SentenceTransformer based on bkai-foundation-models/vietnamese-bi-encoder

This is a sentence-transformers model finetuned from bkai-foundation-models/vietnamese-bi-encoder. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for retrieval.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: bkai-foundation-models/vietnamese-bi-encoder
Maximum Sequence Length: 256 tokens
Output Dimensionality: 768 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': 'RobertaModel'})
  (1): Pooling({'embedding_dimension': 768, 'pooling_mode': 'mean', '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("kttt294/vietnamese-sbert-finetuned")
# Run inference
sentences = [
    'Nhân_dịp này , thay_mặt UBND thành_phố , ông Lê_Khắc_Nam trao_tặng Bằng khen của Chủ_tịch UBND thành_phố và thưởng 50 triệu đồng cho ban chuyên_án 718M .',
    'Với thành_tích triệt_phá , bắt_giữ các đối_tượng trong đường_dây mua_bán ma_tuý lên tới 20kg , ban chuyên_án đã được UBND TP.',
    'Bộ_phim " Người phán_xử " đã đạt giải Phim_truyền_hình ấn_tượng trong sự hân_hoan của khán_giả yêu_mến bộ_phim .',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.9967, 0.9962],
#         [0.9967, 1.0000, 0.9957],
#         [0.9962, 0.9957, 1.0000]])

Training Details

Training Dataset

Unnamed Dataset

Size: 12,001 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: 4 tokens mean: 26.05 tokens max: 82 tokens	min: 4 tokens mean: 21.69 tokens max: 39 tokens	min: 0.0 mean: 0.92 max: 1.0

Samples:

sentence_0	sentence_1	label
`Anh viết : " Thuỷ_thần đã xuất_hiện tại Carnaval Hạ_Long 2018 " kèm hashtag tiếng Anh với nghĩa " Hãy làm điều bạn thích " .`	`Tối 28/4 , Phạm_Anh_Khoa xuất_hiện trong tiết_mục lúc 21h trên sóng trực_tiếp VTV , trong chương_trình biểu_diễn nghệ_thuật quy_mô lớn Carnival Hạ_Long .`	`1.0`
`Khi đi được gần 2km , Sơn bất_ngờ điều_khiển xe quay trở_lại ngã tư Bưu_điện huyện Hương_Sơn và tiếp_tục lao về hướng tổ công_tác CSGT Công_an huyện Hương_Sơn đang làm nhiệm_vụ tại đây .`	`Khi CSGT ra tín_hiệu yêu_cầu dừng xe , Sơn xuống xin các chiến_sĩ cảnh_sát bỏ_qua nhưng không được chấp_thuận .`	`1.0`
`Báo Đất_Việt đưa tin , lực lượng chức năng tỉnh Khánh Hòa đang tạm giữ Lê_Văn Quý ( 25 tuổi , quê xã Vạn Thạnh , huyện Vạn Ninh ) để điều tra hành vi giết người .`	`Dù được yêu_cầu hát karaoke nhỏ lại nhưng ông H. muốn thoải mái hát hò trong ngày nghỉ lễ nên không làm theo .`	`1.0`

Loss: CosineSimilarityLoss with these parameters:

{
    "loss_fct": "torch.nn.modules.loss.MSELoss",
    "cos_score_transformation": "torch.nn.modules.linear.Identity"
}

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

per_device_train_batch_size: 32
num_train_epochs: 3
max_steps: -1
learning_rate: 5e-05
lr_scheduler_type: linear
lr_scheduler_kwargs: None
warmup_steps: 0
optim: adamw_torch_fused
optim_args: None
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
optim_target_modules: None
gradient_accumulation_steps: 1
average_tokens_across_devices: True
max_grad_norm: 1
label_smoothing_factor: 0.0
bf16: False
fp16: False
bf16_full_eval: False
fp16_full_eval: False
tf32: None
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
use_liger_kernel: False
liger_kernel_config: None
use_cache: False
neftune_noise_alpha: None
torch_empty_cache_steps: None
auto_find_batch_size: False
log_on_each_node: True
logging_nan_inf_filter: True
include_num_input_tokens_seen: no
log_level: passive
log_level_replica: warning
disable_tqdm: False
project: huggingface
trackio_space_id: None
trackio_bucket_id: None
trackio_static_space_id: None
per_device_eval_batch_size: 32
prediction_loss_only: True
eval_on_start: False
eval_do_concat_batches: True
eval_use_gather_object: False
eval_accumulation_steps: None
include_for_metrics: []
batch_eval_metrics: False
save_only_model: False
save_on_each_node: False
enable_jit_checkpoint: False
push_to_hub: False
hub_private_repo: None
hub_model_id: None
hub_strategy: every_save
hub_always_push: False
hub_revision: None
load_best_model_at_end: False
ignore_data_skip: False
restore_callback_states_from_checkpoint: False
full_determinism: False
seed: 42
data_seed: None
use_cpu: False
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
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_pin_memory: True
dataloader_persistent_workers: False
dataloader_prefetch_factor: None
remove_unused_columns: True
label_names: None
train_sampling_strategy: random
length_column_name: length
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
ddp_static_graph: None
ddp_backend: None
ddp_timeout: 1800
fsdp: None
fsdp_config: None
deepspeed: None
debug: []
skip_memory_metrics: True
do_predict: False
resume_from_checkpoint: None
warmup_ratio: None
local_rank: -1
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss
1.3298	500	0.0298
2.6596	1000	0.0035

Training Time

Training: 13.0 minutes

Framework Versions

Python: 3.12.13
Sentence Transformers: 5.6.0
Transformers: 5.13.1
PyTorch: 2.11.0+cu128
Accelerate: 1.14.0
Datasets: 4.0.0
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",
}

Downloads last month: 64

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for kttt294/vietnamese-sbert-finetuned

Base model

bkai-foundation-models/vietnamese-bi-encoder

Finetuned

(63)

this model

Paper for kttt294/vietnamese-sbert-finetuned

Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

Paper • 1908.10084 • Published Aug 27, 2019 • 16