ostoveland commited on
Commit
dd5fa21
1 Parent(s): 4bb204d

Add new SentenceTransformer model.

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 1024,
3
+ "pooling_mode_cls_token": true,
4
+ "pooling_mode_mean_tokens": false,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
README.md ADDED
@@ -0,0 +1,473 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: BAAI/bge-m3
3
+ datasets: []
4
+ language: []
5
+ library_name: sentence-transformers
6
+ metrics:
7
+ - cosine_accuracy
8
+ - dot_accuracy
9
+ - manhattan_accuracy
10
+ - euclidean_accuracy
11
+ - max_accuracy
12
+ pipeline_tag: sentence-similarity
13
+ tags:
14
+ - sentence-transformers
15
+ - sentence-similarity
16
+ - feature-extraction
17
+ - generated_from_trainer
18
+ - dataset_size:24000
19
+ - loss:TripletLoss
20
+ - loss:MultipleNegativesRankingLoss
21
+ - loss:CoSENTLoss
22
+ widget:
23
+ - source_sentence: Fjerne trapp i mur utvendig
24
+ sentences:
25
+ - 'query: Montere nytt dusjkabinett'
26
+ - 'query: installasjon av beslag på portaldører'
27
+ - 'query: fjerne utvendig trapp i mur'
28
+ - source_sentence: Drenering av hus
29
+ sentences:
30
+ - Grave drenering rundt huset
31
+ - Legge nytt tak
32
+ - Renovere kjeller
33
+ - source_sentence: Montere 9 IKEA Pax garderobeskap med innhold
34
+ sentences:
35
+ - Sette opp IKEA garderobeskap
36
+ - Bygge nytt bad på loftet
37
+ - Montere kjøkkeninnredning
38
+ - source_sentence: Flettverksgjerde
39
+ sentences:
40
+ - Planlegge kjøkkenløsning i nytt hus
41
+ - Galvaniserte gjerdestolper montert i Asker
42
+ - Service på Volvo V70 2004
43
+ - source_sentence: Takoppløft + div oppussing av enebolig
44
+ sentences:
45
+ - Feilsøking av elektriske problemer i huset
46
+ - Støpe fundament til garasje
47
+ - Renovering av enebolig
48
+ model-index:
49
+ - name: SentenceTransformer based on BAAI/bge-m3
50
+ results:
51
+ - task:
52
+ type: triplet
53
+ name: Triplet
54
+ dataset:
55
+ name: test triplet evaluation
56
+ type: test-triplet-evaluation
57
+ metrics:
58
+ - type: cosine_accuracy
59
+ value: 0.9725158562367865
60
+ name: Cosine Accuracy
61
+ - type: dot_accuracy
62
+ value: 0.02748414376321353
63
+ name: Dot Accuracy
64
+ - type: manhattan_accuracy
65
+ value: 0.9725158562367865
66
+ name: Manhattan Accuracy
67
+ - type: euclidean_accuracy
68
+ value: 0.9725158562367865
69
+ name: Euclidean Accuracy
70
+ - type: max_accuracy
71
+ value: 0.9725158562367865
72
+ name: Max Accuracy
73
+ ---
74
+
75
+ # SentenceTransformer based on BAAI/bge-m3
76
+
77
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-m3](https://huggingface.co/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.
78
+
79
+ ## Model Details
80
+
81
+ ### Model Description
82
+ - **Model Type:** Sentence Transformer
83
+ - **Base model:** [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) <!-- at revision babcf60cae0a1f438d7ade582983d4ba462303c2 -->
84
+ - **Maximum Sequence Length:** 8192 tokens
85
+ - **Output Dimensionality:** 1024 tokens
86
+ - **Similarity Function:** Cosine Similarity
87
+ <!-- - **Training Dataset:** Unknown -->
88
+ <!-- - **Language:** Unknown -->
89
+ <!-- - **License:** Unknown -->
90
+
91
+ ### Model Sources
92
+
93
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
94
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
95
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
96
+
97
+ ### Full Model Architecture
98
+
99
+ ```
100
+ SentenceTransformer(
101
+ (0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
102
+ (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})
103
+ (2): Normalize()
104
+ )
105
+ ```
106
+
107
+ ## Usage
108
+
109
+ ### Direct Usage (Sentence Transformers)
110
+
111
+ First install the Sentence Transformers library:
112
+
113
+ ```bash
114
+ pip install -U sentence-transformers
115
+ ```
116
+
117
+ Then you can load this model and run inference.
118
+ ```python
119
+ from sentence_transformers import SentenceTransformer
120
+
121
+ # Download from the 🤗 Hub
122
+ model = SentenceTransformer("ostoveland/test9")
123
+ # Run inference
124
+ sentences = [
125
+ 'Takoppløft + div oppussing av enebolig',
126
+ 'Renovering av enebolig',
127
+ 'Feilsøking av elektriske problemer i huset',
128
+ ]
129
+ embeddings = model.encode(sentences)
130
+ print(embeddings.shape)
131
+ # [3, 1024]
132
+
133
+ # Get the similarity scores for the embeddings
134
+ similarities = model.similarity(embeddings, embeddings)
135
+ print(similarities.shape)
136
+ # [3, 3]
137
+ ```
138
+
139
+ <!--
140
+ ### Direct Usage (Transformers)
141
+
142
+ <details><summary>Click to see the direct usage in Transformers</summary>
143
+
144
+ </details>
145
+ -->
146
+
147
+ <!--
148
+ ### Downstream Usage (Sentence Transformers)
149
+
150
+ You can finetune this model on your own dataset.
151
+
152
+ <details><summary>Click to expand</summary>
153
+
154
+ </details>
155
+ -->
156
+
157
+ <!--
158
+ ### Out-of-Scope Use
159
+
160
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
161
+ -->
162
+
163
+ ## Evaluation
164
+
165
+ ### Metrics
166
+
167
+ #### Triplet
168
+ * Dataset: `test-triplet-evaluation`
169
+ * Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
170
+
171
+ | Metric | Value |
172
+ |:-------------------|:-----------|
173
+ | cosine_accuracy | 0.9725 |
174
+ | dot_accuracy | 0.0275 |
175
+ | manhattan_accuracy | 0.9725 |
176
+ | euclidean_accuracy | 0.9725 |
177
+ | **max_accuracy** | **0.9725** |
178
+
179
+ <!--
180
+ ## Bias, Risks and Limitations
181
+
182
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
183
+ -->
184
+
185
+ <!--
186
+ ### Recommendations
187
+
188
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
189
+ -->
190
+
191
+ ## Training Details
192
+
193
+ ### Training Datasets
194
+
195
+ #### Unnamed Dataset
196
+
197
+
198
+ * Size: 8,000 training samples
199
+ * Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>sentence_2</code>
200
+ * Approximate statistics based on the first 1000 samples:
201
+ | | sentence_0 | sentence_1 | sentence_2 |
202
+ |:--------|:---------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
203
+ | type | string | string | string |
204
+ | details | <ul><li>min: 3 tokens</li><li>mean: 9.81 tokens</li><li>max: 32 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 7.7 tokens</li><li>max: 18 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 7.14 tokens</li><li>max: 31 tokens</li></ul> |
205
+ * Samples:
206
+ | sentence_0 | sentence_1 | sentence_2 |
207
+ |:---------------------------------------------------------------|:------------------------------------------------------|:-----------------------------------------|
208
+ | <code>Varmekabler i gang</code> | <code>Legge varmekabler i entré</code> | <code>Installere gulvvarme i stue</code> |
209
+ | <code>Gulvsliping med lakkering</code> | <code>Slipe og lakke gulv</code> | <code>Legge nytt gulv</code> |
210
+ | <code>Graving til svømmebasseng og rundtliggende område</code> | <code>Grave til svømmebasseng og området rundt</code> | <code>Grave til hagedam</code> |
211
+ * Loss: [<code>TripletLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#tripletloss) with these parameters:
212
+ ```json
213
+ {
214
+ "distance_metric": "TripletDistanceMetric.EUCLIDEAN",
215
+ "triplet_margin": 5
216
+ }
217
+ ```
218
+
219
+ #### Unnamed Dataset
220
+
221
+
222
+ * Size: 8,000 training samples
223
+ * Columns: <code>sentence_0</code> and <code>sentence_1</code>
224
+ * Approximate statistics based on the first 1000 samples:
225
+ | | sentence_0 | sentence_1 |
226
+ |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
227
+ | type | string | string |
228
+ | details | <ul><li>min: 4 tokens</li><li>mean: 9.57 tokens</li><li>max: 35 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 11.8 tokens</li><li>max: 26 tokens</li></ul> |
229
+ * Samples:
230
+ | sentence_0 | sentence_1 |
231
+ |:--------------------------------------------------|:--------------------------------------------------------|
232
+ | <code>Støping av 15,5m2 gulv 75mm tykkelse</code> | <code>query: støpe 15,5m2 gulv med 75mm tykkelse</code> |
233
+ | <code>montere gjerde rundt hagen</code> | <code>query: gjerde rundt hagen</code> |
234
+ | <code>rive gammel garasje</code> | <code>query: fjerning av gammel garasje</code> |
235
+ * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
236
+ ```json
237
+ {
238
+ "scale": 20.0,
239
+ "similarity_fct": "cos_sim"
240
+ }
241
+ ```
242
+
243
+ #### Unnamed Dataset
244
+
245
+
246
+ * Size: 8,000 training samples
247
+ * Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
248
+ * Approximate statistics based on the first 1000 samples:
249
+ | | sentence_0 | sentence_1 | label |
250
+ |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------|
251
+ | type | string | string | float |
252
+ | details | <ul><li>min: 3 tokens</li><li>mean: 10.23 tokens</li><li>max: 48 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 8.12 tokens</li><li>max: 20 tokens</li></ul> | <ul><li>min: 0.05</li><li>mean: 0.5</li><li>max: 0.95</li></ul> |
253
+ * Samples:
254
+ | sentence_0 | sentence_1 | label |
255
+ |:----------------------------------------------------|:-------------------------------------------|:------------------|
256
+ | <code>Utskiftning av vinduer og terassedører</code> | <code>Bytte vinduer og terassedører</code> | <code>0.95</code> |
257
+ | <code>Kjøkkenventilator</code> | <code>Installere kjøkkenapparater</code> | <code>0.35</code> |
258
+ | <code>Speil på treningsrom</code> | <code>Installere speil på bad</code> | <code>0.55</code> |
259
+ * Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
260
+ ```json
261
+ {
262
+ "scale": 20.0,
263
+ "similarity_fct": "pairwise_cos_sim"
264
+ }
265
+ ```
266
+
267
+ ### Training Hyperparameters
268
+ #### Non-Default Hyperparameters
269
+
270
+ - `per_device_train_batch_size`: 32
271
+ - `per_device_eval_batch_size`: 32
272
+ - `num_train_epochs`: 1
273
+ - `multi_dataset_batch_sampler`: round_robin
274
+
275
+ #### All Hyperparameters
276
+ <details><summary>Click to expand</summary>
277
+
278
+ - `overwrite_output_dir`: False
279
+ - `do_predict`: False
280
+ - `eval_strategy`: no
281
+ - `prediction_loss_only`: True
282
+ - `per_device_train_batch_size`: 32
283
+ - `per_device_eval_batch_size`: 32
284
+ - `per_gpu_train_batch_size`: None
285
+ - `per_gpu_eval_batch_size`: None
286
+ - `gradient_accumulation_steps`: 1
287
+ - `eval_accumulation_steps`: None
288
+ - `learning_rate`: 5e-05
289
+ - `weight_decay`: 0.0
290
+ - `adam_beta1`: 0.9
291
+ - `adam_beta2`: 0.999
292
+ - `adam_epsilon`: 1e-08
293
+ - `max_grad_norm`: 1
294
+ - `num_train_epochs`: 1
295
+ - `max_steps`: -1
296
+ - `lr_scheduler_type`: linear
297
+ - `lr_scheduler_kwargs`: {}
298
+ - `warmup_ratio`: 0.0
299
+ - `warmup_steps`: 0
300
+ - `log_level`: passive
301
+ - `log_level_replica`: warning
302
+ - `log_on_each_node`: True
303
+ - `logging_nan_inf_filter`: True
304
+ - `save_safetensors`: True
305
+ - `save_on_each_node`: False
306
+ - `save_only_model`: False
307
+ - `restore_callback_states_from_checkpoint`: False
308
+ - `no_cuda`: False
309
+ - `use_cpu`: False
310
+ - `use_mps_device`: False
311
+ - `seed`: 42
312
+ - `data_seed`: None
313
+ - `jit_mode_eval`: False
314
+ - `use_ipex`: False
315
+ - `bf16`: False
316
+ - `fp16`: False
317
+ - `fp16_opt_level`: O1
318
+ - `half_precision_backend`: auto
319
+ - `bf16_full_eval`: False
320
+ - `fp16_full_eval`: False
321
+ - `tf32`: None
322
+ - `local_rank`: 0
323
+ - `ddp_backend`: None
324
+ - `tpu_num_cores`: None
325
+ - `tpu_metrics_debug`: False
326
+ - `debug`: []
327
+ - `dataloader_drop_last`: False
328
+ - `dataloader_num_workers`: 0
329
+ - `dataloader_prefetch_factor`: None
330
+ - `past_index`: -1
331
+ - `disable_tqdm`: False
332
+ - `remove_unused_columns`: True
333
+ - `label_names`: None
334
+ - `load_best_model_at_end`: False
335
+ - `ignore_data_skip`: False
336
+ - `fsdp`: []
337
+ - `fsdp_min_num_params`: 0
338
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
339
+ - `fsdp_transformer_layer_cls_to_wrap`: None
340
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
341
+ - `deepspeed`: None
342
+ - `label_smoothing_factor`: 0.0
343
+ - `optim`: adamw_torch
344
+ - `optim_args`: None
345
+ - `adafactor`: False
346
+ - `group_by_length`: False
347
+ - `length_column_name`: length
348
+ - `ddp_find_unused_parameters`: None
349
+ - `ddp_bucket_cap_mb`: None
350
+ - `ddp_broadcast_buffers`: False
351
+ - `dataloader_pin_memory`: True
352
+ - `dataloader_persistent_workers`: False
353
+ - `skip_memory_metrics`: True
354
+ - `use_legacy_prediction_loop`: False
355
+ - `push_to_hub`: False
356
+ - `resume_from_checkpoint`: None
357
+ - `hub_model_id`: None
358
+ - `hub_strategy`: every_save
359
+ - `hub_private_repo`: False
360
+ - `hub_always_push`: False
361
+ - `gradient_checkpointing`: False
362
+ - `gradient_checkpointing_kwargs`: None
363
+ - `include_inputs_for_metrics`: False
364
+ - `eval_do_concat_batches`: True
365
+ - `fp16_backend`: auto
366
+ - `push_to_hub_model_id`: None
367
+ - `push_to_hub_organization`: None
368
+ - `mp_parameters`:
369
+ - `auto_find_batch_size`: False
370
+ - `full_determinism`: False
371
+ - `torchdynamo`: None
372
+ - `ray_scope`: last
373
+ - `ddp_timeout`: 1800
374
+ - `torch_compile`: False
375
+ - `torch_compile_backend`: None
376
+ - `torch_compile_mode`: None
377
+ - `dispatch_batches`: None
378
+ - `split_batches`: None
379
+ - `include_tokens_per_second`: False
380
+ - `include_num_input_tokens_seen`: False
381
+ - `neftune_noise_alpha`: None
382
+ - `optim_target_modules`: None
383
+ - `batch_eval_metrics`: False
384
+ - `batch_sampler`: batch_sampler
385
+ - `multi_dataset_batch_sampler`: round_robin
386
+
387
+ </details>
388
+
389
+ ### Training Logs
390
+ | Epoch | Step | Training Loss | test-triplet-evaluation_max_accuracy |
391
+ |:------:|:----:|:-------------:|:------------------------------------:|
392
+ | 0.6667 | 500 | 5.2926 | - |
393
+ | 1.0 | 750 | - | 0.9725 |
394
+
395
+
396
+ ### Framework Versions
397
+ - Python: 3.10.12
398
+ - Sentence Transformers: 3.0.1
399
+ - Transformers: 4.41.2
400
+ - PyTorch: 2.3.0+cu121
401
+ - Accelerate: 0.31.0
402
+ - Datasets: 2.20.0
403
+ - Tokenizers: 0.19.1
404
+
405
+ ## Citation
406
+
407
+ ### BibTeX
408
+
409
+ #### Sentence Transformers
410
+ ```bibtex
411
+ @inproceedings{reimers-2019-sentence-bert,
412
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
413
+ author = "Reimers, Nils and Gurevych, Iryna",
414
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
415
+ month = "11",
416
+ year = "2019",
417
+ publisher = "Association for Computational Linguistics",
418
+ url = "https://arxiv.org/abs/1908.10084",
419
+ }
420
+ ```
421
+
422
+ #### TripletLoss
423
+ ```bibtex
424
+ @misc{hermans2017defense,
425
+ title={In Defense of the Triplet Loss for Person Re-Identification},
426
+ author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
427
+ year={2017},
428
+ eprint={1703.07737},
429
+ archivePrefix={arXiv},
430
+ primaryClass={cs.CV}
431
+ }
432
+ ```
433
+
434
+ #### MultipleNegativesRankingLoss
435
+ ```bibtex
436
+ @misc{henderson2017efficient,
437
+ title={Efficient Natural Language Response Suggestion for Smart Reply},
438
+ 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},
439
+ year={2017},
440
+ eprint={1705.00652},
441
+ archivePrefix={arXiv},
442
+ primaryClass={cs.CL}
443
+ }
444
+ ```
445
+
446
+ #### CoSENTLoss
447
+ ```bibtex
448
+ @online{kexuefm-8847,
449
+ title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
450
+ author={Su Jianlin},
451
+ year={2022},
452
+ month={Jan},
453
+ url={https://kexue.fm/archives/8847},
454
+ }
455
+ ```
456
+
457
+ <!--
458
+ ## Glossary
459
+
460
+ *Clearly define terms in order to be accessible across audiences.*
461
+ -->
462
+
463
+ <!--
464
+ ## Model Card Authors
465
+
466
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
467
+ -->
468
+
469
+ <!--
470
+ ## Model Card Contact
471
+
472
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
473
+ -->
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "BAAI/bge-m3",
3
+ "architectures": [
4
+ "XLMRobertaModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 8194,
17
+ "model_type": "xlm-roberta",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 24,
20
+ "output_past": true,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.41.2",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 250002
28
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.0.1",
4
+ "transformers": "4.41.2",
5
+ "pytorch": "2.3.0+cu121"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": null
10
+ }
modules.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ },
14
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_Normalize",
18
+ "type": "sentence_transformers.models.Normalize"
19
+ }
20
+ ]
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cd2864ce4ac05dcd5c7b429b4748a473cd755e066d301d6e2b73237920a24b8
3
+ size 2271151270
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 8192,
3
+ "do_lower_case": false
4
+ }
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4f7e21bec3fb0044ca0bb2d50eb5d4d8c596273c422baef84466d2c73748b9c
3
+ size 17083053
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 8192,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "sp_model_kwargs": {},
53
+ "tokenizer_class": "XLMRobertaTokenizer",
54
+ "unk_token": "<unk>"
55
+ }