Hugging Face's logo

wwydmanski
/
bge-m3-retromae-pubmed-v0.1

Sentence Similarity
sentence-transformers
Safetensors
xlm-roberta
feature-extraction
Generated from Trainer
dataset_size:15182
loss:MultipleNegativesRankingLoss
Eval Results
text-embeddings-inference
Inference Endpoints
Model card Files Community
wwydmanski commited on
Commit
72161f1
·
verified ·
1 Parent(s): 54af8dc

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. .gitattributes +1 -0
  2. 1_Pooling/config.json +10 -0
  3. README.md +710 -0
  4. config.json +28 -0
  5. config_sentence_transformers.json +10 -0
  6. model.safetensors +3 -0
  7. modules.json +14 -0
  8. sentence_bert_config.json +4 -0
  9. sentencepiece.bpe.model +3 -0
  10. special_tokens_map.json +51 -0
  11. tokenizer.json +3 -0
  12. tokenizer_config.json +54 -0
.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": false,
4
+ "pooling_mode_mean_tokens": true,
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 +1,710 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - sentence-transformers
4
+ - sentence-similarity
5
+ - feature-extraction
6
+ - generated_from_trainer
7
+ - dataset_size:15182
8
+ - loss:MultipleNegativesRankingLoss
9
+ base_model: BAAI/bge-m3-retromae
10
+ widget:
11
+ - source_sentence: Carditis in pediatric patients following foreign serum administration
12
+ sentences:
13
+ - 'Four cases of carditis occurring in children and associated with the administration
14
+ of a foreign serum. '
15
+ - 'Understanding Positive Youth Development in Sport Through the Voices of Indigenous
16
+ Youth. '
17
+ - 'Pericarditis in children. '
18
+ - source_sentence: Concept Synthesis
19
+ sentences:
20
+ - 'Centeredness in Healthcare: A Concept Synthesis of Family-centered Care, Person-centered
21
+ Care and Child-centered Care. '
22
+ - 'The Power in Concept Mapping! '
23
+ - 'Using propensity scores to estimate the cost-effectiveness of medical therapies. '
24
+ - source_sentence: Visual Pathway Mapping
25
+ sentences:
26
+ - 'The visual connection. '
27
+ - 'The "tobacco issue". '
28
+ - 'Elaboration of the Visual Pathways from the Study of War-Related Cranial Injuries:
29
+ The Period from the Russo-Japanese War to World War I. '
30
+ - source_sentence: Cerebral Aneurysm Thrombosis
31
+ sentences:
32
+ - '[A case of spontaneous thrombosis of a cerebral arteriovenous aneurysm]. '
33
+ - 'Cerebral Sinus Thrombosis. '
34
+ - 'Good clinical practice (GCP) standards: clinical trials in India. An interview
35
+ with Dr. Urmila Thatte, Head of Clinical Pharmacology, TN Medical College & BYL
36
+ Nair Hospital. Interview by Viveka Roychowdhury. '
37
+ - source_sentence: Calcineurin inhibitor-sparing regimen
38
+ sentences:
39
+ - 'Belatacept-based immunosuppression: A calcineurin inhibitor-sparing regimen in
40
+ heart transplant recipients. '
41
+ - 'The Outcomes of Cemented Femoral Revisions for Periprosthetic Femoral Fractures
42
+ in the Elderly: Comparison with Cementless Stems. '
43
+ - 'Neurotoxicity of calcineurin inhibitors: impact and clinical management. '
44
+ pipeline_tag: sentence-similarity
45
+ library_name: sentence-transformers
46
+ metrics:
47
+ - cosine_accuracy
48
+ model-index:
49
+ - name: SentenceTransformer based on BAAI/bge-m3-retromae
50
+ results:
51
+ - task:
52
+ type: triplet
53
+ name: Triplet
54
+ dataset:
55
+ name: triplet dev
56
+ type: triplet-dev
57
+ metrics:
58
+ - type: cosine_accuracy
59
+ value: 0.723
60
+ name: Cosine Accuracy
61
+ ---
62
+
63
+ # SentenceTransformer based on BAAI/bge-m3-retromae
64
+
65
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-m3-retromae](https://huggingface.co/BAAI/bge-m3-retromae) on the json dataset. 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.
66
+
67
+ ## Model Details
68
+
69
+ ### Model Description
70
+ - **Model Type:** Sentence Transformer
71
+ - **Base model:** [BAAI/bge-m3-retromae](https://huggingface.co/BAAI/bge-m3-retromae) <!-- at revision 95c4f81ef8f7911dcac8e384532489c32c8dea64 -->
72
+ - **Maximum Sequence Length:** 8192 tokens
73
+ - **Output Dimensionality:** 1024 dimensions
74
+ - **Similarity Function:** Cosine Similarity
75
+ - **Training Dataset:**
76
+ - json
77
+ <!-- - **Language:** Unknown -->
78
+ <!-- - **License:** Unknown -->
79
+
80
+ ### Model Sources
81
+
82
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
83
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
84
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
85
+
86
+ ### Full Model Architecture
87
+
88
+ ```
89
+ SentenceTransformer(
90
+ (0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: PeftModelForFeatureExtraction
91
+ (1): Pooling({'word_embedding_dimension': 1024, '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})
92
+ )
93
+ ```
94
+
95
+ ## Usage
96
+
97
+ ### Direct Usage (Sentence Transformers)
98
+
99
+ First install the Sentence Transformers library:
100
+
101
+ ```bash
102
+ pip install -U sentence-transformers
103
+ ```
104
+
105
+ Then you can load this model and run inference.
106
+ ```python
107
+ from sentence_transformers import SentenceTransformer
108
+
109
+ # Download from the 🤗 Hub
110
+ model = SentenceTransformer("sentence_transformers_model_id")
111
+ # Run inference
112
+ sentences = [
113
+ 'Calcineurin inhibitor-sparing regimen',
114
+ 'Belatacept-based immunosuppression: A calcineurin inhibitor-sparing regimen in heart transplant recipients. ',
115
+ 'Neurotoxicity of calcineurin inhibitors: impact and clinical management. ',
116
+ ]
117
+ embeddings = model.encode(sentences)
118
+ print(embeddings.shape)
119
+ # [3, 1024]
120
+
121
+ # Get the similarity scores for the embeddings
122
+ similarities = model.similarity(embeddings, embeddings)
123
+ print(similarities.shape)
124
+ # [3, 3]
125
+ ```
126
+
127
+ <!--
128
+ ### Direct Usage (Transformers)
129
+
130
+ <details><summary>Click to see the direct usage in Transformers</summary>
131
+
132
+ </details>
133
+ -->
134
+
135
+ <!--
136
+ ### Downstream Usage (Sentence Transformers)
137
+
138
+ You can finetune this model on your own dataset.
139
+
140
+ <details><summary>Click to expand</summary>
141
+
142
+ </details>
143
+ -->
144
+
145
+ <!--
146
+ ### Out-of-Scope Use
147
+
148
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
149
+ -->
150
+
151
+ ## Evaluation
152
+
153
+ ### Metrics
154
+
155
+ #### Triplet
156
+
157
+ * Dataset: `triplet-dev`
158
+ * Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
159
+
160
+ | Metric | Value |
161
+ |:--------------------|:----------|
162
+ | **cosine_accuracy** | **0.723** |
163
+
164
+ <!--
165
+ ## Bias, Risks and Limitations
166
+
167
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
168
+ -->
169
+
170
+ <!--
171
+ ### Recommendations
172
+
173
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
174
+ -->
175
+
176
+ ## Training Details
177
+
178
+ ### Training Dataset
179
+
180
+ #### json
181
+
182
+ * Dataset: json
183
+ * Size: 15,182 training samples
184
+ * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
185
+ * Approximate statistics based on the first 1000 samples:
186
+ | | anchor | positive | negative |
187
+ |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
188
+ | type | string | string | string |
189
+ | details | <ul><li>min: 4 tokens</li><li>mean: 10.68 tokens</li><li>max: 49 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 26.34 tokens</li><li>max: 79 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 15.75 tokens</li><li>max: 66 tokens</li></ul> |
190
+ * Samples:
191
+ | anchor | positive | negative |
192
+ |:--------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------|
193
+ | <code>Immunogenetic polymorphism</code> | <code>Immunogenetic polymorphism and disease mechanisms in juvenile chronic arthritis. </code> | <code>Immunogenetic model. </code> |
194
+ | <code>Alemtuzumab-induced pancolitis</code> | <code>Pancolitis a novel early complication of Alemtuzumab for MS treatment. </code> | <code>Alemtuzumab in lymphoproliferate disorders. </code> |
195
+ | <code>Intermittent infectiousness</code> | <code>Understanding the effects of intermittent shedding on the transmission of infectious diseases: example of salmonellosis in pigs. </code> | <code>Infectious behaviour. </code> |
196
+ * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
197
+ ```json
198
+ {
199
+ "scale": 20.0,
200
+ "similarity_fct": "cos_sim"
201
+ }
202
+ ```
203
+
204
+ ### Training Hyperparameters
205
+ #### Non-Default Hyperparameters
206
+
207
+ - `eval_strategy`: steps
208
+ - `per_device_train_batch_size`: 32
209
+ - `per_device_eval_batch_size`: 32
210
+ - `num_train_epochs`: 1
211
+ - `lr_scheduler_type`: cosine_with_restarts
212
+ - `warmup_ratio`: 0.1
213
+ - `bf16`: True
214
+ - `batch_sampler`: no_duplicates
215
+
216
+ #### All Hyperparameters
217
+ <details><summary>Click to expand</summary>
218
+
219
+ - `overwrite_output_dir`: False
220
+ - `do_predict`: False
221
+ - `eval_strategy`: steps
222
+ - `prediction_loss_only`: True
223
+ - `per_device_train_batch_size`: 32
224
+ - `per_device_eval_batch_size`: 32
225
+ - `per_gpu_train_batch_size`: None
226
+ - `per_gpu_eval_batch_size`: None
227
+ - `gradient_accumulation_steps`: 1
228
+ - `eval_accumulation_steps`: None
229
+ - `torch_empty_cache_steps`: None
230
+ - `learning_rate`: 5e-05
231
+ - `weight_decay`: 0.0
232
+ - `adam_beta1`: 0.9
233
+ - `adam_beta2`: 0.999
234
+ - `adam_epsilon`: 1e-08
235
+ - `max_grad_norm`: 1.0
236
+ - `num_train_epochs`: 1
237
+ - `max_steps`: -1
238
+ - `lr_scheduler_type`: cosine_with_restarts
239
+ - `lr_scheduler_kwargs`: {}
240
+ - `warmup_ratio`: 0.1
241
+ - `warmup_steps`: 0
242
+ - `log_level`: passive
243
+ - `log_level_replica`: warning
244
+ - `log_on_each_node`: True
245
+ - `logging_nan_inf_filter`: True
246
+ - `save_safetensors`: True
247
+ - `save_on_each_node`: False
248
+ - `save_only_model`: False
249
+ - `restore_callback_states_from_checkpoint`: False
250
+ - `no_cuda`: False
251
+ - `use_cpu`: False
252
+ - `use_mps_device`: False
253
+ - `seed`: 42
254
+ - `data_seed`: None
255
+ - `jit_mode_eval`: False
256
+ - `use_ipex`: False
257
+ - `bf16`: True
258
+ - `fp16`: False
259
+ - `fp16_opt_level`: O1
260
+ - `half_precision_backend`: auto
261
+ - `bf16_full_eval`: False
262
+ - `fp16_full_eval`: False
263
+ - `tf32`: None
264
+ - `local_rank`: 0
265
+ - `ddp_backend`: None
266
+ - `tpu_num_cores`: None
267
+ - `tpu_metrics_debug`: False
268
+ - `debug`: []
269
+ - `dataloader_drop_last`: False
270
+ - `dataloader_num_workers`: 0
271
+ - `dataloader_prefetch_factor`: None
272
+ - `past_index`: -1
273
+ - `disable_tqdm`: False
274
+ - `remove_unused_columns`: True
275
+ - `label_names`: None
276
+ - `load_best_model_at_end`: False
277
+ - `ignore_data_skip`: False
278
+ - `fsdp`: []
279
+ - `fsdp_min_num_params`: 0
280
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
281
+ - `fsdp_transformer_layer_cls_to_wrap`: None
282
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
283
+ - `deepspeed`: None
284
+ - `label_smoothing_factor`: 0.0
285
+ - `optim`: adamw_torch
286
+ - `optim_args`: None
287
+ - `adafactor`: False
288
+ - `group_by_length`: False
289
+ - `length_column_name`: length
290
+ - `ddp_find_unused_parameters`: None
291
+ - `ddp_bucket_cap_mb`: None
292
+ - `ddp_broadcast_buffers`: False
293
+ - `dataloader_pin_memory`: True
294
+ - `dataloader_persistent_workers`: False
295
+ - `skip_memory_metrics`: True
296
+ - `use_legacy_prediction_loop`: False
297
+ - `push_to_hub`: False
298
+ - `resume_from_checkpoint`: None
299
+ - `hub_model_id`: None
300
+ - `hub_strategy`: every_save
301
+ - `hub_private_repo`: False
302
+ - `hub_always_push`: False
303
+ - `gradient_checkpointing`: False
304
+ - `gradient_checkpointing_kwargs`: None
305
+ - `include_inputs_for_metrics`: False
306
+ - `eval_do_concat_batches`: True
307
+ - `fp16_backend`: auto
308
+ - `push_to_hub_model_id`: None
309
+ - `push_to_hub_organization`: None
310
+ - `mp_parameters`:
311
+ - `auto_find_batch_size`: False
312
+ - `full_determinism`: False
313
+ - `torchdynamo`: None
314
+ - `ray_scope`: last
315
+ - `ddp_timeout`: 1800
316
+ - `torch_compile`: False
317
+ - `torch_compile_backend`: None
318
+ - `torch_compile_mode`: None
319
+ - `dispatch_batches`: None
320
+ - `split_batches`: None
321
+ - `include_tokens_per_second`: False
322
+ - `include_num_input_tokens_seen`: False
323
+ - `neftune_noise_alpha`: None
324
+ - `optim_target_modules`: None
325
+ - `batch_eval_metrics`: False
326
+ - `eval_on_start`: False
327
+ - `eval_use_gather_object`: False
328
+ - `prompts`: None
329
+ - `batch_sampler`: no_duplicates
330
+ - `multi_dataset_batch_sampler`: proportional
331
+
332
+ </details>
333
+
334
+ ### Training Logs
335
+ <details><summary>Click to expand</summary>
336
+
337
+ | Epoch | Step | Training Loss | triplet-dev_cosine_accuracy |
338
+ |:------:|:----:|:-------------:|:---------------------------:|
339
+ | 0 | 0 | - | 0.543 |
340
+ | 0.0032 | 1 | 3.4406 | - |
341
+ | 0.0064 | 2 | 3.2403 | - |
342
+ | 0.0096 | 3 | 3.3734 | - |
343
+ | 0.0128 | 4 | 3.3858 | - |
344
+ | 0.0160 | 5 | 3.3195 | - |
345
+ | 0.0192 | 6 | 3.2708 | - |
346
+ | 0.0224 | 7 | 3.4507 | - |
347
+ | 0.0256 | 8 | 3.4782 | - |
348
+ | 0.0288 | 9 | 3.2926 | - |
349
+ | 0.0319 | 10 | 3.2744 | - |
350
+ | 0.0351 | 11 | 3.4455 | - |
351
+ | 0.0383 | 12 | 3.3225 | - |
352
+ | 0.0415 | 13 | 3.3568 | - |
353
+ | 0.0447 | 14 | 3.3349 | - |
354
+ | 0.0479 | 15 | 3.2672 | - |
355
+ | 0.0511 | 16 | 3.2584 | - |
356
+ | 0.0543 | 17 | 3.1607 | - |
357
+ | 0.0575 | 18 | 3.1793 | - |
358
+ | 0.0607 | 19 | 3.1924 | - |
359
+ | 0.0639 | 20 | 3.2913 | - |
360
+ | 0.0671 | 21 | 3.2028 | - |
361
+ | 0.0703 | 22 | 3.1448 | - |
362
+ | 0.0735 | 23 | 3.0991 | - |
363
+ | 0.0767 | 24 | 3.1371 | - |
364
+ | 0.0799 | 25 | 3.0089 | - |
365
+ | 0.0831 | 26 | 3.1232 | - |
366
+ | 0.0863 | 27 | 2.8794 | - |
367
+ | 0.0895 | 28 | 2.982 | - |
368
+ | 0.0927 | 29 | 3.231 | - |
369
+ | 0.0958 | 30 | 2.9288 | - |
370
+ | 0.0990 | 31 | 3.0117 | - |
371
+ | 0.1022 | 32 | 2.8717 | - |
372
+ | 0.1054 | 33 | 2.7002 | - |
373
+ | 0.1086 | 34 | 2.6395 | - |
374
+ | 0.1118 | 35 | 2.5087 | - |
375
+ | 0.1150 | 36 | 2.7469 | - |
376
+ | 0.1182 | 37 | 2.6306 | - |
377
+ | 0.1214 | 38 | 2.1149 | - |
378
+ | 0.1246 | 39 | 2.5591 | - |
379
+ | 0.1278 | 40 | 2.0133 | - |
380
+ | 0.1310 | 41 | 2.2863 | - |
381
+ | 0.1342 | 42 | 2.2592 | - |
382
+ | 0.1374 | 43 | 2.1261 | - |
383
+ | 0.1406 | 44 | 2.278 | - |
384
+ | 0.1438 | 45 | 1.7339 | - |
385
+ | 0.1470 | 46 | 1.8337 | - |
386
+ | 0.1502 | 47 | 1.5944 | - |
387
+ | 0.1534 | 48 | 2.0899 | - |
388
+ | 0.1565 | 49 | 1.509 | - |
389
+ | 0.1597 | 50 | 1.8651 | - |
390
+ | 0.1629 | 51 | 2.2858 | - |
391
+ | 0.1661 | 52 | 2.6881 | - |
392
+ | 0.1693 | 53 | 1.7877 | - |
393
+ | 0.1725 | 54 | 1.6374 | - |
394
+ | 0.1757 | 55 | 2.0763 | - |
395
+ | 0.1789 | 56 | 1.7672 | - |
396
+ | 0.1821 | 57 | 1.7913 | - |
397
+ | 0.1853 | 58 | 1.8524 | - |
398
+ | 0.1885 | 59 | 2.2614 | - |
399
+ | 0.1917 | 60 | 1.8058 | - |
400
+ | 0.1949 | 61 | 2.0403 | - |
401
+ | 0.1981 | 62 | 1.2697 | - |
402
+ | 0.2013 | 63 | 1.9523 | - |
403
+ | 0.2045 | 64 | 1.3965 | - |
404
+ | 0.2077 | 65 | 1.5501 | - |
405
+ | 0.2109 | 66 | 1.0785 | - |
406
+ | 0.2141 | 67 | 1.721 | - |
407
+ | 0.2173 | 68 | 1.9049 | - |
408
+ | 0.2204 | 69 | 1.4317 | - |
409
+ | 0.2236 | 70 | 1.905 | - |
410
+ | 0.2268 | 71 | 1.236 | - |
411
+ | 0.2300 | 72 | 1.7312 | - |
412
+ | 0.2332 | 73 | 0.9951 | - |
413
+ | 0.2364 | 74 | 1.5471 | - |
414
+ | 0.2396 | 75 | 1.1289 | - |
415
+ | 0.2428 | 76 | 1.7902 | - |
416
+ | 0.2460 | 77 | 1.2619 | - |
417
+ | 0.2492 | 78 | 1.0043 | - |
418
+ | 0.2524 | 79 | 1.7546 | - |
419
+ | 0.2556 | 80 | 1.8505 | - |
420
+ | 0.2588 | 81 | 1.7437 | - |
421
+ | 0.2620 | 82 | 1.2788 | - |
422
+ | 0.2652 | 83 | 1.438 | - |
423
+ | 0.2684 | 84 | 1.5399 | - |
424
+ | 0.2716 | 85 | 2.1841 | - |
425
+ | 0.2748 | 86 | 1.6834 | - |
426
+ | 0.2780 | 87 | 1.3842 | - |
427
+ | 0.2812 | 88 | 1.619 | - |
428
+ | 0.2843 | 89 | 1.2492 | - |
429
+ | 0.2875 | 90 | 1.3613 | - |
430
+ | 0.2907 | 91 | 1.2457 | - |
431
+ | 0.2939 | 92 | 1.2966 | - |
432
+ | 0.2971 | 93 | 1.3718 | - |
433
+ | 0.3003 | 94 | 1.3675 | - |
434
+ | 0.3035 | 95 | 2.1095 | - |
435
+ | 0.3067 | 96 | 1.6177 | - |
436
+ | 0.3099 | 97 | 1.3287 | - |
437
+ | 0.3131 | 98 | 1.9805 | - |
438
+ | 0.3163 | 99 | 1.3861 | - |
439
+ | 0.3195 | 100 | 1.8392 | 0.622 |
440
+ | 0.3227 | 101 | 1.4698 | - |
441
+ | 0.3259 | 102 | 1.4499 | - |
442
+ | 0.3291 | 103 | 1.5338 | - |
443
+ | 0.3323 | 104 | 1.3867 | - |
444
+ | 0.3355 | 105 | 1.7414 | - |
445
+ | 0.3387 | 106 | 1.5203 | - |
446
+ | 0.3419 | 107 | 1.6059 | - |
447
+ | 0.3450 | 108 | 1.3799 | - |
448
+ | 0.3482 | 109 | 1.5004 | - |
449
+ | 0.3514 | 110 | 1.0175 | - |
450
+ | 0.3546 | 111 | 1.0399 | - |
451
+ | 0.3578 | 112 | 1.6369 | - |
452
+ | 0.3610 | 113 | 1.5692 | - |
453
+ | 0.3642 | 114 | 1.6808 | - |
454
+ | 0.3674 | 115 | 1.4315 | - |
455
+ | 0.3706 | 116 | 0.9854 | - |
456
+ | 0.3738 | 117 | 1.3637 | - |
457
+ | 0.3770 | 118 | 1.3986 | - |
458
+ | 0.3802 | 119 | 1.3848 | - |
459
+ | 0.3834 | 120 | 1.4436 | - |
460
+ | 0.3866 | 121 | 1.0704 | - |
461
+ | 0.3898 | 122 | 1.3788 | - |
462
+ | 0.3930 | 123 | 1.7131 | - |
463
+ | 0.3962 | 124 | 1.5013 | - |
464
+ | 0.3994 | 125 | 1.7377 | - |
465
+ | 0.4026 | 126 | 2.0296 | - |
466
+ | 0.4058 | 127 | 1.2643 | - |
467
+ | 0.4089 | 128 | 1.3647 | - |
468
+ | 0.4121 | 129 | 1.175 | - |
469
+ | 0.4153 | 130 | 1.0797 | - |
470
+ | 0.4185 | 131 | 1.5746 | - |
471
+ | 0.4217 | 132 | 1.0914 | - |
472
+ | 0.4249 | 133 | 1.6672 | - |
473
+ | 0.4281 | 134 | 1.2959 | - |
474
+ | 0.4313 | 135 | 1.5387 | - |
475
+ | 0.4345 | 136 | 1.2571 | - |
476
+ | 0.4377 | 137 | 1.42 | - |
477
+ | 0.4409 | 138 | 1.3452 | - |
478
+ | 0.4441 | 139 | 1.2238 | - |
479
+ | 0.4473 | 140 | 0.9963 | - |
480
+ | 0.4505 | 141 | 1.0326 | - |
481
+ | 0.4537 | 142 | 0.8793 | - |
482
+ | 0.4569 | 143 | 1.2197 | - |
483
+ | 0.4601 | 144 | 1.2992 | - |
484
+ | 0.4633 | 145 | 1.1456 | - |
485
+ | 0.4665 | 146 | 1.6002 | - |
486
+ | 0.4696 | 147 | 1.54 | - |
487
+ | 0.4728 | 148 | 1.2323 | - |
488
+ | 0.4760 | 149 | 1.0184 | - |
489
+ | 0.4792 | 150 | 1.2416 | - |
490
+ | 0.4824 | 151 | 1.1777 | - |
491
+ | 0.4856 | 152 | 1.0964 | - |
492
+ | 0.4888 | 153 | 1.0828 | - |
493
+ | 0.4920 | 154 | 1.3446 | - |
494
+ | 0.4952 | 155 | 0.9454 | - |
495
+ | 0.4984 | 156 | 0.7719 | - |
496
+ | 0.5016 | 157 | 1.003 | - |
497
+ | 0.5048 | 158 | 0.9863 | - |
498
+ | 0.5080 | 159 | 0.9672 | - |
499
+ | 0.5112 | 160 | 1.1432 | - |
500
+ | 0.5144 | 161 | 1.0377 | - |
501
+ | 0.5176 | 162 | 1.102 | - |
502
+ | 0.5208 | 163 | 0.9345 | - |
503
+ | 0.5240 | 164 | 0.9486 | - |
504
+ | 0.5272 | 165 | 1.5389 | - |
505
+ | 0.5304 | 166 | 1.8956 | - |
506
+ | 0.5335 | 167 | 1.0425 | - |
507
+ | 0.5367 | 168 | 1.5296 | - |
508
+ | 0.5399 | 169 | 0.9602 | - |
509
+ | 0.5431 | 170 | 0.9832 | - |
510
+ | 0.5463 | 171 | 1.0982 | - |
511
+ | 0.5495 | 172 | 1.6295 | - |
512
+ | 0.5527 | 173 | 1.3986 | - |
513
+ | 0.5559 | 174 | 1.1721 | - |
514
+ | 0.5591 | 175 | 0.7994 | - |
515
+ | 0.5623 | 176 | 1.5655 | - |
516
+ | 0.5655 | 177 | 1.2068 | - |
517
+ | 0.5687 | 178 | 1.2747 | - |
518
+ | 0.5719 | 179 | 1.0729 | - |
519
+ | 0.5751 | 180 | 0.9977 | - |
520
+ | 0.5783 | 181 | 1.3537 | - |
521
+ | 0.5815 | 182 | 1.0964 | - |
522
+ | 0.5847 | 183 | 0.8029 | - |
523
+ | 0.5879 | 184 | 0.765 | - |
524
+ | 0.5911 | 185 | 1.0457 | - |
525
+ | 0.5942 | 186 | 1.2928 | - |
526
+ | 0.5974 | 187 | 1.2354 | - |
527
+ | 0.6006 | 188 | 1.031 | - |
528
+ | 0.6038 | 189 | 1.2561 | - |
529
+ | 0.6070 | 190 | 1.1676 | - |
530
+ | 0.6102 | 191 | 1.2186 | - |
531
+ | 0.6134 | 192 | 1.1786 | - |
532
+ | 0.6166 | 193 | 1.283 | - |
533
+ | 0.6198 | 194 | 0.8316 | - |
534
+ | 0.6230 | 195 | 1.2239 | - |
535
+ | 0.6262 | 196 | 1.08 | - |
536
+ | 0.6294 | 197 | 1.7637 | - |
537
+ | 0.6326 | 198 | 1.2315 | - |
538
+ | 0.6358 | 199 | 1.5375 | - |
539
+ | 0.6390 | 200 | 1.4388 | 0.73 |
540
+ | 0.6422 | 201 | 1.3918 | - |
541
+ | 0.6454 | 202 | 1.37 | - |
542
+ | 0.6486 | 203 | 1.3753 | - |
543
+ | 0.6518 | 204 | 1.137 | - |
544
+ | 0.6550 | 205 | 1.4457 | - |
545
+ | 0.6581 | 206 | 1.3072 | - |
546
+ | 0.6613 | 207 | 2.0953 | - |
547
+ | 0.6645 | 208 | 1.6811 | - |
548
+ | 0.6677 | 209 | 0.9206 | - |
549
+ | 0.6709 | 210 | 0.9801 | - |
550
+ | 0.6741 | 211 | 0.961 | - |
551
+ | 0.6773 | 212 | 1.386 | - |
552
+ | 0.6805 | 213 | 1.5354 | - |
553
+ | 0.6837 | 214 | 0.6571 | - |
554
+ | 0.6869 | 215 | 1.2631 | - |
555
+ | 0.6901 | 216 | 1.2122 | - |
556
+ | 0.6933 | 217 | 1.6253 | - |
557
+ | 0.6965 | 218 | 1.266 | - |
558
+ | 0.6997 | 219 | 1.7445 | - |
559
+ | 0.7029 | 220 | 1.1527 | - |
560
+ | 0.7061 | 221 | 1.7681 | - |
561
+ | 0.7093 | 222 | 1.4941 | - |
562
+ | 0.7125 | 223 | 1.8236 | - |
563
+ | 0.7157 | 224 | 1.4117 | - |
564
+ | 0.7188 | 225 | 0.7363 | - |
565
+ | 0.7220 | 226 | 1.4519 | - |
566
+ | 0.7252 | 227 | 1.4138 | - |
567
+ | 0.7284 | 228 | 1.0758 | - |
568
+ | 0.7316 | 229 | 1.6275 | - |
569
+ | 0.7348 | 230 | 1.6303 | - |
570
+ | 0.7380 | 231 | 1.4706 | - |
571
+ | 0.7412 | 232 | 0.5958 | - |
572
+ | 0.7444 | 233 | 1.2442 | - |
573
+ | 0.7476 | 234 | 1.3782 | - |
574
+ | 0.7508 | 235 | 1.3971 | - |
575
+ | 0.7540 | 236 | 1.3412 | - |
576
+ | 0.7572 | 237 | 0.9017 | - |
577
+ | 0.7604 | 238 | 1.6336 | - |
578
+ | 0.7636 | 239 | 1.2652 | - |
579
+ | 0.7668 | 240 | 1.0598 | - |
580
+ | 0.7700 | 241 | 1.3082 | - |
581
+ | 0.7732 | 242 | 0.9677 | - |
582
+ | 0.7764 | 243 | 1.2684 | - |
583
+ | 0.7796 | 244 | 1.3539 | - |
584
+ | 0.7827 | 245 | 1.7301 | - |
585
+ | 0.7859 | 246 | 1.2539 | - |
586
+ | 0.7891 | 247 | 1.1073 | - |
587
+ | 0.7923 | 248 | 1.079 | - |
588
+ | 0.7955 | 249 | 1.3488 | - |
589
+ | 0.7987 | 250 | 1.0672 | - |
590
+ | 0.8019 | 251 | 1.4308 | - |
591
+ | 0.8051 | 252 | 1.126 | - |
592
+ | 0.8083 | 253 | 1.131 | - |
593
+ | 0.8115 | 254 | 0.9585 | - |
594
+ | 0.8147 | 255 | 0.9348 | - |
595
+ | 0.8179 | 256 | 1.1288 | - |
596
+ | 0.8211 | 257 | 1.2577 | - |
597
+ | 0.8243 | 258 | 1.286 | - |
598
+ | 0.8275 | 259 | 1.1985 | - |
599
+ | 0.8307 | 260 | 1.2386 | - |
600
+ | 0.8339 | 261 | 1.6239 | - |
601
+ | 0.8371 | 262 | 0.8122 | - |
602
+ | 0.8403 | 263 | 1.42 | - |
603
+ | 0.8435 | 264 | 0.9854 | - |
604
+ | 0.8466 | 265 | 0.9861 | - |
605
+ | 0.8498 | 266 | 1.2226 | - |
606
+ | 0.8530 | 267 | 1.1535 | - |
607
+ | 0.8562 | 268 | 1.634 | - |
608
+ | 0.8594 | 269 | 1.0699 | - |
609
+ | 0.8626 | 270 | 1.2927 | - |
610
+ | 0.8658 | 271 | 1.2269 | - |
611
+ | 0.8690 | 272 | 0.8528 | - |
612
+ | 0.8722 | 273 | 1.6345 | - |
613
+ | 0.8754 | 274 | 1.4596 | - |
614
+ | 0.8786 | 275 | 0.9795 | - |
615
+ | 0.8818 | 276 | 1.1772 | - |
616
+ | 0.8850 | 277 | 1.135 | - |
617
+ | 0.8882 | 278 | 0.994 | - |
618
+ | 0.8914 | 279 | 0.8705 | - |
619
+ | 0.8946 | 280 | 0.976 | - |
620
+ | 0.8978 | 281 | 1.2215 | - |
621
+ | 0.9010 | 282 | 1.4685 | - |
622
+ | 0.9042 | 283 | 1.6724 | - |
623
+ | 0.9073 | 284 | 1.3882 | - |
624
+ | 0.9105 | 285 | 1.2283 | - |
625
+ | 0.9137 | 286 | 1.0334 | - |
626
+ | 0.9169 | 287 | 1.2039 | - |
627
+ | 0.9201 | 288 | 1.0914 | - |
628
+ | 0.9233 | 289 | 1.7033 | - |
629
+ | 0.9265 | 290 | 1.7687 | - |
630
+ | 0.9297 | 291 | 1.2867 | - |
631
+ | 0.9329 | 292 | 1.196 | - |
632
+ | 0.9361 | 293 | 0.9771 | - |
633
+ | 0.9393 | 294 | 1.1878 | - |
634
+ | 0.9425 | 295 | 1.235 | - |
635
+ | 0.9457 | 296 | 1.4398 | - |
636
+ | 0.9489 | 297 | 1.475 | - |
637
+ | 0.9521 | 298 | 1.2632 | - |
638
+ | 0.9553 | 299 | 1.5732 | - |
639
+ | 0.9585 | 300 | 1.0147 | 0.725 |
640
+ | 0.9617 | 301 | 1.0345 | - |
641
+ | 0.9649 | 302 | 1.2582 | - |
642
+ | 0.9681 | 303 | 1.0398 | - |
643
+ | 0.9712 | 304 | 1.3973 | - |
644
+ | 0.9744 | 305 | 1.6701 | - |
645
+ | 0.9776 | 306 | 1.2617 | - |
646
+ | 0.9808 | 307 | 1.5779 | - |
647
+ | 0.9840 | 308 | 1.0839 | - |
648
+ | 0.9872 | 309 | 1.3117 | - |
649
+ | 0.9904 | 310 | 1.6139 | - |
650
+ | 0.9936 | 311 | 1.0128 | - |
651
+ | 0.9968 | 312 | 0.837 | - |
652
+ | 1.0 | 313 | 1.3687 | 0.723 |
653
+
654
+ </details>
655
+
656
+ ### Framework Versions
657
+ - Python: 3.12.3
658
+ - Sentence Transformers: 3.3.1
659
+ - Transformers: 4.44.2
660
+ - PyTorch: 2.5.1
661
+ - Accelerate: 1.2.1
662
+ - Datasets: 2.19.0
663
+ - Tokenizers: 0.19.1
664
+
665
+ ## Citation
666
+
667
+ ### BibTeX
668
+
669
+ #### Sentence Transformers
670
+ ```bibtex
671
+ @inproceedings{reimers-2019-sentence-bert,
672
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
673
+ author = "Reimers, Nils and Gurevych, Iryna",
674
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
675
+ month = "11",
676
+ year = "2019",
677
+ publisher = "Association for Computational Linguistics",
678
+ url = "https://arxiv.org/abs/1908.10084",
679
+ }
680
+ ```
681
+
682
+ #### MultipleNegativesRankingLoss
683
+ ```bibtex
684
+ @misc{henderson2017efficient,
685
+ title={Efficient Natural Language Response Suggestion for Smart Reply},
686
+ 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},
687
+ year={2017},
688
+ eprint={1705.00652},
689
+ archivePrefix={arXiv},
690
+ primaryClass={cs.CL}
691
+ }
692
+ ```
693
+
694
+ <!--
695
+ ## Glossary
696
+
697
+ *Clearly define terms in order to be accessible across audiences.*
698
+ -->
699
+
700
+ <!--
701
+ ## Model Card Authors
702
+
703
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
704
+ -->
705
+
706
+ <!--
707
+ ## Model Card Contact
708
+
709
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
710
+ -->
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "BAAI/bge-m3-retromae",
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": "4.44.2",
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": "3.3.1",
4
+ "transformers": "4.44.2",
5
+ "pytorch": "2.5.1"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": "cosine"
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b6066d8686b3fe90310048ea05ce173dfcb21a670e7d3e0fe9026208b1d6927
3
+ size 2271064456
modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ ]
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 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "tokenizer_class": "XLMRobertaTokenizer",
53
+ "unk_token": "<unk>"
54
+ }