Not-For-All-Audiences

Qwen3-VL-Embedding-2B-NSFW / README.md

Hyphonical

Upload folder using huggingface_hub

7648777 verified 26 days ago

preview code

Raw

History Blame Contribute Delete

28 kB

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:42977
  - loss:MatryoshkaLoss
  - loss:CachedMultipleNegativesRankingLoss
base_model: Qwen/Qwen3-VL-Embedding-2B
widget:
  - source_sentence: >-
      A muscular, nude man with big, veiny cock and large pecs flexes his biceps
      and traps while his bara chest, complete with visible male nipples and
      pubic hair, rises and falls with a hard erection.
    sentences:
      - ./Images/12604035.jpg
      - ./Images/11882380.jpg
      - ./Images/12535412.jpg
      - ./Images/12450474.jpg
      - ./Images/12604909.jpg
  - source_sentence: >-
      Kafka from Honkai: Star Rail rides her thick dickgirl cock like a cowgirl,
      grinding against her futanari girlfriend Wanila, friends with benefits
      exchanging sweaty smiles as their coworker bodies move in perfect rhythm.
    sentences:
      - ./Images/11902307.jpg
      - ./Images/12562944.jpg
      - ./Images/10856318.jpg
      - ./Images/12110183.jpg
      - ./Images/12323048.jpg
  - source_sentence: >-
      Camilla from Fire Emblem lies completely nude as a hand squeezes her huge
      breasts together, her long wavy hair and purple eyes framed by a hair
      ornament while her tongue pouts from an open mouth, taking a thick penis
      in her mouth and swallowing his cum on her tongue and breasts.
    sentences:
      - ./Images/12281117.jpg
      - ./Images/12315235.jpg
      - ./Images/12297876.jpg
      - ./Images/12516461.jpg
      - ./Images/13030938.jpg
  - source_sentence: >-
      Shuten Douji from Fate stands in a rear view pose, her light-skinned body
      adorned with oni horns, accentuating her big, fleshy ass as it fills the
      high-heeled boots detail.
    sentences:
      - ./Images/12368295.jpg
      - ./Images/12454623.jpg
      - ./Images/11608710.jpg
      - ./Images/12431272.jpg
      - ./Images/12912872.jpg
  - source_sentence: >-
      A young futanari with long black hair and blue eyes stands outdoors in a
      bedroom, her big breasts bouncing as she masturbates her large penis and
      full package, throwing her head back in an ahegao expression while cum
      spurts from her erection and pussy.
    sentences:
      - ./Images/12428280.jpg
      - ./Images/12565353.jpg
      - ./Images/12438214.jpg
      - ./Images/11823231.jpg
      - ./Images/12013212.jpg
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - cosine_accuracy@1
  - cosine_accuracy@3
  - cosine_accuracy@5
  - cosine_accuracy@10
  - cosine_precision@1
  - cosine_precision@3
  - cosine_precision@5
  - cosine_precision@10
  - cosine_recall@1
  - cosine_recall@3
  - cosine_recall@5
  - cosine_recall@10
  - cosine_ndcg@10
  - cosine_mrr@10
  - cosine_map@100
model-index:
  - name: SentenceTransformer based on Qwen/Qwen3-VL-Embedding-2B
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: nsfw ir eval
          type: nsfw-ir-eval
        metrics:
          - type: cosine_accuracy@1
            value: 0.18634840871021777
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.3174204355108878
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.37018425460636517
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.4382328308207705
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.18634840871021777
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.10580681183696257
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.07403685092127303
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.04382328308207705
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.18634840871021777
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.3174204355108878
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.37018425460636517
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.4382328308207705
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.3065599946661936
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.2651106059397514
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.27459570794346067
            name: Cosine Map@100

SentenceTransformer based on Qwen/Qwen3-VL-Embedding-2B

This is a sentence-transformers model finetuned from Qwen/Qwen3-VL-Embedding-2B on the json dataset. It maps sentences & paragraphs to a 2048-dimensional dense vector space and can be used for retrieval.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: Qwen/Qwen3-VL-Embedding-2B
Maximum Sequence Length: 262144 tokens
Output Dimensionality: 2048 dimensions
Similarity Function: Cosine Similarity
Supported Modalities: Text, Image, Video, Message
Training Dataset:
- json

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'}, 'image': {'method': 'forward', 'method_output_name': 'last_hidden_state'}, 'video': {'method': 'forward', 'method_output_name': 'last_hidden_state'}, 'message': {'method': 'forward', 'method_output_name': 'last_hidden_state', 'format': 'structured'}}, 'module_output_name': 'token_embeddings', 'processing_kwargs': {'chat_template': {'add_generation_prompt': True}}, 'unpad_inputs': False, 'architecture': 'Qwen3VLModel'})
  (1): Pooling({'embedding_dimension': 2048, 'pooling_mode': 'lasttoken', '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("sentence_transformers_model_id")
# Run inference
queries = [
    'May sits with her legs spread, her massive breasts barely contained by her bikini as she grips her huge cock and thick, long penis, precum leaking out while she looks over her shoulder with a smile.',
]
documents = [
    './Images/11897115.jpg',
    './Images/12313417.jpg',
    './Images/12110929.jpg',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 2048] [3, 2048]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[ 0.3335,  0.1907, -0.0211]])

Evaluation

Metrics

Information Retrieval

Dataset: nsfw-ir-eval
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.1863
cosine_accuracy@3	0.3174
cosine_accuracy@5	0.3702
cosine_accuracy@10	0.4382
cosine_precision@1	0.1863
cosine_precision@3	0.1058
cosine_precision@5	0.074
cosine_precision@10	0.0438
cosine_recall@1	0.1863
cosine_recall@3	0.3174
cosine_recall@5	0.3702
cosine_recall@10	0.4382
cosine_ndcg@10	0.3066
cosine_mrr@10	0.2651
cosine_map@100	0.2746

Training Details

Training Dataset

json

Dataset: json
Size: 42,977 training samples
Columns: query, positive, negative0, negative1, negative2, and negative3

Approximate statistics based on the first 100 samples:

	query	positive	negative0	negative1	negative2	negative3
type	string	string	string	string	string	string
modality	text	image	image	image	image	image
details	min: 46 tokens mean: 74.73 tokens max: 108 tokens

Samples:

query	positive	negative0	negative1	negative2	negative3
`Jane Doe kneels with her skirt hiked, her large breasts jiggling as she deepthroats a thick penis while licking the shaft, her curvaceous body pressed against the viewer’s face and her smooth thighs spread wide to show her dripping pussy and the thick tail pressed against her ass.`	`./Images/12354799.jpg`	`./Images/12371705.jpg`	`./Images/11812526.jpg`	`./Images/11742962.jpg`	`./Images/11978446.jpg`
`Isabelle from Animal Crossing stands with her tied blonde hair and green bikini top and bottom, her big breasts spilling through the cleavage as green hearts hover around her head and her thick thighs and yellow fur draw a female-only, animal-eyed focus.`	`./Images/11651564.jpg`	`./Images/13035434.jpg`	`./Images/13000601.jpg`	`./Images/11979417.jpg`	`./Images/11790567.jpg`
`Ambrosius Goldenloin fucks the hairy, piercing-adorned Nimona with a thick, juicy cock as she moans and clenches around his balls.`	`./Images/10880184.jpg`	`./Images/11855995.jpg`	`./Images/12893082.jpg`	`./Images/11948541.jpg`	`./Images/12449120.jpg`

Loss: MatryoshkaLoss with these parameters:

{
    "loss": "CachedMultipleNegativesRankingLoss",
    "matryoshka_dims": [
        2048,
        1536,
        1024,
        512,
        256,
        128,
        64
    ],
    "matryoshka_weights": [
        1,
        1,
        1,
        1,
        1,
        1,
        1
    ],
    "n_dims_per_step": -1
}

Evaluation Dataset

json

Dataset: json
Size: 4,776 evaluation samples
Columns: query, positive, negative0, negative1, negative2, and negative3

Approximate statistics based on the first 100 samples:

	query	positive	negative0	negative1	negative2	negative3
type	string	string	string	string	string	string
modality	text	image	image	image	image	image
details	min: 46 tokens mean: 75.79 tokens max: 133 tokens

Samples:

query	positive	negative0	negative1	negative2	negative3
`May sits with her legs spread, her massive breasts barely contained by her bikini as she grips her huge cock and thick, long penis, precum leaking out while she looks over her shoulder with a smile.`	`./Images/11897115.jpg`	`./Images/12829919.jpg`	`./Images/12813676.jpg`	`./Images/12136766.jpg`	`./Images/12403205.jpg`
`On a sunny beach, Mythra from Xenoblade Chronicles 2 wears a skimpy sling bikini, her blonde hair and large breasts on full display as she kneels with arms up, cheeks flushed in an ahegao, enduring deep penetration from a big-penised ugly man while cum trickles from her lactating nipples and a thick toe curls between her fat ass cheeks.`	`./Images/12313417.jpg`	`./Images/12710154.jpg`	`./Images/12739902.jpg`	`./Images/11840408.jpg`	`./Images/12339885.jpg`
`Lisa from Genshin Impact kneels in the center of a gangbang, taking all three large penises deep in her mouth as thick saliva and lipstick marks glisten on their dark skin and her own light skin, while the tattooed, ugly man and his companions thrust into her mouth and onto her face, overwhelming her with big balls and big breasts.`	`./Images/12110929.jpg`	`./Images/12259516.jpg`	`./Images/12317214.jpg`	`./Images/11592249.jpg`	`./Images/12261530.jpg`

Loss: MatryoshkaLoss with these parameters:

{
    "loss": "CachedMultipleNegativesRankingLoss",
    "matryoshka_dims": [
        2048,
        1536,
        1024,
        512,
        256,
        128,
        64
    ],
    "matryoshka_weights": [
        1,
        1,
        1,
        1,
        1,
        1,
        1
    ],
    "n_dims_per_step": -1
}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 48
num_train_epochs: 1
learning_rate: 2e-05
warmup_steps: 0.1
bf16: True
per_device_eval_batch_size: 48
dataloader_num_workers: 8
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

per_device_train_batch_size: 48
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_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: 1.0
label_smoothing_factor: 0.0
bf16: True
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: 48
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: 8
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: no_duplicates
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	Validation Loss	nsfw-ir-eval_cosine_ndcg@10
0.3125	280	14.1777	-	-
0.3237	290	13.0856	-	-
0.3348	300	13.0595	-	-
0.3460	310	13.2660	-	-
0.3571	320	13.9253	-	-
0.3683	330	13.0266	-	-
0.3795	340	12.9428	-	-
0.3906	350	13.0304	-	-
0.4018	360	13.0024	-	-
0.4129	370	12.4377	-	-
0.4241	380	12.8503	-	-
0.4353	390	11.5343	-	-
0.4464	400	13.6251	-	-
0.4576	410	12.6396	-	-
0.4688	420	12.0347	-	-
0.4799	430	12.5446	-	-
0.4911	440	12.1837	-	-
0.5022	450	13.3048	-	-
0.5134	460	13.1663	-	-
0.5246	470	12.7172	-	-
0.5357	480	13.5921	-	-
0.5469	490	12.6573	-	-
0.5580	500	12.0380	-	-
0.5692	510	12.3582	-	-
0.5804	520	12.2693	-	-
0.5915	530	12.0021	-	-
0.6027	540	13.1601	-	-
0.6138	550	11.7692	-	-
0.625	560	12.3722	-	-
0.6362	570	11.3196	-	-
0.6473	580	11.6348	-	-
0.6585	590	11.8007	-	-
0.6696	600	12.9399	-	-
0.6808	610	12.2507	-	-
0.6920	620	12.3191	-	-
0.7031	630	11.2547	-	-
0.7143	640	12.8182	-	-
0.7254	650	11.6674	-	-
0.7366	660	10.7994	-	-
0.7478	670	11.8420	-	-
0.7589	680	11.9707	-	-
0.7701	690	12.0791	-	-
0.7812	700	11.6418	-	-
0.7924	710	11.9785	-	-
0.8036	720	11.1946	-	-
0.8147	730	12.6947	-	-
0.8259	740	12.2069	-	-
0.8371	750	11.7020	-	-
0.8482	760	12.0197	-	-
0.8594	770	12.8374	-	-
0.8705	780	11.4478	-	-
0.8817	790	11.5673	-	-
0.8929	800	11.5145	-	-
0.9040	810	11.6466	-	-
0.9152	820	11.0412	-	-
0.9263	830	11.7764	-	-
0.9375	840	11.4838	-	-
0.9487	850	11.5468	-	-
0.9598	860	12.9759	-	-
0.9710	870	11.7273	-	-
0.9821	880	12.1682	-	-
0.9933	890	13.0278	-	-
1.0	896	-	12.2338	0.3066
-1	-1	-	-	0.3066

Training Time

Training: 1.3 hours
Evaluation: 24.0 minutes
Total: 1.7 hours

Framework Versions

Python: 3.11.15
Sentence Transformers: 5.5.1
Transformers: 5.10.2
PyTorch: 2.11.0+cu128
Accelerate: 1.13.0
Datasets: 4.8.5
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",
}

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}
}

CachedMultipleNegativesRankingLoss

@misc{gao2021scaling,
    title={Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup},
    author={Luyu Gao and Yunyi Zhang and Jiawei Han and Jamie Callan},
    year={2021},
    eprint={2101.06983},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}