blackmlengineer commited on
Commit
485f1a0
·
verified ·
1 Parent(s): 1cefec4

Add new model.

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "embedding_dimension": 128,
3
+ "pooling_mode": "mean",
4
+ "include_prompt": true
5
+ }
README.md ADDED
@@ -0,0 +1,427 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - sentence-transformers
4
+ - sentence-similarity
5
+ - feature-extraction
6
+ - generated_from_trainer
7
+ - dataset_size:991580
8
+ - loss:MultipleNegativesRankingLoss
9
+ widget:
10
+ - source_sentence: Draw Off Worker
11
+ sentences:
12
+ - Computer Systems Analysts
13
+ - Meat, Poultry, and Fish Cutters and Trimmers
14
+ - Food Preparation Workers
15
+ - source_sentence: College Tutor
16
+ sentences:
17
+ - Endoscopy Technicians
18
+ - Mathematical Science Teachers, Postsecondary
19
+ - Tutors
20
+ - source_sentence: Carbon Plant Grinder
21
+ sentences:
22
+ - Crushing, Grinding, and Polishing Machine Setters, Operators, and Tenders
23
+ - Coating, Painting, and Spraying Machine Setters, Operators, and Tenders
24
+ - Adhesive Bonding Machine Operators and Tenders
25
+ - source_sentence: Roofing Supervisor
26
+ sentences:
27
+ - Solar Energy Installation Managers
28
+ - First-Line Supervisors of Construction Trades and Extraction Workers
29
+ - Agricultural Inspectors
30
+ - source_sentence: Meat Wrapper
31
+ sentences:
32
+ - Laundry and Dry-Cleaning Workers
33
+ - Printing Press Operators
34
+ - Packers and Packagers, Hand
35
+ pipeline_tag: sentence-similarity
36
+ library_name: sentence-transformers
37
+ ---
38
+
39
+ # SentenceTransformer
40
+
41
+ This is a [sentence-transformers](https://www.SBERT.net) model trained on the train dataset. It maps sentences & paragraphs to a 128-dimensional dense vector space and can be used for retrieval.
42
+
43
+ ## Model Details
44
+
45
+ ### Model Description
46
+ - **Model Type:** Sentence Transformer
47
+ <!-- - **Base model:** [Unknown](https://huggingface.co/unknown) -->
48
+ - **Maximum Sequence Length:** 32 tokens
49
+ - **Output Dimensionality:** 128 dimensions
50
+ - **Similarity Function:** Cosine Similarity
51
+ - **Supported Modality:** Text
52
+ - **Training Dataset:**
53
+ - train
54
+ <!-- - **Language:** Unknown -->
55
+ <!-- - **License:** Unknown -->
56
+
57
+ ### Model Sources
58
+
59
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
60
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers)
61
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
62
+
63
+ ### Full Model Architecture
64
+
65
+ ```
66
+ SentenceTransformer(
67
+ (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'BertModel'})
68
+ (1): Pooling({'embedding_dimension': 128, 'pooling_mode': 'mean', 'include_prompt': True})
69
+ )
70
+ ```
71
+
72
+ ## Usage
73
+
74
+ ### Direct Usage (Sentence Transformers)
75
+
76
+ First install the Sentence Transformers library:
77
+
78
+ ```bash
79
+ pip install -U sentence-transformers
80
+ ```
81
+ Then you can load this model and run inference.
82
+ ```python
83
+ from sentence_transformers import SentenceTransformer
84
+
85
+ # Download from the 🤗 Hub
86
+ model = SentenceTransformer("blackmlengineer/occucoder-en-small-v0")
87
+ # Run inference
88
+ sentences = [
89
+ 'Meat Wrapper',
90
+ 'Packers and Packagers, Hand',
91
+ 'Laundry and Dry-Cleaning Workers',
92
+ ]
93
+ embeddings = model.encode(sentences)
94
+ print(embeddings.shape)
95
+ # [3, 128]
96
+
97
+ # Get the similarity scores for the embeddings
98
+ similarities = model.similarity(embeddings, embeddings)
99
+ print(similarities)
100
+ # tensor([[1.0000, 0.7078, 0.3098],
101
+ # [0.7078, 1.0000, 0.4332],
102
+ # [0.3098, 0.4332, 1.0000]])
103
+ ```
104
+ <!--
105
+ ### Direct Usage (Transformers)
106
+
107
+ <details><summary>Click to see the direct usage in Transformers</summary>
108
+
109
+ </details>
110
+ -->
111
+
112
+ <!--
113
+ ### Downstream Usage (Sentence Transformers)
114
+
115
+ You can finetune this model on your own dataset.
116
+
117
+ <details><summary>Click to expand</summary>
118
+
119
+ </details>
120
+ -->
121
+
122
+ <!--
123
+ ### Out-of-Scope Use
124
+
125
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
126
+ -->
127
+
128
+ <!--
129
+ ## Bias, Risks and Limitations
130
+
131
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
132
+ -->
133
+
134
+ <!--
135
+ ### Recommendations
136
+
137
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
138
+ -->
139
+
140
+ ## Training Details
141
+
142
+ ### Training Dataset
143
+
144
+ #### train
145
+
146
+ * Dataset: train
147
+ * Size: 991,580 training samples
148
+ * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
149
+ * Approximate statistics based on the first 100 samples:
150
+ | | anchor | positive | negative |
151
+ |:---------|:--------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
152
+ | type | string | string | string |
153
+ | modality | text | text | text |
154
+ | details | <ul><li>min: 3 tokens</li><li>mean: 4.61 tokens</li><li>max: 8 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 7.7 tokens</li><li>max: 19 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 7.95 tokens</li><li>max: 22 tokens</li></ul> |
155
+ * Samples:
156
+ | anchor | positive | negative |
157
+ |:--------------------------------------|:------------------------------------------------------------|:---------------------------------------------------------------------------|
158
+ | <code>Personnel Psychologist</code> | <code>Industrial-Organizational Psychologists</code> | <code>Educational, Guidance, and Career Counselors and Advisors</code> |
159
+ | <code>Property Claims Adjuster</code> | <code>Claims Adjusters, Examiners, and Investigators</code> | <code>Administrative Law Judges, Adjudicators, and Hearing Officers</code> |
160
+ | <code>Assistant Professor</code> | <code>Art, Drama, and Music Teachers, Postsecondary</code> | <code>Area, Ethnic, and Cultural Studies Teachers, Postsecondary</code> |
161
+ * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
162
+ ```json
163
+ {
164
+ "scale": 20.0,
165
+ "similarity_fct": "cos_sim",
166
+ "gather_across_devices": false,
167
+ "directions": [
168
+ "query_to_doc"
169
+ ],
170
+ "partition_mode": "joint",
171
+ "hardness_mode": null,
172
+ "hardness_strength": 0.0
173
+ }
174
+ ```
175
+
176
+ ### Training Hyperparameters
177
+ #### Non-Default Hyperparameters
178
+
179
+ - `per_device_train_batch_size`: 128
180
+ - `num_train_epochs`: 5
181
+
182
+ #### All Hyperparameters
183
+ <details><summary>Click to expand</summary>
184
+
185
+ - `per_device_train_batch_size`: 128
186
+ - `num_train_epochs`: 5
187
+ - `max_steps`: -1
188
+ - `learning_rate`: 5e-05
189
+ - `lr_scheduler_type`: linear
190
+ - `lr_scheduler_kwargs`: None
191
+ - `warmup_steps`: 0
192
+ - `optim`: adamw_torch_fused
193
+ - `optim_args`: None
194
+ - `weight_decay`: 0.0
195
+ - `adam_beta1`: 0.9
196
+ - `adam_beta2`: 0.999
197
+ - `adam_epsilon`: 1e-08
198
+ - `optim_target_modules`: None
199
+ - `gradient_accumulation_steps`: 1
200
+ - `average_tokens_across_devices`: True
201
+ - `max_grad_norm`: 1.0
202
+ - `label_smoothing_factor`: 0.0
203
+ - `bf16`: False
204
+ - `fp16`: False
205
+ - `bf16_full_eval`: False
206
+ - `fp16_full_eval`: False
207
+ - `tf32`: None
208
+ - `gradient_checkpointing`: False
209
+ - `gradient_checkpointing_kwargs`: None
210
+ - `torch_compile`: False
211
+ - `torch_compile_backend`: None
212
+ - `torch_compile_mode`: None
213
+ - `use_liger_kernel`: False
214
+ - `liger_kernel_config`: None
215
+ - `use_cache`: False
216
+ - `neftune_noise_alpha`: None
217
+ - `torch_empty_cache_steps`: None
218
+ - `auto_find_batch_size`: False
219
+ - `log_on_each_node`: True
220
+ - `logging_nan_inf_filter`: True
221
+ - `include_num_input_tokens_seen`: no
222
+ - `log_level`: passive
223
+ - `log_level_replica`: warning
224
+ - `disable_tqdm`: False
225
+ - `project`: huggingface
226
+ - `trackio_space_id`: None
227
+ - `trackio_bucket_id`: None
228
+ - `trackio_static_space_id`: None
229
+ - `per_device_eval_batch_size`: 8
230
+ - `prediction_loss_only`: True
231
+ - `eval_on_start`: False
232
+ - `eval_do_concat_batches`: True
233
+ - `eval_use_gather_object`: False
234
+ - `eval_accumulation_steps`: None
235
+ - `include_for_metrics`: []
236
+ - `batch_eval_metrics`: False
237
+ - `save_only_model`: False
238
+ - `save_on_each_node`: False
239
+ - `enable_jit_checkpoint`: False
240
+ - `push_to_hub`: False
241
+ - `hub_private_repo`: None
242
+ - `hub_model_id`: None
243
+ - `hub_strategy`: every_save
244
+ - `hub_always_push`: False
245
+ - `hub_revision`: None
246
+ - `load_best_model_at_end`: False
247
+ - `ignore_data_skip`: False
248
+ - `restore_callback_states_from_checkpoint`: False
249
+ - `full_determinism`: False
250
+ - `seed`: 42
251
+ - `data_seed`: None
252
+ - `use_cpu`: False
253
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
254
+ - `parallelism_config`: None
255
+ - `dataloader_drop_last`: False
256
+ - `dataloader_num_workers`: 0
257
+ - `dataloader_pin_memory`: True
258
+ - `dataloader_persistent_workers`: False
259
+ - `dataloader_prefetch_factor`: None
260
+ - `remove_unused_columns`: True
261
+ - `label_names`: None
262
+ - `train_sampling_strategy`: random
263
+ - `length_column_name`: length
264
+ - `ddp_find_unused_parameters`: None
265
+ - `ddp_bucket_cap_mb`: None
266
+ - `ddp_broadcast_buffers`: False
267
+ - `ddp_static_graph`: None
268
+ - `ddp_backend`: None
269
+ - `ddp_timeout`: 1800
270
+ - `fsdp`: None
271
+ - `fsdp_config`: None
272
+ - `deepspeed`: None
273
+ - `debug`: []
274
+ - `skip_memory_metrics`: True
275
+ - `do_predict`: False
276
+ - `resume_from_checkpoint`: None
277
+ - `warmup_ratio`: None
278
+ - `local_rank`: -1
279
+ - `prompts`: None
280
+ - `batch_sampler`: batch_sampler
281
+ - `multi_dataset_batch_sampler`: proportional
282
+ - `router_mapping`: {}
283
+ - `learning_rate_mapping`: {}
284
+
285
+ </details>
286
+
287
+ ### Training Logs
288
+ | Epoch | Step | Training Loss |
289
+ |:------:|:-----:|:-------------:|
290
+ | 0.0645 | 500 | 4.4764 |
291
+ | 0.1291 | 1000 | 3.6698 |
292
+ | 0.1936 | 1500 | 3.2978 |
293
+ | 0.2582 | 2000 | 3.0057 |
294
+ | 0.3227 | 2500 | 2.7970 |
295
+ | 0.3872 | 3000 | 2.6114 |
296
+ | 0.4518 | 3500 | 2.4757 |
297
+ | 0.5163 | 4000 | 2.3466 |
298
+ | 0.5809 | 4500 | 2.2433 |
299
+ | 0.6454 | 5000 | 2.1685 |
300
+ | 0.7100 | 5500 | 2.0893 |
301
+ | 0.7745 | 6000 | 2.0204 |
302
+ | 0.8390 | 6500 | 1.9742 |
303
+ | 0.9036 | 7000 | 1.9140 |
304
+ | 0.9681 | 7500 | 1.8665 |
305
+ | 1.0327 | 8000 | 1.8241 |
306
+ | 1.0972 | 8500 | 1.7827 |
307
+ | 1.1617 | 9000 | 1.7489 |
308
+ | 1.2263 | 9500 | 1.7071 |
309
+ | 1.2908 | 10000 | 1.6893 |
310
+ | 1.3554 | 10500 | 1.6828 |
311
+ | 1.4199 | 11000 | 1.6533 |
312
+ | 1.4844 | 11500 | 1.6357 |
313
+ | 1.5490 | 12000 | 1.6031 |
314
+ | 1.6135 | 12500 | 1.5903 |
315
+ | 1.6781 | 13000 | 1.5694 |
316
+ | 1.7426 | 13500 | 1.5630 |
317
+ | 1.8072 | 14000 | 1.5445 |
318
+ | 1.8717 | 14500 | 1.5282 |
319
+ | 1.9362 | 15000 | 1.5208 |
320
+ | 2.0008 | 15500 | 1.5121 |
321
+ | 2.0653 | 16000 | 1.4799 |
322
+ | 2.1299 | 16500 | 1.4785 |
323
+ | 2.1944 | 17000 | 1.4618 |
324
+ | 2.2589 | 17500 | 1.4591 |
325
+ | 2.3235 | 18000 | 1.4514 |
326
+ | 2.3880 | 18500 | 1.4448 |
327
+ | 2.4526 | 19000 | 1.4302 |
328
+ | 2.5171 | 19500 | 1.4267 |
329
+ | 2.5816 | 20000 | 1.4095 |
330
+ | 2.6462 | 20500 | 1.4136 |
331
+ | 2.7107 | 21000 | 1.4104 |
332
+ | 2.7753 | 21500 | 1.4022 |
333
+ | 2.8398 | 22000 | 1.3916 |
334
+ | 2.9044 | 22500 | 1.3886 |
335
+ | 2.9689 | 23000 | 1.3802 |
336
+ | 3.0334 | 23500 | 1.3769 |
337
+ | 3.0980 | 24000 | 1.3668 |
338
+ | 3.1625 | 24500 | 1.3581 |
339
+ | 3.2271 | 25000 | 1.3490 |
340
+ | 3.2916 | 25500 | 1.3557 |
341
+ | 3.3561 | 26000 | 1.3555 |
342
+ | 3.4207 | 26500 | 1.3497 |
343
+ | 3.4852 | 27000 | 1.3471 |
344
+ | 3.5498 | 27500 | 1.3418 |
345
+ | 3.6143 | 28000 | 1.3421 |
346
+ | 3.6788 | 28500 | 1.3375 |
347
+ | 3.7434 | 29000 | 1.3366 |
348
+ | 3.8079 | 29500 | 1.3411 |
349
+ | 3.8725 | 30000 | 1.3298 |
350
+ | 3.9370 | 30500 | 1.3269 |
351
+ | 4.0015 | 31000 | 1.3250 |
352
+ | 4.0661 | 31500 | 1.3134 |
353
+ | 4.1306 | 32000 | 1.3080 |
354
+ | 4.1952 | 32500 | 1.3140 |
355
+ | 4.2597 | 33000 | 1.3134 |
356
+ | 4.3243 | 33500 | 1.3108 |
357
+ | 4.3888 | 34000 | 1.3218 |
358
+ | 4.4533 | 34500 | 1.3068 |
359
+ | 4.5179 | 35000 | 1.2998 |
360
+ | 4.5824 | 35500 | 1.3115 |
361
+ | 4.6470 | 36000 | 1.3002 |
362
+ | 4.7115 | 36500 | 1.3084 |
363
+ | 4.7760 | 37000 | 1.3090 |
364
+ | 4.8406 | 37500 | 1.3027 |
365
+ | 4.9051 | 38000 | 1.3122 |
366
+ | 4.9697 | 38500 | 1.3104 |
367
+
368
+
369
+ ### Training Time
370
+ - **Training**: 25.3 minutes
371
+
372
+ ### Framework Versions
373
+ - Python: 3.14.5
374
+ - Sentence Transformers: 5.6.0
375
+ - Transformers: 5.12.1
376
+ - PyTorch: 2.12.0
377
+ - Accelerate: 1.14.0
378
+ - Datasets: 5.0.0
379
+ - Tokenizers: 0.22.2
380
+
381
+ ## Citation
382
+
383
+ ### BibTeX
384
+
385
+ #### Sentence Transformers
386
+ ```bibtex
387
+ @inproceedings{reimers-2019-sentence-bert,
388
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
389
+ author = "Reimers, Nils and Gurevych, Iryna",
390
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
391
+ month = "11",
392
+ year = "2019",
393
+ publisher = "Association for Computational Linguistics",
394
+ url = "https://arxiv.org/abs/1908.10084",
395
+ }
396
+ ```
397
+
398
+ #### MultipleNegativesRankingLoss
399
+ ```bibtex
400
+ @misc{oord2019representationlearningcontrastivepredictive,
401
+ title={Representation Learning with Contrastive Predictive Coding},
402
+ author={Aaron van den Oord and Yazhe Li and Oriol Vinyals},
403
+ year={2019},
404
+ eprint={1807.03748},
405
+ archivePrefix={arXiv},
406
+ primaryClass={cs.LG},
407
+ url={https://arxiv.org/abs/1807.03748},
408
+ }
409
+ ```
410
+
411
+ <!--
412
+ ## Glossary
413
+
414
+ *Clearly define terms in order to be accessible across audiences.*
415
+ -->
416
+
417
+ <!--
418
+ ## Model Card Authors
419
+
420
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
421
+ -->
422
+
423
+ <!--
424
+ ## Model Card Contact
425
+
426
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
427
+ -->
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": null,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "eos_token_id": null,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 128,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 256,
16
+ "is_decoder": false,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 32,
19
+ "model_type": "bert",
20
+ "num_attention_heads": 2,
21
+ "num_hidden_layers": 1,
22
+ "pad_token_id": 0,
23
+ "tie_word_embeddings": true,
24
+ "transformers_version": "5.12.1",
25
+ "type_vocab_size": 2,
26
+ "use_cache": false,
27
+ "vocab_size": 10000
28
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "pytorch": "2.12.0",
4
+ "sentence_transformers": "5.6.0",
5
+ "transformers": "5.12.1"
6
+ },
7
+ "default_prompt_name": null,
8
+ "model_type": "SentenceTransformer",
9
+ "prompts": {
10
+ "document": "",
11
+ "query": ""
12
+ },
13
+ "similarity_fn_name": "cosine"
14
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4e6562f3f0dbc25dde08d5050a0623a677ef4854cf7140bc7a3ccbed7d49e68
3
+ size 5736824
modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.base.modules.transformer.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.sentence_transformer.modules.pooling.Pooling"
13
+ }
14
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "transformer_task": "feature-extraction",
3
+ "modality_config": {
4
+ "text": {
5
+ "method": "forward",
6
+ "method_output_name": "last_hidden_state"
7
+ }
8
+ },
9
+ "module_output_name": "token_embeddings"
10
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "is_local": true,
6
+ "local_files_only": false,
7
+ "mask_token": "[MASK]",
8
+ "max_length": 32,
9
+ "model_max_length": 32,
10
+ "pad_to_multiple_of": null,
11
+ "pad_token": "[PAD]",
12
+ "pad_token_type_id": 0,
13
+ "padding_side": "right",
14
+ "sep_token": "[SEP]",
15
+ "stride": 0,
16
+ "strip_accents": null,
17
+ "tokenize_chinese_chars": true,
18
+ "tokenizer_class": "BertTokenizer",
19
+ "truncation_side": "right",
20
+ "truncation_strategy": "longest_first",
21
+ "unk_token": "[UNK]"
22
+ }