SentenceTransformer based on BAAI/bge-reasoner-embed-qwen3-8b-0923

This is a sentence-transformers model finetuned from BAAI/bge-reasoner-embed-qwen3-8b-0923. It maps sentences & paragraphs to a 4096-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, classification, clustering, and more.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: BAAI/bge-reasoner-embed-qwen3-8b-0923
Maximum Sequence Length: 768 tokens
Output Dimensionality: 4096 dimensions
Similarity Function: Cosine Similarity
Supported Modality: Text

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'Qwen3Model'})
  (1): Pooling({'embedding_dimension': 4096, 'pooling_mode': 'lasttoken', 'include_prompt': True})
)

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 SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("sentence_transformers_model_id")
# Run inference
queries = [
    'This Java class, `TramCommandsAndEventsIntegrationData`, provides dynamically generated, timestamp-suffixed string identifiers for various command and event channels, aggregate destinations, and dispatchers. It serves as integration data, likely for configuring a messaging or event-driven framework (e.g., Tram Sagas) within a microservices architecture, possibly for testing or unique instance identification.',
]
documents = [
    'This code primarily defines a simple `ActionInfo` DTO and, more significantly, provides comprehensive Spring Boot integration tests for an `OrderService`. These tests validate order creation and state transitions within a microservices context, leveraging an embedded H2 database, Eventuate Tram for event-driven communication, and consumer-driven contract testing with stub runners for external service interactions.',
    'This abstract `Specification` class implements the Specification pattern, providing a framework for defining reusable business rules that can be checked against an object. It enables logical composition of specifications (AND, OR, NOT) and includes mechanisms to capture specific error codes and parameters when a rule is not satisfied.',
    'This code defines classes (`SubscriptionPoloniex`, `SubscriptionHuobi`) for establishing and maintaining real-time WebSocket connections to cryptocurrency exchanges like Poloniex and Huobi. It subscribes to specific currency pair order book updates, manages heartbeats, parses incoming market data, and dispatches processed updates to a provided callback function, likely for arbitrage or trading applications.',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 4096] [3, 4096]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[0.3574, 0.4746, 0.7891]], dtype=torch.bfloat16)

Training Details

Training Dataset

Unnamed Dataset

Size: 1,716 training samples
Columns: sentence_0, sentence_1, and label

Approximate statistics based on the first 100 samples:

	sentence_0	sentence_1	label
type	string	string	float
modality	text	text
details	min: 42 tokens mean: 66.1 tokens max: 88 tokens	min: 43 tokens mean: 66.93 tokens max: 100 tokens	min: 0.0 mean: 0.27 max: 1.0

Samples:

sentence_0	sentence_1	label
`This Python code defines an Apache Thrift client (Client class) for a user management service. It implements methods for user registration (with or without a pre-defined ID), login, and retrieving user-related information, utilizing a distinct send_ and recv_ pattern for each remote procedure call.`	`This code defines DTOs for various question answer types and implements the core business logic for creating insurance offers and policies. It showcases a microservice interaction pattern where the CreateOfferHandler orchestrates price calculation via a PricingClient and then persists domain objects like Offer and Policy.`	`1.0`
`This Python code defines a test_repository function that orchestrates the testing of a given repository by first detecting its type (Java or Python). It then dispatches the testing process to a language-specific function (test_java_repository or test_python_repository), returning the test outcome and the detected repository type.`	`This Python code defines a Client class that acts as a client-side interface for user management operations, including user registration (with or without a specified ID), login, and uploading user data by ID or username. It implements these functionalities using a distinct send_ and recv_ method pattern for each operation, characteristic of an Apache Thrift RPC client.`	`0.0`
`This TradeConfig class centralizes all configuration and runtime parameters for the DayTrader sample application, defining operational modes, database settings, and UI types. It also provides a comprehensive suite of static utility methods for generating random trade-related data (users, quotes, prices) and simulating workload scenarios, notably employing a "card deck" algorithm for user selection.`	`This TradeConfig class acts as a central, static configuration store for the DayTrader sample application, defining various runtime parameters such as operational modes (EJB, JDBC), order processing, UI preferences, and database settings. It also provides utility methods for generating random user and market data, crucial for simulating trade scenarios and managing user IDs through a "card deck" approach.`	`0.0`

Loss: ContrastiveLoss with these parameters:

{
    "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
    "margin": 0.5,
    "size_average": true
}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 32
per_device_eval_batch_size: 32
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
prediction_loss_only: True
per_device_train_batch_size: 32
per_device_eval_batch_size: 32
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: 3
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: {'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
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: round_robin
router_mapping: {}
learning_rate_mapping: {}

Training Time

Training: 6.1 minutes

Framework Versions

Python: 3.12.3
Sentence Transformers: 5.7.0
Transformers: 4.57.6
PyTorch: 2.6.0+cu124
Accelerate: 1.15.0
Datasets: 5.0.1
Tokenizers: 0.22.2

Additional Resources

Training and Finetuning Embedding Models with Sentence Transformers: the end-to-end guide for training or finetuning Sentence Transformer models.
Introduction to Matryoshka Embedding Models: variable-size embeddings that can be truncated with minimal quality loss.
Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval: post-training compression of embedding vectors.
Multimodal Embedding & Reranker Models with Sentence Transformers: use text, image, audio, and video models through the same API.
Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers: train multimodal embedding models, with a Visual Document Retrieval walkthrough.

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",
}

ContrastiveLoss

@inproceedings{hadsell2006dimensionality,
    author={Hadsell, R. and Chopra, S. and LeCun, Y.},
    booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
    title={Dimensionality Reduction by Learning an Invariant Mapping},
    year={2006},
    volume={2},
    number={},
    pages={1735-1742},
    doi={10.1109/CVPR.2006.100}
}

Downloads last month: 25

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for hasinthakapiyumal/bge-reasoner-embed-ms-patterns

Base model

BAAI/bge-reasoner-embed-qwen3-8b-0923

Finetuned

(4)

this model

Paper for hasinthakapiyumal/bge-reasoner-embed-ms-patterns

Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

Paper • 1908.10084 • Published Aug 27, 2019 • 18