Instructions to use KhaledReda/all-MiniLM-L6-v33-pair_score with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KhaledReda/all-MiniLM-L6-v33-pair_score with sentence-transformers:

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("KhaledReda/all-MiniLM-L6-v33-pair_score")

sentences = [
"girls writing board",
"kids digital writing board 10 category kids toys and games educational games writing tags kids writing board boys writing board girls writing board unisex writing board drawing writing board color lcd screen writing board lock content writing board sketchboard todo list writing board notes panel writing board attrs units 10 target group kid description display a 10-inch 25.4 cm color lcd screen provides ample space for drawing and writing. posts lock content save drawings and notes. sketchboard to draw and color freely. to-do list write daily tasks. notes panel take notes and messages. this colorful electronic board is a fun and effective tool to enhance creativity and imagination in children. children can use them to draw color write letters and numbers take notes. adults can also use them to write lists and quick notes. the panel features a user-friendly interface and a high-quality color display which makes the process of drawing and writing enjoyable. in addition it is environmentally friendly and reusable making it an i",
"kids snorkelling kit fins and easybreath mask - blue category sports water sports snorkeling snorkeling tags easybreath snorkel mask water sports easybreath mask fins gear kit snorkel set keywords easybreath mask fins gear kit snorkel set attrs color blue target group kid sport snorkelling description designed for the user seeking to equip himself with an assorted set of easybreath jr fins snk 520. kit is easy to carry for a holiday at the sea. this set contains an easybreath mask a pair of snorkelling fins. it comes with a carry bag for easier transport. the perfect set for surface snorkellers.",
"non vegan shish tawook category restaurants international meat and poultry shish tawook tags rice shish tawook grilled vegetables shish tawook non vegan shish tawook shish tawook keywords non vegan shish tawook shish tawook description shish tawook. served with rice and grilled vegetables. 535 calories."
]
embeddings = model.encode(sentences)

similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [4, 4]

Notebooks
Google Colab
Kaggle

all-MiniLM-L6-v33-pair_score

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2 on the pairs_with_scores_v29 dataset. It maps sentences & paragraphs to a 384-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: sentence-transformers/all-MiniLM-L6-v2
Maximum Sequence Length: 256 tokens
Output Dimensionality: 384 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- pairs_with_scores_v29
Language: en
License: apache-2.0

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': 256, 'do_lower_case': False, 'architecture': 'BertModel'})
  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, '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
sentences = [
    'garnier facial kleenex mask',
    'neutrogena purify.boost t.detox.mask 30 m category beauty skincare face mask face mask tags neutrogena neutrogena boost detox mask neutrogena mask neutrogena purify boost mask neutrogena purify mask keywords neutrogena neutrogena boost detox mask neutrogena mask neutrogena purify boost mask neutrogena purify mask attrs units 30 m',
    'frozen sand painting set box category stationary arts and crafts painting paint tags kids toy boys toy girls toy unisex toy frozen sand painting box painting box painting set box keywords frozen sand painting box painting box painting set box description frozen sand painting set 15 tube of colorful sand .. no glue needed it s pre glued you just need to remove the yellow paper 3 y',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.7156, 0.4858],
#         [0.7156, 1.0000, 0.5266],
#         [0.4858, 0.5266, 1.0000]])

Training Details

Training Dataset

pairs_with_scores_v29

Dataset: pairs_with_scores_v29 at 1df6a91
Size: 9,464,974 training samples
Columns: sentence1, sentence2, and score
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 score
type string string float
details
min: 5 tokens
mean: 7.03 tokens
max: 21 tokens

min: 22 tokens
mean: 116.06 tokens
max: 256 tokens

min: 0.09
mean: 0.57
max: 1.0

	sentence1	sentence2	score
type	string	string	float
details	min: 5 tokens mean: 7.03 tokens max: 21 tokens	min: 22 tokens mean: 116.06 tokens max: 256 tokens	min: 0.09 mean: 0.57 max: 1.0

Samples:

sentence1	sentence2	score
`avocado omelette roll`	`greek yogurt category restaurants international dairy yogurt tags cinnamon greek yogurt walnuts greek yogurt honey greek yogurt greek yogurt yogurt greek nan greek yoghurt nan yoghurt keywords greek yogurt yogurt greek nan greek yoghurt nan yoghurt description greek yogurt cinnamon walnuts honey.`	`0.566356`
`wet brush detangler/bwr`	`titania hair care f/kids brush hr/1304 category beauty haircare hair brush and comb hair brush and comb tags kids hair brush girls hair brush boys hair brush unisex hair brush hair brush hair care brush titania titania hair brush keywords hair brush hair care brush titania titania hair brush attrs target group kid`	`0.808883`
`hand cleansing gel`	`alin 3.5 g/pcs 20/pcs category health and nutrition dietary supplements antioxidant antioxidant tags alin keywords alin attrs units 3.5 g 20 pcs`	`0.234341`

Loss: CoSENTLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "pairwise_cos_sim"
}

Evaluation Dataset

pairs_with_scores_v29

Dataset: pairs_with_scores_v29 at 1df6a91
Size: 47,563 evaluation samples
Columns: sentence1, sentence2, and score
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 score
type string string float
details
min: 5 tokens
mean: 6.99 tokens
max: 18 tokens

min: 22 tokens
mean: 116.61 tokens
max: 256 tokens

min: 0.11
mean: 0.57
max: 1.0

	sentence1	sentence2	score
type	string	string	float
details	min: 5 tokens mean: 6.99 tokens max: 18 tokens	min: 22 tokens mean: 116.61 tokens max: 256 tokens	min: 0.11 mean: 0.57 max: 1.0

Samples:

sentence1	sentence2	score
`givenchy pour homme edt men`	`uncharted the lost legacy hits ps 4 category entertainment gaming video game playstation game tags gaming accessory uncharted uncharted lost legacy hits uncharted ps 4 keywords uncharted uncharted lost legacy hits uncharted ps 4 description gaming accessories.`	`0.244742`
`lemon salt for fish and poultry`	stevia green powder ground category restaurants specialty foods pantry pantry tags stevia green powder caloriefree sweetener lowcalorie sugar stevia stevia for diabetes stevia powder for beverages stevia sweetener for desserts green stevia powder ground stevia powder natural sweetener stevia powder stevia sweetener keywords green stevia powder ground stevia powder natural sweetener stevia powder stevia sweetener description enjoy the natural sweetness of stevia green powder ground a calorie-free sugar substitute. benefits 1. natural sweetener stevia green powder is a natural sugar alternative. 2. low in calories it contains virtually no calories making it suitable for calorie-conscious individuals. 3. diabetic-friendly stevia is considered safe for people with diabetes. how to use use stevia green powder to sweeten beverages desserts or any recipe that calls for sugar.	`0.749969`
`the ordinary body cleanser`	`4 my hair curly shea but.hr.cr.250 m category beauty haircare hair cream hair cream tags 4 my hair 4 my hair hair cream curly hair cream shea butter hair cream keywords 4 my hair 4 my hair hair cream curly hair cream shea butter hair cream attrs units 250 m`	`0.473733`

Loss: CoSENTLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "pairwise_cos_sim"
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 128
per_device_eval_batch_size: 128
learning_rate: 2e-05
num_train_epochs: 1
warmup_ratio: 0.1
fp16: True

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 128
per_device_eval_batch_size: 128
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: True
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}
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch
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: batch_sampler
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Click to expand

Epoch	Step	Training Loss
0.0014	100	12.2795
0.0027	200	12.2016
0.0041	300	11.3843
0.0054	400	10.755
0.0068	500	10.0926
0.0081	600	9.6438
0.0095	700	9.2467
0.0108	800	9.0615
0.0122	900	8.911
0.0135	1000	8.7909
0.0149	1100	8.7178
0.0162	1200	8.6723
0.0176	1300	8.6135
0.0189	1400	8.5761
0.0203	1500	8.5354
0.0216	1600	8.5162
0.0230	1700	8.4944
0.0243	1800	8.4622
0.0257	1900	8.4543
0.0270	2000	8.4376
0.0284	2100	8.4256
0.0298	2200	8.408
0.0311	2300	8.3904
0.0325	2400	8.3793
0.0338	2500	8.3843
0.0352	2600	8.3628
0.0365	2700	8.3573
0.0379	2800	8.3498
0.0392	2900	8.3575
0.0406	3000	8.3403
0.0419	3100	8.3443
0.0433	3200	8.3428
0.0446	3300	8.3378
0.0460	3400	8.3329
0.0473	3500	8.3156
0.0487	3600	8.3146
0.0500	3700	8.3218
0.0514	3800	8.315
0.0527	3900	8.3073
0.0541	4000	8.2888
0.0554	4100	8.2963
0.0568	4200	8.3071
0.0582	4300	8.3028
0.0595	4400	8.2832
0.0609	4500	8.2928
0.0622	4600	8.2922
0.0636	4700	8.275
0.0649	4800	8.2843
0.0663	4900	8.2717
0.0676	5000	8.2712
0.0690	5100	8.2743
0.0703	5200	8.2773
0.0717	5300	8.2735
0.0730	5400	8.2712
0.0744	5500	8.2487
0.0757	5600	8.2732
0.0771	5700	8.2506
0.0784	5800	8.2403
0.0798	5900	8.2601
0.0811	6000	8.2558
0.0825	6100	8.2452
0.0838	6200	8.2486
0.0852	6300	8.2413
0.0865	6400	8.2597
0.0879	6500	8.2321
0.0893	6600	8.2289
0.0906	6700	8.2293
0.0920	6800	8.2378
0.0933	6900	8.2391
0.0947	7000	8.2287
0.0960	7100	8.2388
0.0974	7200	8.2335
0.0987	7300	8.2202
0.1001	7400	8.2255
0.1014	7500	8.2236
0.1028	7600	8.2095
0.1041	7700	8.1989
0.1055	7800	8.2061
0.1068	7900	8.202
0.1082	8000	8.2133
0.1095	8100	8.2127
0.1109	8200	8.1989
0.1122	8300	8.2144
0.1136	8400	8.1945
0.1149	8500	8.1897
0.1163	8600	8.1967
0.1177	8700	8.1951
0.1190	8800	8.191
0.1204	8900	8.1836
0.1217	9000	8.1947
0.1231	9100	8.1796
0.1244	9200	8.1916
0.1258	9300	8.1858
0.1271	9400	8.185
0.1285	9500	8.1759
0.1298	9600	8.1665
0.1312	9700	8.1852
0.1325	9800	8.1793
0.1339	9900	8.1843
0.1352	10000	8.1868
0.1366	10100	8.1836
0.1379	10200	8.175
0.1393	10300	8.1713
0.1406	10400	8.1761
0.1420	10500	8.1716
0.1433	10600	8.1694
0.1447	10700	8.1676
0.1461	10800	8.1558
0.1474	10900	8.167
0.1488	11000	8.1569
0.1501	11100	8.156
0.1515	11200	8.1568
0.1528	11300	8.152
0.1542	11400	8.171
0.1555	11500	8.1481
0.1569	11600	8.1503
0.1582	11700	8.1482
0.1596	11800	8.1513
0.1609	11900	8.1522
0.1623	12000	8.1457
0.1636	12100	8.1474
0.1650	12200	8.1545
0.1663	12300	8.142
0.1677	12400	8.1549
0.1690	12500	8.1367
0.1704	12600	8.1482
0.1717	12700	8.1448
0.1731	12800	8.1531
0.1745	12900	8.1375
0.1758	13000	8.1522
0.1772	13100	8.1382
0.1785	13200	8.1457
0.1799	13300	8.1372
0.1812	13400	8.123
0.1826	13500	8.1342
0.1839	13600	8.1333
0.1853	13700	8.1494
0.1866	13800	8.1368
0.1880	13900	8.14
0.1893	14000	8.1288
0.1907	14100	8.1274
0.1920	14200	8.1331
0.1934	14300	8.1423
0.1947	14400	8.1179
0.1961	14500	8.1265
0.1974	14600	8.1314
0.1988	14700	8.1334
0.2001	14800	8.1187
0.2015	14900	8.131
0.2029	15000	8.127
0.2042	15100	8.1182
0.2056	15200	8.1301
0.2069	15300	8.1293
0.2083	15400	8.1191
0.2096	15500	8.1116
0.2110	15600	8.1242
0.2123	15700	8.1109
0.2137	15800	8.1047
0.2150	15900	8.111
0.2164	16000	8.1119
0.2177	16100	8.1158
0.2191	16200	8.1095
0.2204	16300	8.1044
0.2218	16400	8.1133
0.2231	16500	8.1089
0.2245	16600	8.1192
0.2258	16700	8.1022
0.2272	16800	8.1266
0.2285	16900	8.105
0.2299	17000	8.1097
0.2312	17100	8.1107
0.2326	17200	8.098
0.2340	17300	8.1116
0.2353	17400	8.0907
0.2367	17500	8.1139
0.2380	17600	8.1004
0.2394	17700	8.1072
0.2407	17800	8.1064
0.2421	17900	8.1086
0.2434	18000	8.1038
0.2448	18100	8.0967
0.2461	18200	8.1005
0.2475	18300	8.1043
0.2488	18400	8.1046
0.2502	18500	8.1001
0.2515	18600	8.0979
0.2529	18700	8.0809
0.2542	18800	8.0931
0.2556	18900	8.1028
0.2569	19000	8.0913
0.2583	19100	8.0852
0.2596	19200	8.0887
0.2610	19300	8.1051
0.2624	19400	8.0955
0.2637	19500	8.0825
0.2651	19600	8.0924
0.2664	19700	8.0941
0.2678	19800	8.0894
0.2691	19900	8.0739
0.2705	20000	8.0964
0.2718	20100	8.0955
0.2732	20200	8.0847
0.2745	20300	8.0909
0.2759	20400	8.0763
0.2772	20500	8.0865
0.2786	20600	8.0806
0.2799	20700	8.0741
0.2813	20800	8.0788
0.2826	20900	8.0993
0.2840	21000	8.0889
0.2853	21100	8.1066
0.2867	21200	8.0787
0.2880	21300	8.0766
0.2894	21400	8.0913
0.2908	21500	8.0922
0.2921	21600	8.0713
0.2935	21700	8.0794
0.2948	21800	8.0984
0.2962	21900	8.0854
0.2975	22000	8.0753
0.2989	22100	8.0766
0.3002	22200	8.0753
0.3016	22300	8.0797
0.3029	22400	8.0679
0.3043	22500	8.0845
0.3056	22600	8.077
0.3070	22700	8.0772
0.3083	22800	8.0789
0.3097	22900	8.0796
0.3110	23000	8.0824
0.3124	23100	8.0907
0.3137	23200	8.0718
0.3151	23300	8.0731
0.3164	23400	8.0722
0.3178	23500	8.0721
0.3192	23600	8.0596
0.3205	23700	8.0724
0.3219	23800	8.0754
0.3232	23900	8.073
0.3246	24000	8.0695
0.3259	24100	8.072
0.3273	24200	8.0747
0.3286	24300	8.065
0.3300	24400	8.0725
0.3313	24500	8.0537
0.3327	24600	8.0738
0.3340	24700	8.08
0.3354	24800	8.0577
0.3367	24900	8.0679
0.3381	25000	8.0668
0.3394	25100	8.0666
0.3408	25200	8.0565
0.3421	25300	8.0783
0.3435	25400	8.071
0.3448	25500	8.084
0.3462	25600	8.0592
0.3476	25700	8.0522
0.3489	25800	8.0531
0.3503	25900	8.0811
0.3516	26000	8.0554
0.3530	26100	8.0649
0.3543	26200	8.0486
0.3557	26300	8.0627
0.3570	26400	8.0694
0.3584	26500	8.0624
0.3597	26600	8.0687
0.3611	26700	8.0561
0.3624	26800	8.0466
0.3638	26900	8.0607
0.3651	27000	8.0461
0.3665	27100	8.0541
0.3678	27200	8.0624
0.3692	27300	8.0543
0.3705	27400	8.0624
0.3719	27500	8.0648
0.3732	27600	8.0625
0.3746	27700	8.0656
0.3760	27800	8.0514
0.3773	27900	8.061
0.3787	28000	8.0461
0.3800	28100	8.0426
0.3814	28200	8.0481
0.3827	28300	8.0554
0.3841	28400	8.0526
0.3854	28500	8.046
0.3868	28600	8.0488
0.3881	28700	8.045
0.3895	28800	8.0568
0.3908	28900	8.0539
0.3922	29000	8.0453
0.3935	29100	8.0674
0.3949	29200	8.0426
0.3962	29300	8.0433
0.3976	29400	8.0532
0.3989	29500	8.0289
0.4003	29600	8.0539
0.4016	29700	8.0574
0.4030	29800	8.0558
0.4043	29900	8.0585
0.4057	30000	8.0512
0.4071	30100	8.0519
0.4084	30200	8.0514
0.4098	30300	8.0464
0.4111	30400	8.0417
0.4125	30500	8.0476
0.4138	30600	8.0346
0.4152	30700	8.0618
0.4165	30800	8.0414
0.4179	30900	8.0421
0.4192	31000	8.0349
0.4206	31100	8.0603
0.4219	31200	8.0436
0.4233	31300	8.0441
0.4246	31400	8.0462
0.4260	31500	8.042
0.4273	31600	8.0424
0.4287	31700	8.0387
0.4300	31800	8.0512
0.4314	31900	8.0372
0.4327	32000	8.037
0.4341	32100	8.0529
0.4355	32200	8.046
0.4368	32300	8.0362
0.4382	32400	8.0438
0.4395	32500	8.0431
0.4409	32600	8.0355
0.4422	32700	8.0276
0.4436	32800	8.0263
0.4449	32900	8.0263
0.4463	33000	8.0299
0.4476	33100	8.0394
0.4490	33200	8.0262
0.4503	33300	8.0514
0.4517	33400	8.0194
0.4530	33500	8.0506
0.4544	33600	8.0361
0.4557	33700	8.0383
0.4571	33800	8.0341
0.4584	33900	8.0565
0.4598	34000	8.0325
0.4611	34100	8.0259
0.4625	34200	8.0377
0.4639	34300	8.0133
0.4652	34400	8.0346
0.4666	34500	8.0291
0.4679	34600	8.0238
0.4693	34700	8.0273
0.4706	34800	8.0415
0.4720	34900	8.0226
0.4733	35000	8.0408
0.4747	35100	8.0433
0.4760	35200	8.0432
0.4774	35300	8.0542
0.4787	35400	8.0346
0.4801	35500	8.0292
0.4814	35600	8.0221
0.4828	35700	8.0321
0.4841	35800	8.0036
0.4855	35900	8.018
0.4868	36000	8.0329
0.4882	36100	8.0265
0.4895	36200	8.0235
0.4909	36300	8.0247
0.4923	36400	8.0261
0.4936	36500	8.0237
0.4950	36600	8.0245
0.4963	36700	8.0263
0.4977	36800	8.0137
0.4990	36900	8.0176
0.5004	37000	8.0292
0.5017	37100	8.0287
0.5031	37200	8.0378
0.5044	37300	8.0297
0.5058	37400	8.0203
0.5071	37500	8.0158
0.5085	37600	8.0481
0.5098	37700	8.0142
0.5112	37800	8.031
0.5125	37900	8.017
0.5139	38000	8.0353
0.5152	38100	8.0059
0.5166	38200	8.0259
0.5179	38300	8.0396
0.5193	38400	8.023
0.5207	38500	8.0223
0.5220	38600	8.0262
0.5234	38700	8.0226
0.5247	38800	8.0216
0.5261	38900	8.0253
0.5274	39000	8.0185
0.5288	39100	8.0271
0.5301	39200	8.0144
0.5315	39300	8.0214
0.5328	39400	8.029
0.5342	39500	8.0105
0.5355	39600	8.0103
0.5369	39700	8.0121
0.5382	39800	8.0184
0.5396	39900	8.0085
0.5409	40000	8.0041
0.5423	40100	8.0109
0.5436	40200	8.0246
0.5450	40300	8.0274
0.5463	40400	8.0287
0.5477	40500	8.0238
0.5490	40600	8.0297
0.5504	40700	8.0073
0.5518	40800	8.0265
0.5531	40900	8.0144
0.5545	41000	8.0176
0.5558	41100	8.0261
0.5572	41200	8.0197
0.5585	41300	8.0208
0.5599	41400	8.0145
0.5612	41500	8.0127
0.5626	41600	8.0233
0.5639	41700	8.0229
0.5653	41800	8.0175
0.5666	41900	8.0068
0.5680	42000	8.0071
0.5693	42100	8.0038
0.5707	42200	8.0027
0.5720	42300	8.0213
0.5734	42400	8.0154
0.5747	42500	8.0299
0.5761	42600	8.0031
0.5774	42700	8.0103
0.5788	42800	8.0131
0.5802	42900	8.0096
0.5815	43000	8.0314
0.5829	43100	8.0157
0.5842	43200	8.0159
0.5856	43300	8.001
0.5869	43400	7.9849
0.5883	43500	8.014
0.5896	43600	8.0176
0.5910	43700	7.9985
0.5923	43800	8.013
0.5937	43900	8.0277
0.5950	44000	8.0088
0.5964	44100	8.0087
0.5977	44200	8.0155
0.5991	44300	8.0118
0.6004	44400	8.0181
0.6018	44500	8.0197
0.6031	44600	8.0137
0.6045	44700	8.0059
0.6058	44800	8.0075
0.6072	44900	8.0021
0.6086	45000	8.0008
0.6099	45100	7.9883
0.6113	45200	7.9835
0.6126	45300	8.0089
0.6140	45400	8.0063
0.6153	45500	8.0204
0.6167	45600	7.9975
0.6180	45700	8.0016
0.6194	45800	8.0002
0.6207	45900	8.0153
0.6221	46000	8.0109
0.6234	46100	8.0101
0.6248	46200	8.0067
0.6261	46300	7.986
0.6275	46400	7.9997
0.6288	46500	8.0096
0.6302	46600	7.9938
0.6315	46700	7.9949
0.6329	46800	8.0059
0.6342	46900	8.0081
0.6356	47000	8.0123
0.6370	47100	8.0119
0.6383	47200	7.9975
0.6397	47300	7.9997
0.6410	47400	8.0107
0.6424	47500	7.9979
0.6437	47600	8.0084
0.6451	47700	8.0174
0.6464	47800	8.0076
0.6478	47900	8.0256
0.6491	48000	8.0063
0.6505	48100	8.0097
0.6518	48200	7.9999
0.6532	48300	8.0015
0.6545	48400	7.9936
0.6559	48500	7.9893
0.6572	48600	8.0179
0.6586	48700	7.9885
0.6599	48800	7.996
0.6613	48900	8.0184
0.6626	49000	8.0006
0.6640	49100	8.0084
0.6654	49200	8.0089
0.6667	49300	8.0036
0.6681	49400	7.9857
0.6694	49500	7.9916
0.6708	49600	7.9891
0.6721	49700	7.9988
0.6735	49800	7.9783
0.6748	49900	7.9963
0.6762	50000	7.9927
0.6775	50100	8.0019
0.6789	50200	7.9996
0.6802	50300	8.0086
0.6816	50400	7.9843
0.6829	50500	7.9965
0.6843	50600	8.0086
0.6856	50700	7.9946
0.6870	50800	7.9944
0.6883	50900	8.0038
0.6897	51000	7.996
0.6910	51100	7.9857
0.6924	51200	7.9979
0.6937	51300	8.0075
0.6951	51400	7.994
0.6965	51500	7.9955
0.6978	51600	7.9968
0.6992	51700	8.0039
0.7005	51800	8.0121
0.7019	51900	7.9934
0.7032	52000	7.9888
0.7046	52100	7.9967
0.7059	52200	8.0016
0.7073	52300	7.9998
0.7086	52400	8.0095
0.7100	52500	8.0039
0.7113	52600	7.9842
0.7127	52700	7.9922
0.7140	52800	7.9817
0.7154	52900	7.9834
0.7167	53000	7.9919
0.7181	53100	7.9802
0.7194	53200	7.9949
0.7208	53300	7.9832
0.7221	53400	7.9957
0.7235	53500	8.0054
0.7249	53600	7.9865
0.7262	53700	7.9833
0.7276	53800	8.0055
0.7289	53900	8.0239
0.7303	54000	8.0075
0.7316	54100	7.9921
0.7330	54200	7.9942
0.7343	54300	8.0124
0.7357	54400	7.9977
0.7370	54500	8.0085
0.7384	54600	7.9812
0.7397	54700	8.0043
0.7411	54800	8.011
0.7424	54900	7.9716
0.7438	55000	7.9917
0.7451	55100	7.9928
0.7465	55200	7.9922
0.7478	55300	8.0015
0.7492	55400	7.9784
0.7505	55500	7.98
0.7519	55600	7.9931
0.7533	55700	7.9935
0.7546	55800	7.971
0.7560	55900	7.9826
0.7573	56000	7.9786
0.7587	56100	7.9919
0.7600	56200	7.9737
0.7614	56300	7.9909
0.7627	56400	7.9818
0.7641	56500	7.9898
0.7654	56600	7.9984
0.7668	56700	7.9854
0.7681	56800	7.9818
0.7695	56900	8.0007
0.7708	57000	7.9833
0.7722	57100	7.9976
0.7735	57200	7.9921
0.7749	57300	7.9926
0.7762	57400	7.9989
0.7776	57500	7.9851
0.7789	57600	7.987
0.7803	57700	7.9836
0.7817	57800	8.0069
0.7830	57900	8.0049
0.7844	58000	7.9807
0.7857	58100	7.9768
0.7871	58200	7.992
0.7884	58300	7.974
0.7898	58400	8.0023
0.7911	58500	7.9865
0.7925	58600	8.0048
0.7938	58700	7.9811
0.7952	58800	7.9989
0.7965	58900	7.9771
0.7979	59000	7.9906
0.7992	59100	7.9841
0.8006	59200	8.0019
0.8019	59300	7.9819
0.8033	59400	7.9775
0.8046	59500	7.9923
0.8060	59600	7.994
0.8073	59700	7.9813
0.8087	59800	7.991
0.8101	59900	7.9854
0.8114	60000	7.9798
0.8128	60100	7.9846
0.8141	60200	7.986
0.8155	60300	7.9872
0.8168	60400	7.9918
0.8182	60500	7.9683
0.8195	60600	7.9749
0.8209	60700	7.9853
0.8222	60800	7.9958
0.8236	60900	7.9825
0.8249	61000	7.9913
0.8263	61100	7.9849
0.8276	61200	7.9786
0.8290	61300	7.9839
0.8303	61400	7.9894
0.8317	61500	7.9818
0.8330	61600	7.9895
0.8344	61700	7.9717
0.8357	61800	7.9998
0.8371	61900	7.9856
0.8384	62000	7.9835
0.8398	62100	7.9773
0.8412	62200	7.9781
0.8425	62300	7.9779
0.8439	62400	7.9734
0.8452	62500	7.9947
0.8466	62600	7.9778
0.8479	62700	7.9857
0.8493	62800	7.9793
0.8506	62900	7.9729
0.8520	63000	7.9825
0.8533	63100	7.9773
0.8547	63200	7.9715
0.8560	63300	7.9758
0.8574	63400	7.9715
0.8587	63500	7.9856
0.8601	63600	7.9913
0.8614	63700	7.9703
0.8628	63800	7.9802
0.8641	63900	7.9941
0.8655	64000	7.9715
0.8668	64100	8.0014
0.8682	64200	7.9967
0.8696	64300	7.9788
0.8709	64400	7.9809
0.8723	64500	7.9719
0.8736	64600	7.9846
0.8750	64700	7.9933
0.8763	64800	7.9716
0.8777	64900	7.9799
0.8790	65000	7.9718
0.8804	65100	7.982
0.8817	65200	7.9701
0.8831	65300	8.0089
0.8844	65400	7.9687
0.8858	65500	7.9724
0.8871	65600	7.9781
0.8885	65700	7.9867
0.8898	65800	7.9909
0.8912	65900	7.9875
0.8925	66000	7.9748
0.8939	66100	7.9729
0.8952	66200	7.9777
0.8966	66300	7.9898
0.8980	66400	7.9806
0.8993	66500	7.9762
0.9007	66600	7.9694
0.9020	66700	7.9949
0.9034	66800	7.9785
0.9047	66900	7.978
0.9061	67000	7.969
0.9074	67100	7.9844
0.9088	67200	7.9678
0.9101	67300	7.988
0.9115	67400	7.9696
0.9128	67500	7.9921
0.9142	67600	7.9744
0.9155	67700	7.9647
0.9169	67800	7.96
0.9182	67900	7.9649
0.9196	68000	7.974
0.9209	68100	7.9747
0.9223	68200	7.9783
0.9236	68300	7.9794
0.9250	68400	7.9659
0.9264	68500	7.9875
0.9277	68600	7.9639
0.9291	68700	7.9767
0.9304	68800	7.9741
0.9318	68900	7.9663
0.9331	69000	7.9677
0.9345	69100	7.9745
0.9358	69200	7.9703
0.9372	69300	7.9768
0.9385	69400	7.9683
0.9399	69500	7.9776
0.9412	69600	7.9656
0.9426	69700	7.983
0.9439	69800	7.9763
0.9453	69900	7.9708
0.9466	70000	7.9702
0.9480	70100	7.968
0.9493	70200	7.9637
0.9507	70300	7.9766
0.9520	70400	7.9808
0.9534	70500	7.9659
0.9548	70600	7.9809
0.9561	70700	7.9829
0.9575	70800	7.9808
0.9588	70900	7.9755
0.9602	71000	7.9811
0.9615	71100	7.9796
0.9629	71200	7.9736
0.9642	71300	7.9692
0.9656	71400	7.9704
0.9669	71500	7.9819
0.9683	71600	7.9793
0.9696	71700	7.9818
0.9710	71800	7.9648
0.9723	71900	7.9953
0.9737	72000	7.9799
0.9750	72100	7.9734
0.9764	72200	7.99
0.9777	72300	7.9727
0.9791	72400	7.9832
0.9804	72500	7.9609
0.9818	72600	7.9734
0.9831	72700	7.9573
0.9845	72800	7.9753
0.9859	72900	7.9946
0.9872	73000	7.9823
0.9886	73100	7.9682
0.9899	73200	7.9774
0.9913	73300	7.9952
0.9926	73400	7.9699
0.9940	73500	7.9682
0.9953	73600	7.9745
0.9967	73700	7.9712
0.9980	73800	7.969
0.9994	73900	7.9629

Framework Versions

Python: 3.12.3
Sentence Transformers: 5.1.0
Transformers: 4.55.4
PyTorch: 2.6.0+cu124
Accelerate: 1.10.1
Datasets: 4.0.0
Tokenizers: 0.21.4

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",
}

CoSENTLoss

@online{kexuefm-8847,
    title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
    author={Su Jianlin},
    year={2022},
    month={Jan},
    url={https://kexue.fm/archives/8847},
}

Downloads last month: 1

Safetensors

Model size

22.7M params

Tensor type

F32

Model tree for KhaledReda/all-MiniLM-L6-v33-pair_score

Base model

sentence-transformers/all-MiniLM-L6-v2

Finetuned

(907)

this model

Dataset used to train KhaledReda/all-MiniLM-L6-v33-pair_score

Paper for KhaledReda/all-MiniLM-L6-v33-pair_score

Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

Paper • 1908.10084 • Published Aug 27, 2019 • 13