click to expand
overwrite_output_dir
: Falsedo_predict
: Falseeval_strategy
: stepsprediction_loss_only
: Trueper_device_train_batch_size
: 256per_device_eval_batch_size
: 256per_gpu_train_batch_size
: Noneper_gpu_eval_batch_size
: Nonegradient_accumulation_steps
: 1eval_accumulation_steps
: Nonetorch_empty_cache_steps
: Nonelearning_rate
: 2e-05weight_decay
: 0.0adam_beta1
: 0.9adam_beta2
: 0.999adam_epsilon
: 1e-08max_grad_norm
: 1.0num_train_epochs
: 5max_steps
: -1lr_scheduler_type
: linearlr_scheduler_kwargs
: {}warmup_ratio
: 0.1warmup_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
: 12data_seed
: Nonejit_mode_eval
: Falseuse_ipex
: Falsebf16
: Truefp16
: Falsefp16_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
: 12dataloader_prefetch_factor
: Nonepast_index
: -1disable_tqdm
: Falseremove_unused_columns
: Truelabel_names
: Noneload_best_model_at_end
: Trueignore_data_skip
: Falsefsdp
: []fsdp_min_num_params
: 0fsdp_config
: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}tp_size
: 0fsdp_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
: Falsegradient_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
: Nonedispatch_batches
: Nonesplit_batches
: Noneinclude_tokens_per_second
: Falseinclude_num_input_tokens_seen
: Falseneftune_noise_alpha
: Noneoptim_target_modules
: Nonebatch_eval_metrics
: Falseeval_on_start
: Falseuse_liger_kernel
: Falseeval_use_gather_object
: Falseaverage_tokens_across_devices
: Falseprompts
: Nonebatch_sampler
: batch_samplermulti_dataset_batch_sampler
: proportional
Training Logs
Click to expand
Epoch | Step | Training Loss | gooaq-dev_ndcg@10 | NanoMSMARCO_R100_ndcg@10 | NanoNFCorpus_R100_ndcg@10 | NanoNQ_R100_ndcg@10 | NanoBEIR_R100_mean_ndcg@10 |
---|---|---|---|---|---|---|---|
-1 | -1 | - | 0.1023 (-0.2073) | 0.0063 (-0.5341) | 0.2762 (-0.0489) | 0.0240 (-0.4766) | 0.1022 (-0.3532) |
0.0000 | 1 | 1.1577 | - | - | - | - | - |
0.0045 | 200 | 1.1721 | - | - | - | - | - |
0.0089 | 400 | 1.1758 | - | - | - | - | - |
0.0134 | 600 | 1.1755 | - | - | - | - | - |
0.0179 | 800 | 1.1809 | - | - | - | - | - |
0.0223 | 1000 | 1.1717 | - | - | - | - | - |
0.0268 | 1200 | 1.1723 | - | - | - | - | - |
0.0313 | 1400 | 1.1687 | - | - | - | - | - |
0.0358 | 1600 | 1.1727 | - | - | - | - | - |
0.0402 | 1800 | 1.177 | - | - | - | - | - |
0.0447 | 2000 | 1.1792 | - | - | - | - | - |
0.0492 | 2200 | 1.172 | - | - | - | - | - |
0.0536 | 2400 | 1.1117 | - | - | - | - | - |
0.0581 | 2600 | 1.0198 | - | - | - | - | - |
0.0626 | 2800 | 0.9849 | - | - | - | - | - |
0.0670 | 3000 | 0.9572 | - | - | - | - | - |
0.0715 | 3200 | 0.9359 | - | - | - | - | - |
0.0760 | 3400 | 0.9216 | - | - | - | - | - |
0.0804 | 3600 | 0.9244 | - | - | - | - | - |
0.0849 | 3800 | 0.914 | - | - | - | - | - |
đ License
This model is licensed under the apache-2.0 license.
Jina Embeddings V3
Jina Embeddings V3 is a multilingual sentence embedding model supporting over 100 languages, specializing in sentence similarity and feature extraction tasks.
Text Embedding
Transformers Supports Multiple Languages

J
jinaai
3.7M
911
Ms Marco MiniLM L6 V2
Apache-2.0
A cross-encoder model trained on the MS Marco passage ranking task for query-passage relevance scoring in information retrieval
Text Embedding English
M
cross-encoder
2.5M
86
Opensearch Neural Sparse Encoding Doc V2 Distill
Apache-2.0
A sparse retrieval model based on distillation technology, optimized for OpenSearch, supporting inference-free document encoding with improved search relevance and efficiency over V1
Text Embedding
Transformers English

O
opensearch-project
1.8M
7
Sapbert From PubMedBERT Fulltext
Apache-2.0
A biomedical entity representation model based on PubMedBERT, optimized for semantic relation capture through self-aligned pre-training
Text Embedding English
S
cambridgeltl
1.7M
49
Gte Large
MIT
GTE-Large is a powerful sentence transformer model focused on sentence similarity and text embedding tasks, excelling in multiple benchmark tests.
Text Embedding English
G
thenlper
1.5M
278
Gte Base En V1.5
Apache-2.0
GTE-base-en-v1.5 is an English sentence transformer model focused on sentence similarity tasks, excelling in multiple text embedding benchmarks.
Text Embedding
Transformers Supports Multiple Languages

G
Alibaba-NLP
1.5M
63
Gte Multilingual Base
Apache-2.0
GTE Multilingual Base is a multilingual sentence embedding model supporting over 50 languages, suitable for tasks like sentence similarity calculation.
Text Embedding
Transformers Supports Multiple Languages

G
Alibaba-NLP
1.2M
246
Polybert
polyBERT is a chemical language model designed to achieve fully machine-driven ultrafast polymer informatics. It maps PSMILES strings into 600-dimensional dense fingerprints to numerically represent polymer chemical structures.
Text Embedding
Transformers

P
kuelumbus
1.0M
5
Bert Base Turkish Cased Mean Nli Stsb Tr
Apache-2.0
A sentence embedding model based on Turkish BERT, optimized for semantic similarity tasks
Text Embedding
Transformers Other

B
emrecan
1.0M
40
GIST Small Embedding V0
MIT
A text embedding model fine-tuned based on BAAI/bge-small-en-v1.5, trained with the MEDI dataset and MTEB classification task datasets, optimized for query encoding in retrieval tasks.
Text Embedding
Safetensors English
G
avsolatorio
945.68k
29
Featured Recommended AI Models
Š 2025AIbase