hmm404 commited on
Commit
13fcbe8
·
verified ·
1 Parent(s): 275d4e6

hmm404/triplet_728

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
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 +1,393 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - sentence-transformers
4
+ - sentence-similarity
5
+ - feature-extraction
6
+ - generated_from_trainer
7
+ - dataset_size:25880
8
+ - loss:TripletLoss
9
+ base_model: sentence-transformers/all-mpnet-base-v2
10
+ widget:
11
+ - source_sentence: Die Verabschiedung des NetzDG hat wichtige Symbolkraft.
12
+ sentences:
13
+ - Der Symbolwert von Gesetzen sollte nicht maßgeblich für ihre Erstellung, Umsetzung
14
+ und Bewertung sein. Gesetzte sollten einen praktischen Mehrwert haben.
15
+ - Politicians should not take limited job opportunities that would have otherwise
16
+ been available to other people in need of work.
17
+ - Symbole wirken als Kommunikationsmittel \(Dirk Hülst, S. 207\); das NetzDG beinhaltet
18
+ zentrale Botschaften.
19
+ - source_sentence: Capital punishment protects public safety by ensuring that convicted
20
+ criminals do not ever offend again.
21
+ sentences:
22
+ - That is a statement of fact, but is not an argument for why capital punishment
23
+ is just. Technically, capital punishment can also be used to against people who
24
+ drive over the speed limit, but we understand that there are more humane methods
25
+ of punishment.
26
+ - Society has an absolute right to protect itself with the execution of killers
27
+ who have committed premeditated murder and so are apt to kill again. In such
28
+ instances of premeditated murder, since the penalty suits the crime, society should
29
+ not be obligated to incur the extraordinary expense as well as the hazard of a
30
+ life sentence in lieu of the death penalty. Such obligations -- the extraordinary
31
+ cost and hazard -- in effect penalize society rather than the murderer who committed
32
+ the crime.
33
+ - 2 Nephi 3:6-22 in the Book of Mormon describes Joseph Smith as a "choice seer."
34
+ - source_sentence: Daenerys has proven that she is incapable of ruling even a single
35
+ city.
36
+ sentences:
37
+ - She now has Tyrion Lannister to do that for her, she only has to provide the looks.
38
+ - Hemp is known for having effective bioremediation/phyto-remediation qualities,
39
+ meaning it can be used to cleanse the soil.
40
+ - Daenerys takes the moral high ground to a fault. Her tendency to choose what is
41
+ "right" over what is a better strategy could be her undoing.
42
+ - source_sentence: Consumers within public health systems should be empowered to make
43
+ their own choices about their treatment.
44
+ sentences:
45
+ - People have a right to choose what kind of treatment they want regarding something
46
+ as important as their own health.
47
+ - The money available to public health systems is limited. One patient's decisions
48
+ to use homeopathy limits another's access to a more effective treatment.
49
+ - Wizard healing can cure any "normal" illness \(any illness Muggles might contract\).
50
+ - source_sentence: 'Nobody should have to take the responsibility for another couple''s
51
+ bad decisions: to put a child up for adoption is selfish because you are deciding
52
+ to have a better life for yourself rather than raise a kid.'
53
+ sentences:
54
+ - It is not selfish to have children as long as you love them and care for them.
55
+ Putting a child up for adoption is selfish \(depending on the reason\) because
56
+ the child is always going to wonder why they were left.
57
+ - In order to go from "is" to "ought," one must introduce something from outside
58
+ the realm of the "is."
59
+ - Putting a child up for adoption can be considered a selfless act if you do it
60
+ because someone else can give the child a better life than you can.
61
+ pipeline_tag: sentence-similarity
62
+ library_name: sentence-transformers
63
+ ---
64
+
65
+ # SentenceTransformer based on sentence-transformers/all-mpnet-base-v2
66
+
67
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
68
+
69
+ ## Model Details
70
+
71
+ ### Model Description
72
+ - **Model Type:** Sentence Transformer
73
+ - **Base model:** [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) <!-- at revision 9a3225965996d404b775526de6dbfe85d3368642 -->
74
+ - **Maximum Sequence Length:** 384 tokens
75
+ - **Output Dimensionality:** 768 dimensions
76
+ - **Similarity Function:** Cosine Similarity
77
+ <!-- - **Training Dataset:** Unknown -->
78
+ <!-- - **Language:** Unknown -->
79
+ <!-- - **License:** Unknown -->
80
+
81
+ ### Model Sources
82
+
83
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
84
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
85
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
86
+
87
+ ### Full Model Architecture
88
+
89
+ ```
90
+ SentenceTransformer(
91
+ (0): Transformer({'max_seq_length': 384, 'do_lower_case': False}) with Transformer model: MPNetModel
92
+ (1): Pooling({'word_embedding_dimension': 768, '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})
93
+ (2): Normalize()
94
+ )
95
+ ```
96
+
97
+ ## Usage
98
+
99
+ ### Direct Usage (Sentence Transformers)
100
+
101
+ First install the Sentence Transformers library:
102
+
103
+ ```bash
104
+ pip install -U sentence-transformers
105
+ ```
106
+
107
+ Then you can load this model and run inference.
108
+ ```python
109
+ from sentence_transformers import SentenceTransformer
110
+
111
+ # Download from the 🤗 Hub
112
+ model = SentenceTransformer("sentence_transformers_model_id")
113
+ # Run inference
114
+ sentences = [
115
+ "Nobody should have to take the responsibility for another couple's bad decisions: to put a child up for adoption is selfish because you are deciding to have a better life for yourself rather than raise a kid.",
116
+ 'It is not selfish to have children as long as you love them and care for them. Putting a child up for adoption is selfish \\(depending on the reason\\) because the child is always going to wonder why they were left.',
117
+ 'Putting a child up for adoption can be considered a selfless act if you do it because someone else can give the child a better life than you can.',
118
+ ]
119
+ embeddings = model.encode(sentences)
120
+ print(embeddings.shape)
121
+ # [3, 768]
122
+
123
+ # Get the similarity scores for the embeddings
124
+ similarities = model.similarity(embeddings, embeddings)
125
+ print(similarities.shape)
126
+ # [3, 3]
127
+ ```
128
+
129
+ <!--
130
+ ### Direct Usage (Transformers)
131
+
132
+ <details><summary>Click to see the direct usage in Transformers</summary>
133
+
134
+ </details>
135
+ -->
136
+
137
+ <!--
138
+ ### Downstream Usage (Sentence Transformers)
139
+
140
+ You can finetune this model on your own dataset.
141
+
142
+ <details><summary>Click to expand</summary>
143
+
144
+ </details>
145
+ -->
146
+
147
+ <!--
148
+ ### Out-of-Scope Use
149
+
150
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
151
+ -->
152
+
153
+ <!--
154
+ ## Bias, Risks and Limitations
155
+
156
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
157
+ -->
158
+
159
+ <!--
160
+ ### Recommendations
161
+
162
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
163
+ -->
164
+
165
+ ## Training Details
166
+
167
+ ### Training Dataset
168
+
169
+ #### Unnamed Dataset
170
+
171
+ * Size: 25,880 training samples
172
+ * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
173
+ * Approximate statistics based on the first 1000 samples:
174
+ | | anchor | positive | negative |
175
+ |:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
176
+ | type | string | string | string |
177
+ | details | <ul><li>min: 3 tokens</li><li>mean: 27.9 tokens</li><li>max: 186 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 34.46 tokens</li><li>max: 140 tokens</li></ul> | <ul><li>min: 8 tokens</li><li>mean: 35.42 tokens</li><li>max: 185 tokens</li></ul> |
178
+ * Samples:
179
+ | anchor | positive | negative |
180
+ |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
181
+ | <code>Security services such as the USA's NSA, or UK's GCHQ require secrecy about what actions they are taking. Open sourcing all code would reveal those actions.</code> | <code>Writing implants/malware would not be possible in open source.</code> | <code>This could be a good thing if you side with whistleblowers \(eg Snowden/Wikileaks\), as it would have revealed the governments actions sooner.</code> |
182
+ | <code>Monarchs are still extremely vulnerable to the effects of public opinion, meaning that the use of their power is implicitly determined by the will of the people.</code> | <code>In Liechtenstein, according to the Constitution, the Prince is subject to a popular vote of no confidence \(Art. 13ter\). Furthermore, the Constitution itself provides a procedure to abolish the monarchy upon popular request \(Art. 113\).</code> | <code>Being subject to the pressure of public opinion is very different from representing the will of the people.</code> |
183
+ | <code>The Church of Jesus Christ of Latter-day Saints \(The "Mormon" Church\) teaches that free will, or "Agency," is essential the God's plan of Happiness for mankind and our freedom to choose is one of mankind's greatest blessings.</code> | <code>The Church of Jesus Christ of Latter-day Saints also teaches that one of Satan's greatest sins was that he ["sought to destroy the agency \[i.e. free will\] of man, which I, the Lord God, had given him."](https://www.lds.org/scriptures/pgp/moses/4.3-4)</code> | <code>There's no logic or rational thinking into your claim other than implicit authority. It'd be the same as claiming that Harry Potter teaches us that free will or "Agency" is an illusion on page 137. If you don't take Harry Potter as an authority this claim means nothing to you. That's why we have science and logic to support any explanation without implicit authority.</code> |
184
+ * Loss: [<code>TripletLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#tripletloss) with these parameters:
185
+ ```json
186
+ {
187
+ "distance_metric": "TripletDistanceMetric.COSINE",
188
+ "triplet_margin": 0.3
189
+ }
190
+ ```
191
+
192
+ ### Training Hyperparameters
193
+
194
+ #### All Hyperparameters
195
+ <details><summary>Click to expand</summary>
196
+
197
+ - `overwrite_output_dir`: False
198
+ - `do_predict`: False
199
+ - `eval_strategy`: no
200
+ - `prediction_loss_only`: True
201
+ - `per_device_train_batch_size`: 8
202
+ - `per_device_eval_batch_size`: 8
203
+ - `per_gpu_train_batch_size`: None
204
+ - `per_gpu_eval_batch_size`: None
205
+ - `gradient_accumulation_steps`: 1
206
+ - `eval_accumulation_steps`: None
207
+ - `torch_empty_cache_steps`: None
208
+ - `learning_rate`: 5e-05
209
+ - `weight_decay`: 0.0
210
+ - `adam_beta1`: 0.9
211
+ - `adam_beta2`: 0.999
212
+ - `adam_epsilon`: 1e-08
213
+ - `max_grad_norm`: 1.0
214
+ - `num_train_epochs`: 3.0
215
+ - `max_steps`: -1
216
+ - `lr_scheduler_type`: linear
217
+ - `lr_scheduler_kwargs`: {}
218
+ - `warmup_ratio`: 0.0
219
+ - `warmup_steps`: 0
220
+ - `log_level`: passive
221
+ - `log_level_replica`: warning
222
+ - `log_on_each_node`: True
223
+ - `logging_nan_inf_filter`: True
224
+ - `save_safetensors`: True
225
+ - `save_on_each_node`: False
226
+ - `save_only_model`: False
227
+ - `restore_callback_states_from_checkpoint`: False
228
+ - `no_cuda`: False
229
+ - `use_cpu`: False
230
+ - `use_mps_device`: False
231
+ - `seed`: 42
232
+ - `data_seed`: None
233
+ - `jit_mode_eval`: False
234
+ - `use_ipex`: False
235
+ - `bf16`: False
236
+ - `fp16`: False
237
+ - `fp16_opt_level`: O1
238
+ - `half_precision_backend`: auto
239
+ - `bf16_full_eval`: False
240
+ - `fp16_full_eval`: False
241
+ - `tf32`: None
242
+ - `local_rank`: 0
243
+ - `ddp_backend`: None
244
+ - `tpu_num_cores`: None
245
+ - `tpu_metrics_debug`: False
246
+ - `debug`: []
247
+ - `dataloader_drop_last`: False
248
+ - `dataloader_num_workers`: 0
249
+ - `dataloader_prefetch_factor`: None
250
+ - `past_index`: -1
251
+ - `disable_tqdm`: False
252
+ - `remove_unused_columns`: True
253
+ - `label_names`: None
254
+ - `load_best_model_at_end`: False
255
+ - `ignore_data_skip`: False
256
+ - `fsdp`: []
257
+ - `fsdp_min_num_params`: 0
258
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
259
+ - `fsdp_transformer_layer_cls_to_wrap`: None
260
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
261
+ - `deepspeed`: None
262
+ - `label_smoothing_factor`: 0.0
263
+ - `optim`: adamw_torch
264
+ - `optim_args`: None
265
+ - `adafactor`: False
266
+ - `group_by_length`: False
267
+ - `length_column_name`: length
268
+ - `ddp_find_unused_parameters`: None
269
+ - `ddp_bucket_cap_mb`: None
270
+ - `ddp_broadcast_buffers`: False
271
+ - `dataloader_pin_memory`: True
272
+ - `dataloader_persistent_workers`: False
273
+ - `skip_memory_metrics`: True
274
+ - `use_legacy_prediction_loop`: False
275
+ - `push_to_hub`: False
276
+ - `resume_from_checkpoint`: None
277
+ - `hub_model_id`: None
278
+ - `hub_strategy`: every_save
279
+ - `hub_private_repo`: None
280
+ - `hub_always_push`: False
281
+ - `gradient_checkpointing`: False
282
+ - `gradient_checkpointing_kwargs`: None
283
+ - `include_inputs_for_metrics`: False
284
+ - `include_for_metrics`: []
285
+ - `eval_do_concat_batches`: True
286
+ - `fp16_backend`: auto
287
+ - `push_to_hub_model_id`: None
288
+ - `push_to_hub_organization`: None
289
+ - `mp_parameters`:
290
+ - `auto_find_batch_size`: False
291
+ - `full_determinism`: False
292
+ - `torchdynamo`: None
293
+ - `ray_scope`: last
294
+ - `ddp_timeout`: 1800
295
+ - `torch_compile`: False
296
+ - `torch_compile_backend`: None
297
+ - `torch_compile_mode`: None
298
+ - `dispatch_batches`: None
299
+ - `split_batches`: None
300
+ - `include_tokens_per_second`: False
301
+ - `include_num_input_tokens_seen`: False
302
+ - `neftune_noise_alpha`: None
303
+ - `optim_target_modules`: None
304
+ - `batch_eval_metrics`: False
305
+ - `eval_on_start`: False
306
+ - `use_liger_kernel`: False
307
+ - `eval_use_gather_object`: False
308
+ - `average_tokens_across_devices`: False
309
+ - `prompts`: None
310
+ - `batch_sampler`: batch_sampler
311
+ - `multi_dataset_batch_sampler`: proportional
312
+
313
+ </details>
314
+
315
+ ### Training Logs
316
+ | Epoch | Step | Training Loss |
317
+ |:------:|:----:|:-------------:|
318
+ | 0.1546 | 500 | 0.2287 |
319
+ | 0.3091 | 1000 | 0.2057 |
320
+ | 0.4637 | 1500 | 0.1884 |
321
+ | 0.6182 | 2000 | 0.1873 |
322
+ | 0.7728 | 2500 | 0.2153 |
323
+ | 0.9274 | 3000 | 0.2972 |
324
+ | 1.0819 | 3500 | 0.2991 |
325
+ | 1.2365 | 4000 | 0.2994 |
326
+ | 1.3910 | 4500 | 0.3 |
327
+ | 1.5456 | 5000 | 0.3 |
328
+ | 1.7002 | 5500 | 0.3 |
329
+ | 1.8547 | 6000 | 0.3001 |
330
+ | 2.0093 | 6500 | 0.3 |
331
+ | 2.1638 | 7000 | 0.3001 |
332
+ | 2.3184 | 7500 | 0.3 |
333
+ | 2.4730 | 8000 | 0.3 |
334
+ | 2.6275 | 8500 | 0.3001 |
335
+ | 2.7821 | 9000 | 0.3 |
336
+ | 2.9366 | 9500 | 0.3001 |
337
+
338
+
339
+ ### Framework Versions
340
+ - Python: 3.11.11
341
+ - Sentence Transformers: 3.4.1
342
+ - Transformers: 4.48.3
343
+ - PyTorch: 2.5.1+cu124
344
+ - Accelerate: 1.3.0
345
+ - Datasets: 3.3.1
346
+ - Tokenizers: 0.21.0
347
+
348
+ ## Citation
349
+
350
+ ### BibTeX
351
+
352
+ #### Sentence Transformers
353
+ ```bibtex
354
+ @inproceedings{reimers-2019-sentence-bert,
355
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
356
+ author = "Reimers, Nils and Gurevych, Iryna",
357
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
358
+ month = "11",
359
+ year = "2019",
360
+ publisher = "Association for Computational Linguistics",
361
+ url = "https://arxiv.org/abs/1908.10084",
362
+ }
363
+ ```
364
+
365
+ #### TripletLoss
366
+ ```bibtex
367
+ @misc{hermans2017defense,
368
+ title={In Defense of the Triplet Loss for Person Re-Identification},
369
+ author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
370
+ year={2017},
371
+ eprint={1703.07737},
372
+ archivePrefix={arXiv},
373
+ primaryClass={cs.CV}
374
+ }
375
+ ```
376
+
377
+ <!--
378
+ ## Glossary
379
+
380
+ *Clearly define terms in order to be accessible across audiences.*
381
+ -->
382
+
383
+ <!--
384
+ ## Model Card Authors
385
+
386
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
387
+ -->
388
+
389
+ <!--
390
+ ## Model Card Contact
391
+
392
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
393
+ -->
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sentence-transformers/all-mpnet-base-v2",
3
+ "architectures": [
4
+ "MPNetModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "mpnet",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
+ "relative_attention_num_buckets": 32,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.48.3",
23
+ "vocab_size": 30527
24
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.4.1",
4
+ "transformers": "4.48.3",
5
+ "pytorch": "2.5.1+cu124"
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:bb28db92f7b339893f9f69c4a76f93fdb8d75f28a028c83fae207b010ca87df7
3
+ size 437967672
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
+ ]
runs/Feb18_06-37-18_9d18770862ef/events.out.tfevents.1739860645.9d18770862ef.7189.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa92fa41bc8db747d7aa9f08ba34a5ea2b626bd938be267b3ab8dbe9e498e142
3
+ size 8738
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 384,
3
+ "do_lower_case": false
4
+ }
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
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "104": {
36
+ "content": "[UNK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "30526": {
44
+ "content": "<mask>",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ }
51
+ },
52
+ "bos_token": "<s>",
53
+ "clean_up_tokenization_spaces": false,
54
+ "cls_token": "<s>",
55
+ "do_lower_case": true,
56
+ "eos_token": "</s>",
57
+ "extra_special_tokens": {},
58
+ "mask_token": "<mask>",
59
+ "max_length": 128,
60
+ "model_max_length": 384,
61
+ "pad_to_multiple_of": null,
62
+ "pad_token": "<pad>",
63
+ "pad_token_type_id": 0,
64
+ "padding_side": "right",
65
+ "sep_token": "</s>",
66
+ "stride": 0,
67
+ "strip_accents": null,
68
+ "tokenize_chinese_chars": true,
69
+ "tokenizer_class": "MPNetTokenizer",
70
+ "truncation_side": "right",
71
+ "truncation_strategy": "longest_first",
72
+ "unk_token": "[UNK]"
73
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f03dc66115a20cc231388424ba4857549fdc8b3487964815848347220bc248d
3
+ size 5560
vocab.txt ADDED
The diff for this file is too large to render. See raw diff