SentenceTransformer based on unsloth/Qwen3-Embedding-0.6B

This is a sentence-transformers model finetuned from unsloth/Qwen3-Embedding-0.6B. It maps inputs to a 1024-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: unsloth/Qwen3-Embedding-0.6B
Maximum Sequence Length: 512 tokens
Output Dimensionality: 1024 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': 1024, 'pooling_mode': 'lasttoken', 'include_prompt': True})
  (2): Normalize({'module_input_name': 'sentence_embedding', 'module_output_name': 'sentence_embedding'})
)

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("jersobh/epochdb-embed-0.6b")
# Run inference
queries = [
    'Instruct: Retrieve current active agent memory state and entity facts.\nQuery: Но он не знает их так, как я, девчонка дрожала.',
]
documents = [
    'Но он не знаком с ними, девчонка дрожала.',
    'Он знает их так же, как и я, они безобидны, девушка улыбнулась.',
    'Actually, Lukas now works at rpc and relocated to Lisboa.',
]
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([[0.7700, 0.6676, 0.1506]])

Training Details

Training Dataset

Unnamed Dataset

Size: 6,492 training samples
Columns: anchor, positive, and negative

Approximate statistics based on the first 100 samples:

	anchor	positive	negative
type	string	string	string
modality	text	text	text
details	min: 24 tokens mean: 29.48 tokens max: 118 tokens	min: 9 tokens mean: 16.55 tokens max: 20 tokens	min: 13 tokens mean: 17.28 tokens max: 41 tokens

Samples:

anchor	positive	negative
`Instruct: Retrieve current active agent memory state and entity facts. Query: Where does Claire currently work and live?`	`Actually, Claire now works at BMW Group and relocated to Odivelas.`	`Claire previously worked at VectorAI and used to live in São Paulo.`
`Instruct: Retrieve current active agent memory state and entity facts. Query: Where does Jefferson currently work and live?`	`Actually, Jefferson now works at rpc and relocated to Bologna.`	`Jefferson previously worked at BMW Group and used to live in São Paulo.`
`Instruct: Retrieve current active agent memory state and entity facts. Query: Where does Sofia currently work and live?`	`Actually, Sofia now works at VectorAI and relocated to São Paulo.`	`Sofia previously worked at BMW Group and used to live in Odivelas.`

Loss: MatryoshkaLoss with these parameters:

{
    "loss": "MultipleNegativesRankingLoss",
    "matryoshka_dims": [
        1024,
        512,
        384,
        256
    ],
    "matryoshka_weights": [
        1,
        1,
        1,
        1
    ],
    "n_dims_per_step": -1
}

Training Hyperparameters

Non-Default Hyperparameters

num_train_epochs: 1
learning_rate: 2e-05
warmup_steps: 0.1
optim: adamw_bnb_8bit
gradient_accumulation_steps: 8
bf16: True
gradient_checkpointing: True

All Hyperparameters

Click to expand

per_device_train_batch_size: 8
num_train_epochs: 1
max_steps: -1
learning_rate: 2e-05
lr_scheduler_type: linear
lr_scheduler_kwargs: None
warmup_steps: 0.1
optim: adamw_bnb_8bit
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: 8
average_tokens_across_devices: True
max_grad_norm: 1.0
label_smoothing_factor: 0.0
bf16: True
fp16: False
bf16_full_eval: False
fp16_full_eval: False
tf32: None
gradient_checkpointing: True
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: 8
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
dataloader_multiprocessing_context: None
dataloader_in_order: True
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
local_rank: -1
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}
warmup_ratio: None

Training Logs

Epoch	Step	Training Loss
0.2463	25	2.3655
0.4926	50	1.6021
0.7389	75	1.5353
0.9852	100	1.4491

Training Time

Training: 6.3 minutes

Framework Versions

Python: 3.13.16
Sentence Transformers: 6.2.0
Transformers: 5.17.0
PyTorch: 2.11.0+cu130
Accelerate: 1.15.0
Datasets: 4.8.5
Tokenizers: 0.23.3

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",
}

MatryoshkaLoss

@misc{kusupati2024matryoshka,
    title={Matryoshka Representation Learning},
    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
    year={2024},
    eprint={2205.13147},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

MultipleNegativesRankingLoss

@misc{oord2019representationlearningcontrastivepredictive,
      title={Representation Learning with Contrastive Predictive Coding},
      author={Aaron van den Oord and Yazhe Li and Oriol Vinyals},
      year={2019},
      eprint={1807.03748},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/1807.03748},
}

Downloads last month: -

Safetensors

Model size

0.6B params

Tensor type

BF16

Model tree for jersobh/epochdb-embed-0.6b

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

unsloth/Qwen3-Embedding-0.6B

Quantized

(3)

this model

Papers for jersobh/epochdb-embed-0.6b