This is a sentence-transformers model finetuned from Qwen/Qwen3-Embedding-0.6B on the flash_rag_datasets dataset. 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
Training Dataset:
- flash_rag_datasets
Language: en

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': 'PeftModelForFeatureExtraction'})
  (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.

python

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("qwen3-embedding-0.6b_qwen3-8b_nq_lsr")
# Run inference
queries = [
    "when did captain crunch oops all berries come out",
]
documents = [
    'First released in 1997',
    'Shel Silverstein',
    'Notre Dame',
]
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([[0.2762, 0.2308, 0.1852]])

Training Details

Training Dataset

flash_rag_datasets

Dataset: flash_rag_datasets at bcafb8d
Size: 79,168 training samples
Columns: query and response
Approximate statistics based on the first 1000 samples:
query response
type string string
details
min: 9 tokens
mean: 11.35 tokens
max: 25 tokens
min: 2 tokens
mean: 5.31 tokens
max: 16 tokens
Samples:
query response
total number of death row inmates in the us 2,718
big little lies season 2 how many episodes seven
who sang waiting for a girl like you Foreigner
Loss: fed_rag.loss.pytorch.lsr.LSRLoss

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 1
gradient_accumulation_steps: 16
learning_rate: 1e-05
max_steps: 100
lr_scheduler_type: constant
remove_unused_columns: False
dataloader_pin_memory: False
push_to_hub: True

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: no
prediction_loss_only: True
per_device_train_batch_size: 1
per_device_eval_batch_size: 8
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 16
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 1e-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: 3.0
max_steps: 100
lr_scheduler_type: constant
lr_scheduler_kwargs: {}
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: False
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
project: huggingface
trackio_space_id: trackio
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
dataloader_pin_memory: False
dataloader_persistent_workers: False
skip_memory_metrics: True
use_legacy_prediction_loop: False
push_to_hub: True
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: proportional
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss
0.0002	1	0.0003
0.0004	2	0.0004
0.0006	3	0.0005
0.0008	4	0.0002
0.0010	5	0.0001
0.0012	6	0.0003
0.0014	7	0.0002
0.0016	8	0.0004
0.0018	9	0.0006
0.0020	10	0.0002
0.0022	11	0.0003
0.0024	12	0.0002
0.0026	13	0.0005
0.0028	14	0.0004
0.0030	15	0.0004
0.0032	16	0.0005
0.0034	17	0.0003
0.0036	18	0.0004
0.0038	19	0.0004
0.0040	20	0.0006
0.0042	21	0.0003
0.0044	22	0.0002
0.0046	23	0.0004
0.0049	24	0.0003
0.0051	25	0.0003
0.0053	26	0.0003
0.0055	27	0.0004
0.0057	28	0.0003
0.0059	29	0.0003
0.0061	30	0.0004
0.0063	31	0.0002
0.0065	32	0.0003
0.0067	33	0.0003
0.0069	34	0.0007
0.0071	35	0.0003
0.0073	36	0.0002
0.0075	37	0.0003
0.0077	38	0.0003
0.0079	39	0.0007
0.0081	40	0.0003
0.0083	41	0.0004
0.0085	42	0.0003
0.0087	43	0.0002
0.0089	44	0.0003
0.0091	45	0.0002
0.0093	46	0.0002
0.0095	47	0.0003
0.0097	48	0.0004
0.0099	49	0.0003
0.0101	50	0.0002
0.0103	51	0.0005
0.0105	52	0.0002
0.0107	53	0.0004
0.0109	54	0.0003
0.0111	55	0.0003
0.0113	56	0.0004
0.0115	57	0.0009
0.0117	58	0.0003
0.0119	59	0.0003
0.0121	60	0.0007
0.0123	61	0.0005
0.0125	62	0.0004
0.0127	63	0.0003
0.0129	64	0.0003
0.0131	65	0.0004
0.0133	66	0.0005
0.0135	67	0.0002
0.0137	68	0.0003
0.0139	69	0.0004
0.0141	70	0.0002
0.0143	71	0.0005
0.0146	72	0.0002
0.0148	73	0.0003
0.0150	74	0.0002
0.0152	75	0.0004
0.0154	76	0.0003
0.0156	77	0.0002
0.0158	78	0.0003
0.0160	79	0.0003
0.0162	80	0.0002
0.0164	81	0.0003
0.0166	82	0.0003
0.0168	83	0.0002
0.0170	84	0.0003
0.0172	85	0.0004
0.0174	86	0.0004
0.0176	87	0.0001
0.0178	88	0.0003
0.0180	89	0.0005
0.0182	90	0.0003
0.0184	91	0.0004
0.0186	92	0.0002
0.0188	93	0.0002
0.0190	94	0.0003
0.0192	95	0.0002
0.0194	96	0.0003
0.0196	97	0.0005
0.0198	98	0.0003
0.0200	99	0.0003
0.0202	100	0.0004

Framework Versions

Python: 3.11.14
Sentence Transformers: 5.2.0
Transformers: 4.57.2
PyTorch: 2.9.1+cu128
Accelerate: 1.12.0
Datasets: 4.5.0
Tokenizers: 0.22.2

Citation

BibTeX

Sentence Transformers

bibtex

@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",
}

	query	response
type	string	string
details	min: 9 tokens mean: 11.35 tokens max: 25 tokens	min: 2 tokens mean: 5.31 tokens max: 16 tokens

query	response
`total number of death row inmates in the us`	`2,718`
`big little lies season 2 how many episodes`	`seven`
`who sang waiting for a girl like you`	`Foreigner`

zyc-zju/qwen3-embedding-0.6b_qwen3-8b_nq_lsr

SentenceTransformer based on Qwen/Qwen3-Embedding-0.6B