SentenceTransformer based on Qwen/Qwen3-Embedding-0.6B

This is a sentence-transformers model finetuned from Qwen/Qwen3-Embedding-0.6B. 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.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: Qwen/Qwen3-Embedding-0.6B
Maximum Sequence Length: 32768 tokens
Output Dimensionality: 1024 dimensions
Similarity Function: Cosine Similarity

Model Sources

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

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 32768, 'do_lower_case': False, 'architecture': 'Qwen3Model'})
  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, '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': True, 'include_prompt': True})
  (2): Normalize()
)

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("kevinadityai/qwen3-ai-faq-embeddings")
# Run inference
queries = [
    "Apa itu SHTB?",
]
documents = [
    'Siloam Hospitals TB Simatupang adalah kepanjangan dari SHTB',
    'Nama lain Siloam Rawalumbu adalah Siloam Hospitals Bekasi Sepanjang Jaya atau SHBS',
    'Hasil MCU / Medical Check Up akan tersedia dalam waktu 1 hari setelah seluruh rangkaian pemeriksaan selesai, kecuali pemeriksaan tertentu yang memerlukan waktu pengerjaan yang lebih lama (contoh: papsmear, biopsi, kultur, dsb).',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 1024] [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[0.7575, 0.1560, 0.0555]])

Evaluation

Metrics

Triplet

Datasets: ai-faq-validation and ai-faq-test
Evaluated with TripletEvaluator

Metric	ai-faq-validation	ai-faq-test
cosine_accuracy	0.9667	1.0

Training Details

Training Dataset

Unnamed Dataset

Size: 243 training samples
Columns: query, answer_positive, and answer_negative

Approximate statistics based on the first 243 samples:

	query	answer_positive	answer_negative
type	string	string	string
details	min: 3 tokens mean: 13.65 tokens max: 54 tokens	min: 14 tokens mean: 41.42 tokens max: 353 tokens	min: 10 tokens mean: 42.43 tokens max: 533 tokens

Samples:

query	answer_positive	answer_negative
`Apa nama lain Siloam Kuta?`	`Nama lain Siloam Kuta adalah Siloam Hospitals Denpasar atau SHDP`	`Saat ini memang hanya ada produk tertentu di website. Untuk mengetahui apakah produk yang Anda cari ada di rumah sakit tertentu, Anda dapat langsung menghubungi contact center 1-500-911.`
`Rumah sakit Siloam Hospitals Banjarmasin punya nama lain apa?`	`Nama lain Siloam Hospitals Banjarmasin adalah SHBJ atau Siloam Banjarmasin Tengah`	`Anda dapat melakukan cancel appointment dan melakukan booking ulang di tanggal yang diinginkan, atau dapat menghubungi/mendatangi Rumah Sakit yang ingin dituju.`
`Apa itu MRCCC?`	`MRCCC Siloam Hospitals Semanggi adalah kepanjangan dari MRCCC`	`Lokasinya di Jl. Sultan Hasanuddin No.58, Batulo, Kec. Wolio, Kota Bau-Bau, Sulawesi Tenggara 93716`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim",
    "gather_across_devices": false
}

Evaluation Dataset

Unnamed Dataset

Size: 30 evaluation samples
Columns: query, answer_positive, and answer_negative

Approximate statistics based on the first 30 samples:

	query	answer_positive	answer_negative
type	string	string	string
details	min: 7 tokens mean: 13.07 tokens max: 21 tokens	min: 10 tokens mean: 59.33 tokens max: 533 tokens	min: 15 tokens mean: 41.9 tokens max: 105 tokens

Samples:

query	answer_positive	answer_negative
`Apa itu fitur Self-Check In?`	`Fitur untuk memudahkan pasien melakukan check-in hanya dengan menggunakan aplikasi MySiloam. FItur ini dapat digunakan jika sudah ditanggal booking yang sudah dibuat sebelumnya oleh pasien.`	`Lokasinya di Jl. MT Haryono No.23, Damai, Kecamatan Balikpapan Selatan, Kota Balikpapan, Kalimantan Timur 76114`
`Alamat Siloam Hospitals Purwakarta dimana?`	`Lokasinya di Jl. Raya Bungursari No.1, Cibening, Kec. Bungursari, Kabupaten Purwakarta, Jawa Barat 41181`	`Siloam Hospitals Denpasar adalah kepanjangan dari SHDP`
`Alamat Siloam Hospitals Lubuk Linggau dimana?`	`Lokasinya di Jl. Yos Sudarso No.RT.11, Taba Jemekeh, Kec. Lubuk Linggau Tim. I, Kota Lubuklinggau, Sumatera Selatan 31613`	`Siloam Hospitals Kelapa Dua adalah kepanjangan dari SHKD`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim",
    "gather_across_devices": false
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
learning_rate: 2e-05
num_train_epochs: 1
warmup_ratio: 0.1
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 8
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: 2e-05
weight_decay: 0.0
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: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.1
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
use_ipex: 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_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: no_duplicates
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	ai-faq-validation_cosine_accuracy	ai-faq-test_cosine_accuracy
-1	-1	0.9667	1.0

Framework Versions

Python: 3.12.10
Sentence Transformers: 5.1.1
Transformers: 4.56.2
PyTorch: 2.8.0+cpu
Accelerate: 1.10.1
Datasets: 4.1.1
Tokenizers: 0.22.1

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",
}

MultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply},
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}

Downloads last month: 3

Safetensors

Model size

0.6B params

Tensor type

F32

Model tree for kevinadityai/qwen3-ai-faq-embeddings

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

Qwen/Qwen3-Embedding-0.6B

Finetuned

(79)

this model

Evaluation results

Cosine Accuracy on ai faq validation
self-reported

0.967
Cosine Accuracy on ai faq test
self-reported

1.000

View on Papers With Code