Edit model card

SentenceTransformer based on BAAI/bge-m3

This is a sentence-transformers model finetuned from BAAI/bge-m3. 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: BAAI/bge-m3
  • Maximum Sequence Length: 1024 tokens
  • Output Dimensionality: 1024 tokens
  • Similarity Function: Cosine Similarity

Model Sources

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 1024, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, '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': 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("seongil-dn/bge-m3")
# Run inference
sentences = [
    '메이지 유신 시기에 폐번치현이 언제 단행되었나요?',
    "메이지 4년(1871년)2월, 산조 저택에 이와쿠라, 오쿠보, 사이고, 기도, 이타가키등 정부 수뇌가 모여 폐번치현에 대비하여 번의 지휘권에 속하지 않는 천황 직속의 고신베이를 만들 필요가 있다는 의견에 일치. 사쓰마, 조슈, 도사의 세 번에 병사를 두도록 명하여, 8000명의 병사가 급히 조직되었다. 7월 14일 메이지 천황이 전 지사를 고쿄로 불러내어, 폐번치현을 선고하였다. 정부의 예상과는 달리 모든 지사가 찬동하여 염려하였던 저항이나 반항은 전혀 보이지 않았고, 이 날로 '번'은 하나도 남지 않고 일본에서 소멸되었다. 영지를 잃은 ‘다이묘’들은 전원 도쿄로 소집되어, 화족으로써의 책무를 다한 것이 되었다. 이리하여 일본은 하나의 국가, 한사람의 원수의 아래에 근대통일국가로써 시작하게 되었다.",
    '메이지 원년(1868년) 보신 전쟁 때, 미쓰카이치 번은 시바타 번과 행동을 함께 했다. 이듬해 판적봉환이 이루어지면서 노리타다는 미쓰카치이 번지사가 되었고, 메이지 4년(1871년) 7월 14일 폐번치현으로 면직되었다. 미쓰카이치 번도 이때 폐지되어 미쓰카이치 현이 되었다가, 같은해 11월 20일, 니가타현에 편입되었다.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Training Details

Training Hyperparameters

Non-Default Hyperparameters

  • gradient_accumulation_steps: 8
  • learning_rate: 0.0001
  • adam_epsilon: 1e-07
  • num_train_epochs: 1
  • warmup_ratio: 0.1
  • bf16: True
  • dataloader_drop_last: True
  • batch_sampler: no_duplicates

All Hyperparameters

Click to expand
  • overwrite_output_dir: False
  • do_predict: False
  • eval_strategy: no
  • prediction_loss_only: True
  • per_device_train_batch_size: 8
  • per_device_eval_batch_size: 8
  • per_gpu_train_batch_size: None
  • per_gpu_eval_batch_size: None
  • gradient_accumulation_steps: 8
  • eval_accumulation_steps: None
  • torch_empty_cache_steps: None
  • learning_rate: 0.0001
  • weight_decay: 0.0
  • adam_beta1: 0.9
  • adam_beta2: 0.999
  • adam_epsilon: 1e-07
  • 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: True
  • 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: True
  • 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: False
  • hub_always_push: False
  • gradient_checkpointing: False
  • gradient_checkpointing_kwargs: None
  • include_inputs_for_metrics: False
  • 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
  • dispatch_batches: None
  • split_batches: 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
  • eval_use_gather_object: False
  • batch_sampler: no_duplicates
  • multi_dataset_batch_sampler: proportional

Training Logs

Click to expand
Epoch Step Training Loss
0.0018 1 0.9287
0.0035 2 0.8795
0.0053 3 0.7323
0.0071 4 0.8168
0.0088 5 0.8891
0.0106 6 0.8382
0.0124 7 0.751
0.0142 8 0.8765
0.0159 9 0.6881
0.0177 10 0.7446
0.0195 11 0.5825
0.0212 12 0.6931
0.0230 13 0.6806
0.0248 14 0.5909
0.0265 15 0.7772
0.0283 16 0.618
0.0301 17 0.6316
0.0318 18 0.5642
0.0336 19 0.4686
0.0354 20 0.5431
0.0372 21 0.6239
0.0389 22 0.6386
0.0407 23 0.7793
0.0425 24 0.4454
0.0442 25 0.4976
0.0460 26 0.5601
0.0478 27 0.5978
0.0495 28 0.5229
0.0513 29 0.536
0.0531 30 0.5151
0.0548 31 0.6601
0.0566 32 0.7382
0.0584 33 0.4538
0.0602 34 0.4374
0.0619 35 0.5382
0.0637 36 0.6438
0.0655 37 0.6456
0.0672 38 0.4794
0.0690 39 0.5547
0.0708 40 0.5454
0.0725 41 0.6481
0.0743 42 0.4435
0.0761 43 0.5318
0.0778 44 0.6393
0.0796 45 0.5986
0.0814 46 0.5288
0.0831 47 0.4729
0.0849 48 0.5356
0.0867 49 0.5965
0.0885 50 0.5614
0.0902 51 0.4382
0.0920 52 0.5069
0.0938 53 0.4223
0.0955 54 0.5828
0.0973 55 0.6139
0.0991 56 0.6316
0.1008 57 0.4838
0.1026 58 0.4764
0.1044 59 0.4956
0.1061 60 0.5174
0.1079 61 0.6608
0.1097 62 0.6359
0.1115 63 0.6471
0.1132 64 0.5463
0.1150 65 0.4316
0.1168 66 0.5231
0.1185 67 0.4882
0.1203 68 0.5099
0.1221 69 0.6045
0.1238 70 0.6246
0.1256 71 0.4859
0.1274 72 0.5487
0.1291 73 0.6231
0.1309 74 0.5117
0.1327 75 0.5257
0.1345 76 0.634
0.1362 77 0.6379
0.1380 78 0.5938
0.1398 79 0.6219
0.1415 80 0.6745
0.1433 81 0.5874
0.1451 82 0.5805
0.1468 83 0.6183
0.1486 84 0.5967
0.1504 85 0.5625
0.1521 86 0.56
0.1539 87 0.5423
0.1557 88 0.5155
0.1575 89 0.4188
0.1592 90 0.4489
0.1610 91 0.4199
0.1628 92 0.6389
0.1645 93 0.4987
0.1663 94 0.356
0.1681 95 0.645
0.1698 96 0.6058
0.1716 97 0.5401
0.1734 98 0.5984
0.1751 99 0.5249
0.1769 100 0.5264
0.1787 101 0.6159
0.1805 102 0.5916
0.1822 103 0.5023
0.1840 104 0.7227
0.1858 105 0.5136
0.1875 106 0.6373
0.1893 107 0.6511
0.1911 108 0.6405
0.1928 109 0.454
0.1946 110 0.6881
0.1964 111 0.7013
0.1981 112 0.6714
0.1999 113 0.8498
0.2017 114 0.4946
0.2034 115 0.6246
0.2052 116 0.7128
0.2070 117 0.5758
0.2088 118 0.633
0.2105 119 0.5469
0.2123 120 0.5253
0.2141 121 0.5381
0.2158 122 0.5744
0.2176 123 0.4789
0.2194 124 0.5805
0.2211 125 0.6207
0.2229 126 0.5268
0.2247 127 0.6476
0.2264 128 0.5248
0.2282 129 0.3464
0.2300 130 0.4496
0.2318 131 0.6134
0.2335 132 0.5413
0.2353 133 0.5155
0.2371 134 0.5984
0.2388 135 0.6471
0.2406 136 0.5767
0.2424 137 0.4031
0.2441 138 0.4356
0.2459 139 0.4664
0.2477 140 0.7054
0.2494 141 0.4958
0.2512 142 0.5696
0.2530 143 0.5011
0.2548 144 0.5952
0.2565 145 0.4872
0.2583 146 0.5751
0.2601 147 0.6347
0.2618 148 0.6824
0.2636 149 0.531
0.2654 150 0.7025
0.2671 151 0.4048
0.2689 152 0.6253
0.2707 153 0.5461
0.2724 154 0.7396
0.2742 155 0.5136
0.2760 156 0.4704
0.2778 157 0.4535
0.2795 158 0.372
0.2813 159 0.5653
0.2831 160 0.5282
0.2848 161 0.5453
0.2866 162 0.5837
0.2884 163 0.5761
0.2901 164 0.6161
0.2919 165 0.405
0.2937 166 0.6214
0.2954 167 0.411
0.2972 168 0.6529
0.2990 169 0.6642
0.3008 170 0.4985
0.3025 171 0.4257
0.3043 172 0.5372
0.3061 173 0.5431
0.3078 174 0.4973
0.3096 175 0.6549
0.3114 176 0.5224
0.3131 177 0.4476
0.3149 178 0.4718
0.3167 179 0.5344
0.3184 180 0.5656
0.3202 181 0.4768
0.3220 182 0.3768
0.3238 183 0.4206
0.3255 184 0.5402
0.3273 185 0.6454
0.3291 186 0.5776
0.3308 187 0.5703
0.3326 188 0.4107
0.3344 189 0.4764
0.3361 190 0.605
0.3379 191 0.4292
0.3397 192 0.457
0.3414 193 0.4937
0.3432 194 0.51
0.3450 195 0.5098
0.3467 196 0.5767
0.3485 197 0.5132
0.3503 198 0.5998
0.3521 199 0.3802
0.3538 200 0.4518
0.3556 201 0.5625
0.3574 202 0.7021
0.3591 203 0.5112
0.3609 204 0.4492
0.3627 205 0.3903
0.3644 206 0.4139
0.3662 207 0.6053
0.3680 208 0.5281
0.3697 209 0.4487
0.3715 210 0.3983
0.3733 211 0.5477
0.3751 212 0.572
0.3768 213 0.5786
0.3786 214 0.4123
0.3804 215 0.5131
0.3821 216 0.4661
0.3839 217 0.48
0.3857 218 0.5004
0.3874 219 0.5233
0.3892 220 0.4319
0.3910 221 0.4578
0.3927 222 0.5002
0.3945 223 0.6277
0.3963 224 0.4109
0.3981 225 0.6681
0.3998 226 0.3696
0.4016 227 0.6667
0.4034 228 0.5185
0.4051 229 0.5518
0.4069 230 0.4752
0.4087 231 0.4377
0.4104 232 0.5806
0.4122 233 0.4447
0.4140 234 0.5611
0.4157 235 0.6371
0.4175 236 0.6357
0.4193 237 0.483
0.4211 238 0.8846
0.4228 239 0.3929
0.4246 240 0.4226
0.4264 241 0.6122
0.4281 242 0.5454
0.4299 243 0.5696
0.4317 244 0.4731
0.4334 245 0.5638
0.4352 246 0.4026
0.4370 247 0.6631
0.4387 248 0.572
0.4405 249 0.4938
0.4423 250 0.369
0.4441 251 0.4748
0.4458 252 0.5621
0.4476 253 0.5465
0.4494 254 0.4949
0.4511 255 0.3838
0.4529 256 0.6259
0.4547 257 0.4021
0.4564 258 0.5296
0.4582 259 0.3736
0.4600 260 0.6393
0.4617 261 0.4681
0.4635 262 0.5441
0.4653 263 0.4178
0.4670 264 0.4084
0.4688 265 0.4875
0.4706 266 0.589
0.4724 267 0.5376
0.4741 268 0.5175
0.4759 269 0.4991
0.4777 270 0.559
0.4794 271 0.4451
0.4812 272 0.5305
0.4830 273 0.4795
0.4847 274 0.3441
0.4865 275 0.4596
0.4883 276 0.4433
0.4900 277 0.5669
0.4918 278 0.4614
0.4936 279 0.4943
0.4954 280 0.3863
0.4971 281 0.4121
0.4989 282 0.4229
0.5007 283 0.5033
0.5024 284 0.675
0.5042 285 0.5288
0.5060 286 0.4191
0.5077 287 0.5367
0.5095 288 0.5107
0.5113 289 0.4916
0.5130 290 0.4284
0.5148 291 0.5335
0.5166 292 0.5831
0.5184 293 0.4883
0.5201 294 0.4728
0.5219 295 0.5285
0.5237 296 0.4676
0.5254 297 0.6879
0.5272 298 0.5272
0.5290 299 0.5624
0.5307 300 0.5593
0.5325 301 0.4439
0.5343 302 0.4053
0.5360 303 0.4719
0.5378 304 0.4711
0.5396 305 0.4547
0.5414 306 0.5011
0.5431 307 0.4481
0.5449 308 0.408
0.5467 309 0.5667
0.5484 310 0.3552
0.5502 311 0.6648
0.5520 312 0.3842
0.5537 313 0.4724
0.5555 314 0.5586
0.5573 315 0.4365
0.5590 316 0.5099
0.5608 317 0.4732
0.5626 318 0.4542
0.5644 319 0.5091
0.5661 320 0.4554
0.5679 321 0.4214
0.5697 322 0.43
0.5714 323 0.4869
0.5732 324 0.5742
0.5750 325 0.4742
0.5767 326 0.4297
0.5785 327 0.4393
0.5803 328 0.4328
0.5820 329 0.5083
0.5838 330 0.4538
0.5856 331 0.3838
0.5874 332 0.5849
0.5891 333 0.5001
0.5909 334 0.5127
0.5927 335 0.476
0.5944 336 0.4675
0.5962 337 0.3552
0.5980 338 0.6057
0.5997 339 0.32
0.6015 340 0.4914
0.6033 341 0.4509
0.6050 342 0.4392
0.6068 343 0.543
0.6086 344 0.4421
0.6103 345 0.464
0.6121 346 0.6176
0.6139 347 0.3951
0.6157 348 0.4938
0.6174 349 0.4524
0.6192 350 0.4172
0.6210 351 0.5521
0.6227 352 0.3702
0.6245 353 0.3919
0.6263 354 0.5618
0.6280 355 0.4427
0.6298 356 0.4738
0.6316 357 0.6444
0.6333 358 0.5583
0.6351 359 0.4518
0.6369 360 0.4273
0.6387 361 0.5467
0.6404 362 0.5191
0.6422 363 0.4899
0.6440 364 0.4292
0.6457 365 0.514
0.6475 366 0.4397
0.6493 367 0.4591
0.6510 368 0.4554
0.6528 369 0.4312
0.6546 370 0.5847
0.6563 371 0.4237
0.6581 372 0.4889
0.6599 373 0.4684
0.6617 374 0.4797
0.6634 375 0.3599
0.6652 376 0.3451
0.6670 377 0.5332
0.6687 378 0.6504
0.6705 379 0.4116
0.6723 380 0.5084
0.6740 381 0.44
0.6758 382 0.4978
0.6776 383 0.5116
0.6793 384 0.5067
0.6811 385 0.3746
0.6829 386 0.3171
0.6847 387 0.3612
0.6864 388 0.4299
0.6882 389 0.4617
0.6900 390 0.5644
0.6917 391 0.3117
0.6935 392 0.4392
0.6953 393 0.4645
0.6970 394 0.661
0.6988 395 0.4788
0.7006 396 0.3638
0.7023 397 0.4741
0.7041 398 0.4464
0.7059 399 0.5869
0.7077 400 0.434
0.7094 401 0.4735
0.7112 402 0.4239
0.7130 403 0.4081
0.7147 404 0.501
0.7165 405 0.4817
0.7183 406 0.3406
0.7200 407 0.4839
0.7218 408 0.3744
0.7236 409 0.3842
0.7253 410 0.4081
0.7271 411 0.3914
0.7289 412 0.4597
0.7307 413 0.496
0.7324 414 0.2643
0.7342 415 0.5362
0.7360 416 0.2989
0.7377 417 0.3131
0.7395 418 0.4448
0.7413 419 0.5362
0.7430 420 0.3664
0.7448 421 0.5276
0.7466 422 0.3311
0.7483 423 0.3007
0.7501 424 0.4684
0.7519 425 0.4699
0.7536 426 0.3848
0.7554 427 0.3242
0.7572 428 0.3836
0.7590 429 0.4012
0.7607 430 0.5405
0.7625 431 0.4142
0.7643 432 0.3844
0.7660 433 0.2952
0.7678 434 0.5217
0.7696 435 0.486
0.7713 436 0.4244
0.7731 437 0.5105
0.7749 438 0.3892
0.7766 439 0.3699
0.7784 440 0.5893
0.7802 441 0.4628
0.7820 442 0.5032
0.7837 443 0.4953
0.7855 444 0.3133
0.7873 445 0.4575
0.7890 446 0.3201
0.7908 447 0.3212
0.7926 448 0.3756
0.7943 449 0.3449
0.7961 450 0.5293
0.7979 451 0.4334
0.7996 452 0.5617
0.8014 453 0.4368
0.8032 454 0.4581
0.8050 455 0.5356
0.8067 456 0.4242
0.8085 457 0.4365
0.8103 458 0.4116
0.8120 459 0.524
0.8138 460 0.4186
0.8156 461 0.2628
0.8173 462 0.5308
0.8191 463 0.4477
0.8209 464 0.4603
0.8226 465 0.4916
0.8244 466 0.3912
0.8262 467 0.3229
0.8280 468 0.4401
0.8297 469 0.5192
0.8315 470 0.4098
0.8333 471 0.5335
0.8350 472 0.5351
0.8368 473 0.3954
0.8386 474 0.3258
0.8403 475 0.4786
0.8421 476 0.4658
0.8439 477 0.3757
0.8456 478 0.4224
0.8474 479 0.4206
0.8492 480 0.3882
0.8510 481 0.4152
0.8527 482 0.4559
0.8545 483 0.4767
0.8563 484 0.2923
0.8580 485 0.3954
0.8598 486 0.4099
0.8616 487 0.5608
0.8633 488 0.5015
0.8651 489 0.3528
0.8669 490 0.4496
0.8686 491 0.4348
0.8704 492 0.3825
0.8722 493 0.4025
0.8739 494 0.5198
0.8757 495 0.3614
0.8775 496 0.412
0.8793 497 0.5151
0.8810 498 0.5478
0.8828 499 0.387
0.8846 500 0.2864
0.8863 501 0.4617
0.8881 502 0.4682
0.8899 503 0.3962
0.8916 504 0.3429
0.8934 505 0.4239
0.8952 506 0.4094
0.8969 507 0.3582
0.8987 508 0.3192
0.9005 509 0.4337
0.9023 510 0.2739
0.9040 511 0.3407
0.9058 512 0.427
0.9076 513 0.3724
0.9093 514 0.6289
0.9111 515 0.3995
0.9129 516 0.2738
0.9146 517 0.3219
0.9164 518 0.4324
0.9182 519 0.4209
0.9199 520 0.4462
0.9217 521 0.4318
0.9235 522 0.5073
0.9253 523 0.464
0.9270 524 0.4001
0.9288 525 0.3977
0.9306 526 0.5226
0.9323 527 0.3441
0.9341 528 0.5057
0.9359 529 0.5437
0.9376 530 0.4516
0.9394 531 0.347
0.9412 532 0.3971
0.9429 533 0.6176
0.9447 534 0.4616
0.9465 535 0.5525
0.9483 536 0.5172
0.9500 537 0.3715
0.9518 538 0.4075
0.9536 539 0.4067
0.9553 540 0.2413
0.9571 541 0.5025
0.9589 542 0.3473
0.9606 543 0.4071
0.9624 544 0.4812
0.9642 545 0.4871
0.9659 546 0.3069
0.9677 547 0.4824
0.9695 548 0.3028
0.9713 549 0.4561
0.9730 550 0.4598
0.9748 551 0.4712
0.9766 552 0.3909
0.9783 553 0.5058
0.9801 554 0.3624
0.9819 555 0.3914
0.9836 556 0.4798
0.9854 557 0.2983
0.9872 558 0.3628
0.9889 559 0.4062
0.9907 560 0.4956
0.9925 561 0.3459
0.9943 562 0.4157
0.9960 563 0.5642
0.9978 564 0.3373
0.9996 565 0.4446

Framework Versions

  • Python: 3.10.12
  • Sentence Transformers: 3.2.1
  • Transformers: 4.44.2
  • PyTorch: 2.3.1+cu121
  • Accelerate: 1.1.1
  • Datasets: 2.21.0
  • Tokenizers: 0.19.1

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
7
Safetensors
Model size
568M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for seongil-dn/bge-m3

Base model

BAAI/bge-m3
Finetuned
(130)
this model