SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2. 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

Model Sources

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("Devy1/MiniLM-cosqa-32")
# Run inference
sentences = [
    'bottom 5 rows in python',
    'def table_top_abs(self):\n        """Returns the absolute position of table top"""\n        table_height = np.array([0, 0, self.table_full_size[2]])\n        return string_to_array(self.floor.get("pos")) + table_height',
    'def refresh(self, document):\n\t\t""" Load a new copy of a document from the database.  does not\n\t\t\treplace the old one """\n\t\ttry:\n\t\t\told_cache_size = self.cache_size\n\t\t\tself.cache_size = 0\n\t\t\tobj = self.query(type(document)).filter_by(mongo_id=document.mongo_id).one()\n\t\tfinally:\n\t\t\tself.cache_size = old_cache_size\n\t\tself.cache_write(obj)\n\t\treturn obj',
]
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,  0.4728, -0.0350],
#         [ 0.4728,  1.0000, -0.0494],
#         [-0.0350, -0.0494,  1.0000]])

Training Details

Training Dataset

Unnamed Dataset

  • Size: 9,020 training samples
  • Columns: anchor and positive
  • Approximate statistics based on the first 1000 samples:
    anchor positive
    type string string
    details
    • min: 6 tokens
    • mean: 9.67 tokens
    • max: 21 tokens
    • min: 40 tokens
    • mean: 86.17 tokens
    • max: 256 tokens
  • Samples:
    anchor positive
    1d array in char datatype in python def _convert_to_array(array_like, dtype):
    """
    Convert Matrix attributes which are array-like or buffer to array.
    """
    if isinstance(array_like, bytes):
    return np.frombuffer(array_like, dtype=dtype)
    return np.asarray(array_like, dtype=dtype)
    python condition non none def _not(condition=None, **kwargs):
    """
    Return the opposite of input condition.

    :param condition: condition to process.

    :result: not condition.
    :rtype: bool
    """

    result = True

    if condition is not None:
    result = not run(condition, **kwargs)

    return result
    accessing a column from a matrix in python def get_column(self, X, column):
    """Return a column of the given matrix.

    Args:
    X: numpy.ndarray or pandas.DataFrame.
    column: int or str.

    Returns:
    np.ndarray: Selected column.
    """
    if isinstance(X, pd.DataFrame):
    return X[column].values

    return X[:, column]
  • Loss: MultipleNegativesRankingLoss with these parameters:
    {
        "scale": 20.0,
        "similarity_fct": "cos_sim",
        "gather_across_devices": false
    }
    

Training Hyperparameters

Non-Default Hyperparameters

  • per_device_train_batch_size: 32
  • fp16: 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: 32
  • 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: 5e-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
  • max_steps: -1
  • lr_scheduler_type: linear
  • 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
  • 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}
  • 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: batch_sampler
  • multi_dataset_batch_sampler: proportional
  • router_mapping: {}
  • learning_rate_mapping: {}

Training Logs

Click to expand
Epoch Step Training Loss
0.0035 1 0.5705
0.0071 2 0.1217
0.0106 3 0.1985
0.0142 4 0.2742
0.0177 5 0.0782
0.0213 6 0.1748
0.0248 7 0.1914
0.0284 8 0.0911
0.0319 9 0.0368
0.0355 10 0.219
0.0390 11 0.1571
0.0426 12 0.081
0.0461 13 0.1152
0.0496 14 0.0556
0.0532 15 0.1375
0.0567 16 0.1844
0.0603 17 0.3164
0.0638 18 0.2312
0.0674 19 0.1767
0.0709 20 0.0975
0.0745 21 0.2848
0.0780 22 0.0972
0.0816 23 0.3153
0.0851 24 0.1087
0.0887 25 0.1673
0.0922 26 0.2074
0.0957 27 0.2197
0.0993 28 0.2571
0.1028 29 0.1873
0.1064 30 0.0657
0.1099 31 0.0675
0.1135 32 0.0749
0.1170 33 0.0948
0.1206 34 0.0849
0.1241 35 0.0882
0.1277 36 0.0436
0.1312 37 0.1173
0.1348 38 0.1512
0.1383 39 0.1062
0.1418 40 0.0384
0.1454 41 0.148
0.1489 42 0.0432
0.1525 43 0.1027
0.1560 44 0.4193
0.1596 45 0.1003
0.1631 46 0.113
0.1667 47 0.0846
0.1702 48 0.0899
0.1738 49 0.0952
0.1773 50 0.0553
0.1809 51 0.11
0.1844 52 0.1955
0.1879 53 0.1103
0.1915 54 0.0738
0.1950 55 0.1217
0.1986 56 0.274
0.2021 57 0.1471
0.2057 58 0.0727
0.2092 59 0.0438
0.2128 60 0.1521
0.2163 61 0.1359
0.2199 62 0.1217
0.2234 63 0.2226
0.2270 64 0.2676
0.2305 65 0.1649
0.2340 66 0.1675
0.2376 67 0.1278
0.2411 68 0.1627
0.2447 69 0.108
0.2482 70 0.1327
0.2518 71 0.1762
0.2553 72 0.41
0.2589 73 0.1551
0.2624 74 0.1893
0.2660 75 0.0847
0.2695 76 0.0949
0.2730 77 0.2214
0.2766 78 0.0439
0.2801 79 0.1355
0.2837 80 0.1951
0.2872 81 0.068
0.2908 82 0.1032
0.2943 83 0.1131
0.2979 84 0.2245
0.3014 85 0.2323
0.3050 86 0.1512
0.3085 87 0.1686
0.3121 88 0.0797
0.3156 89 0.2182
0.3191 90 0.2181
0.3227 91 0.0944
0.3262 92 0.083
0.3298 93 0.1554
0.3333 94 0.0999
0.3369 95 0.1948
0.3404 96 0.1446
0.3440 97 0.2856
0.3475 98 0.0786
0.3511 99 0.1112
0.3546 100 0.0571
0.3582 101 0.2553
0.3617 102 0.0546
0.3652 103 0.1948
0.3688 104 0.0945
0.3723 105 0.0973
0.3759 106 0.0478
0.3794 107 0.3652
0.3830 108 0.2676
0.3865 109 0.1216
0.3901 110 0.0701
0.3936 111 0.0918
0.3972 112 0.1813
0.4007 113 0.1243
0.4043 114 0.2819
0.4078 115 0.0103
0.4113 116 0.2099
0.4149 117 0.0879
0.4184 118 0.1614
0.4220 119 0.0869
0.4255 120 0.0942
0.4291 121 0.0592
0.4326 122 0.1387
0.4362 123 0.0805
0.4397 124 0.1844
0.4433 125 0.0292
0.4468 126 0.3999
0.4504 127 0.1031
0.4539 128 0.3445
0.4574 129 0.2309
0.4610 130 0.1887
0.4645 131 0.2472
0.4681 132 0.1128
0.4716 133 0.1276
0.4752 134 0.1141
0.4787 135 0.1117
0.4823 136 0.1593
0.4858 137 0.0363
0.4894 138 0.1564
0.4929 139 0.21
0.4965 140 0.2024
0.5 141 0.1785
0.5035 142 0.1456
0.5071 143 0.0986
0.5106 144 0.1947
0.5142 145 0.1733
0.5177 146 0.1656
0.5213 147 0.0951
0.5248 148 0.1216
0.5284 149 0.0875
0.5319 150 0.1284
0.5355 151 0.1066
0.5390 152 0.0692
0.5426 153 0.2287
0.5461 154 0.233
0.5496 155 0.1066
0.5532 156 0.0862
0.5567 157 0.0877
0.5603 158 0.3095
0.5638 159 0.1237
0.5674 160 0.0682
0.5709 161 0.0741
0.5745 162 0.2003
0.5780 163 0.1392
0.5816 164 0.0493
0.5851 165 0.3129
0.5887 166 0.1186
0.5922 167 0.0369
0.5957 168 0.1224
0.5993 169 0.2212
0.6028 170 0.0809
0.6064 171 0.116
0.6099 172 0.2251
0.6135 173 0.0195
0.6170 174 0.0476
0.6206 175 0.0818
0.6241 176 0.0313
0.6277 177 0.188
0.6312 178 0.2736
0.6348 179 0.1444
0.6383 180 0.0924
0.6418 181 0.0895
0.6454 182 0.2116
0.6489 183 0.3288
0.6525 184 0.1659
0.6560 185 0.1367
0.6596 186 0.1834
0.6631 187 0.0822
0.6667 188 0.1384
0.6702 189 0.1602
0.6738 190 0.1325
0.6773 191 0.1033
0.6809 192 0.1102
0.6844 193 0.0786
0.6879 194 0.1158
0.6915 195 0.0639
0.6950 196 0.18
0.6986 197 0.0512
0.7021 198 0.1271
0.7057 199 0.0839
0.7092 200 0.0838
0.7128 201 0.0691
0.7163 202 0.1457
0.7199 203 0.1363
0.7234 204 0.1059
0.7270 205 0.1051
0.7305 206 0.0541
0.7340 207 0.1409
0.7376 208 0.0911
0.7411 209 0.2823
0.7447 210 0.156
0.7482 211 0.394
0.7518 212 0.1946
0.7553 213 0.0282
0.7589 214 0.1497
0.7624 215 0.1643
0.7660 216 0.0236
0.7695 217 0.0654
0.7730 218 0.0537
0.7766 219 0.1068
0.7801 220 0.051
0.7837 221 0.072
0.7872 222 0.0413
0.7908 223 0.0918
0.7943 224 0.1308
0.7979 225 0.0694
0.8014 226 0.0852
0.8050 227 0.0321
0.8085 228 0.1497
0.8121 229 0.0959
0.8156 230 0.226
0.8191 231 0.1129
0.8227 232 0.0831
0.8262 233 0.2181
0.8298 234 0.1054
0.8333 235 0.1812
0.8369 236 0.0455
0.8404 237 0.1413
0.8440 238 0.0801
0.8475 239 0.0301
0.8511 240 0.0846
0.8546 241 0.1862
0.8582 242 0.1015
0.8617 243 0.0459
0.8652 244 0.0774
0.8688 245 0.1444
0.8723 246 0.2849
0.8759 247 0.3935
0.8794 248 0.2126
0.8830 249 0.0845
0.8865 250 0.1429
0.8901 251 0.0107
0.8936 252 0.0599
0.8972 253 0.1192
0.9007 254 0.1369
0.9043 255 0.1246
0.9078 256 0.0163
0.9113 257 0.1844
0.9149 258 0.1017
0.9184 259 0.0415
0.9220 260 0.1658
0.9255 261 0.0755
0.9291 262 0.086
0.9326 263 0.081
0.9362 264 0.2776
0.9397 265 0.1284
0.9433 266 0.1591
0.9468 267 0.1397
0.9504 268 0.0334
0.9539 269 0.0449
0.9574 270 0.1382
0.9610 271 0.1736
0.9645 272 0.236
0.9681 273 0.225
0.9716 274 0.2444
0.9752 275 0.0497
0.9787 276 0.1212
0.9823 277 0.1405
0.9858 278 0.1116
0.9894 279 0.0369
0.9929 280 0.0321
0.9965 281 0.1481
1.0 282 0.1046
1.0035 283 0.0673
1.0071 284 0.078
1.0106 285 0.0723
1.0142 286 0.1328
1.0177 287 0.1399
1.0213 288 0.186
1.0248 289 0.0747
1.0284 290 0.0291
1.0319 291 0.0427
1.0355 292 0.0288
1.0390 293 0.1552
1.0426 294 0.0123
1.0461 295 0.0617
1.0496 296 0.0646
1.0532 297 0.2001
1.0567 298 0.068
1.0603 299 0.0108
1.0638 300 0.0776
1.0674 301 0.1037
1.0709 302 0.0087
1.0745 303 0.1564
1.0780 304 0.0665
1.0816 305 0.0246
1.0851 306 0.061
1.0887 307 0.038
1.0922 308 0.1016
1.0957 309 0.0434
1.0993 310 0.1178
1.1028 311 0.1235
1.1064 312 0.0164
1.1099 313 0.0838
1.1135 314 0.0516
1.1170 315 0.1195
1.1206 316 0.1026
1.1241 317 0.0387
1.1277 318 0.1057
1.1312 319 0.0332
1.1348 320 0.033
1.1383 321 0.0648
1.1418 322 0.0067
1.1454 323 0.0402
1.1489 324 0.1376
1.1525 325 0.0852
1.1560 326 0.0245
1.1596 327 0.087
1.1631 328 0.0403
1.1667 329 0.0998
1.1702 330 0.0634
1.1738 331 0.0218
1.1773 332 0.1244
1.1809 333 0.1178
1.1844 334 0.1135
1.1879 335 0.0721
1.1915 336 0.0427
1.1950 337 0.0314
1.1986 338 0.0577
1.2021 339 0.0337
1.2057 340 0.0312
1.2092 341 0.0336
1.2128 342 0.0289
1.2163 343 0.0946
1.2199 344 0.2581
1.2234 345 0.1359
1.2270 346 0.0223
1.2305 347 0.055
1.2340 348 0.0591
1.2376 349 0.0286
1.2411 350 0.0128
1.2447 351 0.0676
1.2482 352 0.0744
1.2518 353 0.0208
1.2553 354 0.0877
1.2589 355 0.0759
1.2624 356 0.052
1.2660 357 0.2666
1.2695 358 0.0455
1.2730 359 0.0893
1.2766 360 0.1706
1.2801 361 0.059
1.2837 362 0.049
1.2872 363 0.1249
1.2908 364 0.0229
1.2943 365 0.1088
1.2979 366 0.198
1.3014 367 0.2119
1.3050 368 0.0397
1.3085 369 0.1772
1.3121 370 0.1251
1.3156 371 0.0286
1.3191 372 0.0273
1.3227 373 0.1161
1.3262 374 0.1128
1.3298 375 0.1323
1.3333 376 0.0245
1.3369 377 0.0342
1.3404 378 0.1177
1.3440 379 0.0584
1.3475 380 0.0164
1.3511 381 0.1174
1.3546 382 0.043
1.3582 383 0.0706
1.3617 384 0.0862
1.3652 385 0.1093
1.3688 386 0.0849
1.3723 387 0.0252
1.3759 388 0.0517
1.3794 389 0.0634
1.3830 390 0.0526
1.3865 391 0.1388
1.3901 392 0.0747
1.3936 393 0.0362
1.3972 394 0.1148
1.4007 395 0.0208
1.4043 396 0.1426
1.4078 397 0.1611
1.4113 398 0.0302
1.4149 399 0.0446
1.4184 400 0.0182
1.4220 401 0.089
1.4255 402 0.1423
1.4291 403 0.1599
1.4326 404 0.0438
1.4362 405 0.0103
1.4397 406 0.083
1.4433 407 0.0914
1.4468 408 0.0436
1.4504 409 0.124
1.4539 410 0.0896
1.4574 411 0.256
1.4610 412 0.0061
1.4645 413 0.0529
1.4681 414 0.0851
1.4716 415 0.08
1.4752 416 0.0115
1.4787 417 0.0784
1.4823 418 0.0321
1.4858 419 0.0976
1.4894 420 0.0725
1.4929 421 0.0834
1.4965 422 0.122
1.5 423 0.1294
1.5035 424 0.2754
1.5071 425 0.0884
1.5106 426 0.076
1.5142 427 0.0799
1.5177 428 0.0439
1.5213 429 0.0943
1.5248 430 0.077
1.5284 431 0.0696
1.5319 432 0.0251
1.5355 433 0.1715
1.5390 434 0.0913
1.5426 435 0.0251
1.5461 436 0.0642
1.5496 437 0.0375
1.5532 438 0.0381
1.5567 439 0.0628
1.5603 440 0.095
1.5638 441 0.0441
1.5674 442 0.0496
1.5709 443 0.0531
1.5745 444 0.0304
1.5780 445 0.2032
1.5816 446 0.109
1.5851 447 0.1481
1.5887 448 0.0706
1.5922 449 0.0346
1.5957 450 0.0364
1.5993 451 0.0513
1.6028 452 0.3153
1.6064 453 0.1135
1.6099 454 0.1034
1.6135 455 0.0566
1.6170 456 0.0707
1.6206 457 0.1564
1.6241 458 0.1602
1.6277 459 0.0149
1.6312 460 0.1243
1.6348 461 0.0579
1.6383 462 0.1693
1.6418 463 0.0911
1.6454 464 0.0278
1.6489 465 0.0315
1.6525 466 0.0176
1.6560 467 0.1197
1.6596 468 0.0162
1.6631 469 0.0492
1.6667 470 0.0495
1.6702 471 0.0318
1.6738 472 0.0703
1.6773 473 0.0175
1.6809 474 0.1457
1.6844 475 0.026
1.6879 476 0.067
1.6915 477 0.0657
1.6950 478 0.1421
1.6986 479 0.0341
1.7021 480 0.022
1.7057 481 0.0641
1.7092 482 0.1315
1.7128 483 0.0328
1.7163 484 0.0489
1.7199 485 0.0199
1.7234 486 0.0475
1.7270 487 0.0662
1.7305 488 0.0133
1.7340 489 0.0081
1.7376 490 0.0356
1.7411 491 0.092
1.7447 492 0.0653
1.7482 493 0.0457
1.7518 494 0.0949
1.7553 495 0.0108
1.7589 496 0.0287
1.7624 497 0.1043
1.7660 498 0.0166
1.7695 499 0.0068
1.7730 500 0.1521
1.7766 501 0.0356
1.7801 502 0.0083
1.7837 503 0.1221
1.7872 504 0.046
1.7908 505 0.0339
1.7943 506 0.021
1.7979 507 0.1706
1.8014 508 0.0176
1.8050 509 0.0275
1.8085 510 0.0521
1.8121 511 0.1083
1.8156 512 0.098
1.8191 513 0.0746
1.8227 514 0.0944
1.8262 515 0.075
1.8298 516 0.0997
1.8333 517 0.0416
1.8369 518 0.154
1.8404 519 0.1534
1.8440 520 0.0387
1.8475 521 0.0957
1.8511 522 0.0136
1.8546 523 0.0426
1.8582 524 0.1499
1.8617 525 0.0111
1.8652 526 0.122
1.8688 527 0.2204
1.8723 528 0.1677
1.8759 529 0.0298
1.8794 530 0.0873
1.8830 531 0.0747
1.8865 532 0.0849
1.8901 533 0.0525
1.8936 534 0.0233
1.8972 535 0.0805
1.9007 536 0.0236
1.9043 537 0.142
1.9078 538 0.0585
1.9113 539 0.0271
1.9149 540 0.1606
1.9184 541 0.2148
1.9220 542 0.0568
1.9255 543 0.0248
1.9291 544 0.0878
1.9326 545 0.0044
1.9362 546 0.0354
1.9397 547 0.0638
1.9433 548 0.1875
1.9468 549 0.031
1.9504 550 0.0547
1.9539 551 0.1292
1.9574 552 0.23
1.9610 553 0.0913
1.9645 554 0.0561
1.9681 555 0.0189
1.9716 556 0.0177
1.9752 557 0.0195
1.9787 558 0.1032
1.9823 559 0.1502
1.9858 560 0.0457
1.9894 561 0.0577
1.9929 562 0.1172
1.9965 563 0.0504
2.0 564 0.0374
2.0035 565 0.1079
2.0071 566 0.0609
2.0106 567 0.0366
2.0142 568 0.0674
2.0177 569 0.1084
2.0213 570 0.066
2.0248 571 0.0102
2.0284 572 0.0876
2.0319 573 0.0407
2.0355 574 0.0581
2.0390 575 0.1215
2.0426 576 0.0068
2.0461 577 0.1015
2.0496 578 0.0047
2.0532 579 0.0925
2.0567 580 0.0836
2.0603 581 0.021
2.0638 582 0.0209
2.0674 583 0.0702
2.0709 584 0.0117
2.0745 585 0.0517
2.0780 586 0.061
2.0816 587 0.0207
2.0851 588 0.034
2.0887 589 0.1045
2.0922 590 0.03
2.0957 591 0.0081
2.0993 592 0.0234
2.1028 593 0.073
2.1064 594 0.0074
2.1099 595 0.0655
2.1135 596 0.079
2.1170 597 0.0358
2.1206 598 0.1006
2.1241 599 0.0624
2.1277 600 0.0479
2.1312 601 0.0105
2.1348 602 0.0448
2.1383 603 0.0305
2.1418 604 0.0432
2.1454 605 0.0771
2.1489 606 0.0545
2.1525 607 0.0299
2.1560 608 0.0712
2.1596 609 0.1006
2.1631 610 0.0117
2.1667 611 0.0462
2.1702 612 0.0576
2.1738 613 0.0696
2.1773 614 0.0685
2.1809 615 0.0596
2.1844 616 0.0127
2.1879 617 0.0089
2.1915 618 0.0135
2.1950 619 0.2405
2.1986 620 0.0212
2.2021 621 0.0637
2.2057 622 0.1356
2.2092 623 0.0943
2.2128 624 0.0147
2.2163 625 0.0038
2.2199 626 0.0624
2.2234 627 0.016
2.2270 628 0.032
2.2305 629 0.0154
2.2340 630 0.0724
2.2376 631 0.008
2.2411 632 0.0877
2.2447 633 0.0228
2.2482 634 0.1929
2.2518 635 0.026
2.2553 636 0.0117
2.2589 637 0.0325
2.2624 638 0.0127
2.2660 639 0.0054
2.2695 640 0.0909
2.2730 641 0.0326
2.2766 642 0.0291
2.2801 643 0.0499
2.2837 644 0.0394
2.2872 645 0.0422
2.2908 646 0.0156
2.2943 647 0.0626
2.2979 648 0.0143
2.3014 649 0.0707
2.3050 650 0.0474
2.3085 651 0.0387
2.3121 652 0.104
2.3156 653 0.0981
2.3191 654 0.0284
2.3227 655 0.0123
2.3262 656 0.1346
2.3298 657 0.0157
2.3333 658 0.1276
2.3369 659 0.0634
2.3404 660 0.0327
2.3440 661 0.0633
2.3475 662 0.0618
2.3511 663 0.0171
2.3546 664 0.141
2.3582 665 0.0626
2.3617 666 0.0149
2.3652 667 0.0455
2.3688 668 0.0507
2.3723 669 0.0492
2.3759 670 0.1528
2.3794 671 0.0484
2.3830 672 0.0826
2.3865 673 0.044
2.3901 674 0.2045
2.3936 675 0.0083
2.3972 676 0.0109
2.4007 677 0.0262
2.4043 678 0.0965
2.4078 679 0.1926
2.4113 680 0.0494
2.4149 681 0.1212
2.4184 682 0.0467
2.4220 683 0.0093
2.4255 684 0.0662
2.4291 685 0.0487
2.4326 686 0.1391
2.4362 687 0.1416
2.4397 688 0.1691
2.4433 689 0.0936
2.4468 690 0.1812
2.4504 691 0.0327
2.4539 692 0.1146
2.4574 693 0.0711
2.4610 694 0.0947
2.4645 695 0.0525
2.4681 696 0.0223
2.4716 697 0.0266
2.4752 698 0.206
2.4787 699 0.0669
2.4823 700 0.0421
2.4858 701 0.0198
2.4894 702 0.0255
2.4929 703 0.008
2.4965 704 0.0183
2.5 705 0.0498
2.5035 706 0.0839
2.5071 707 0.0219
2.5106 708 0.0977
2.5142 709 0.0206
2.5177 710 0.0051
2.5213 711 0.0199
2.5248 712 0.0366
2.5284 713 0.01
2.5319 714 0.1622
2.5355 715 0.0452
2.5390 716 0.0681
2.5426 717 0.0103
2.5461 718 0.0059
2.5496 719 0.0493
2.5532 720 0.016
2.5567 721 0.134
2.5603 722 0.0119
2.5638 723 0.1173
2.5674 724 0.2206
2.5709 725 0.0368
2.5745 726 0.0176
2.5780 727 0.0599
2.5816 728 0.123
2.5851 729 0.0764
2.5887 730 0.0695
2.5922 731 0.0405
2.5957 732 0.012
2.5993 733 0.0469
2.6028 734 0.0142
2.6064 735 0.1236
2.6099 736 0.0194
2.6135 737 0.115
2.6170 738 0.105
2.6206 739 0.0937
2.6241 740 0.1916
2.6277 741 0.0903
2.6312 742 0.1579
2.6348 743 0.0902
2.6383 744 0.0304
2.6418 745 0.0881
2.6454 746 0.0646
2.6489 747 0.0941
2.6525 748 0.0204
2.6560 749 0.1679
2.6596 750 0.028
2.6631 751 0.0205
2.6667 752 0.0307
2.6702 753 0.0365
2.6738 754 0.0141
2.6773 755 0.0212
2.6809 756 0.0447
2.6844 757 0.1072
2.6879 758 0.0332
2.6915 759 0.0513
2.6950 760 0.062
2.6986 761 0.0941
2.7021 762 0.0201
2.7057 763 0.2132
2.7092 764 0.0323
2.7128 765 0.0654
2.7163 766 0.059
2.7199 767 0.1027
2.7234 768 0.0091
2.7270 769 0.0585
2.7305 770 0.0102
2.7340 771 0.0265
2.7376 772 0.0403
2.7411 773 0.0913
2.7447 774 0.0212
2.7482 775 0.0423
2.7518 776 0.083
2.7553 777 0.0073
2.7589 778 0.0815
2.7624 779 0.0786
2.7660 780 0.1079
2.7695 781 0.0477
2.7730 782 0.116
2.7766 783 0.0523
2.7801 784 0.049
2.7837 785 0.0153
2.7872 786 0.0173
2.7908 787 0.0656
2.7943 788 0.0094
2.7979 789 0.0757
2.8014 790 0.0924
2.8050 791 0.0717
2.8085 792 0.011
2.8121 793 0.0312
2.8156 794 0.0188
2.8191 795 0.0244
2.8227 796 0.0138
2.8262 797 0.0956
2.8298 798 0.0125
2.8333 799 0.0196
2.8369 800 0.0766
2.8404 801 0.0105
2.8440 802 0.0347
2.8475 803 0.1152
2.8511 804 0.0745
2.8546 805 0.0275
2.8582 806 0.1096
2.8617 807 0.0571
2.8652 808 0.008
2.8688 809 0.0428
2.8723 810 0.0639
2.8759 811 0.1364
2.8794 812 0.062
2.8830 813 0.0782
2.8865 814 0.0311
2.8901 815 0.1234
2.8936 816 0.0302
2.8972 817 0.0984
2.9007 818 0.0141
2.9043 819 0.1342
2.9078 820 0.0115
2.9113 821 0.0608
2.9149 822 0.0246
2.9184 823 0.0388
2.9220 824 0.0557
2.9255 825 0.011
2.9291 826 0.0262
2.9326 827 0.0655
2.9362 828 0.0843
2.9397 829 0.0549
2.9433 830 0.0791
2.9468 831 0.0254
2.9504 832 0.1365
2.9539 833 0.2078
2.9574 834 0.0485
2.9610 835 0.0309
2.9645 836 0.0974
2.9681 837 0.004
2.9716 838 0.1136
2.9752 839 0.0227
2.9787 840 0.0458
2.9823 841 0.016
2.9858 842 0.1003
2.9894 843 0.0289
2.9929 844 0.0702
2.9965 845 0.055
3.0 846 0.2404

Framework Versions

  • Python: 3.10.14
  • Sentence Transformers: 5.1.1
  • Transformers: 4.56.2
  • PyTorch: 2.8.0+cu128
  • 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
20
Safetensors
Model size
22.7M params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Devy1/MiniLM-cosqa-32

Finetuned
(541)
this model

Collection including Devy1/MiniLM-cosqa-32