kathleenge
commited on
Commit
•
006e61b
1
Parent(s):
e07d2c0
Add new SentenceTransformer model.
Browse files- 1_Pooling/config.json +10 -0
- README.md +380 -0
- config.json +26 -0
- config_sentence_transformers.json +10 -0
- model.safetensors +3 -0
- modules.json +14 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- vocab.txt +0 -0
1_Pooling/config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 768,
|
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 +1,380 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: google-bert/bert-base-uncased
|
3 |
+
datasets: []
|
4 |
+
language: []
|
5 |
+
library_name: sentence-transformers
|
6 |
+
pipeline_tag: sentence-similarity
|
7 |
+
tags:
|
8 |
+
- sentence-transformers
|
9 |
+
- sentence-similarity
|
10 |
+
- feature-extraction
|
11 |
+
- generated_from_trainer
|
12 |
+
- dataset_size:100000
|
13 |
+
- loss:DenoisingAutoEncoderLoss
|
14 |
+
widget:
|
15 |
+
- source_sentence: 1109/icnsurv
|
16 |
+
sentences:
|
17 |
+
- 1109/icnsurv
|
18 |
+
- A cost function is needed to assign a performance metric value to a particular
|
19 |
+
test run
|
20 |
+
- Aircraft OperationsFuture aircraft will sense, control, communicate, and navigate
|
21 |
+
with increasing levels of autonomy, enabling new concepts in air traffic management
|
22 |
+
- source_sentence: Table 1 of and to well as the median taxi from STBO KDFW
|
23 |
+
sentences:
|
24 |
+
- Table 1 Metrics of accuracy, median and MAD of residuals as compared to STBO predictions,
|
25 |
+
as well as the median taxi time from STBO for KDFW and KCLT airports
|
26 |
+
- ', IEEE, 2005, pp'
|
27 |
+
- 'RESULTS: EFFICIENCY ANALYSIS'
|
28 |
+
- source_sentence: gate time to known
|
29 |
+
sentences:
|
30 |
+
- 3FIVE INPUT VARIABLESParameterDescriptionHead windHead WindGust windGust WindCeiling_ftForecast
|
31 |
+
CeilingVis_ftForecast VisibilityAct_Land_Wgt Actual Landing Weightfive parameters
|
32 |
+
listed in
|
33 |
+
- Instead, gate departure time was assumed to be known
|
34 |
+
- The proof is very similar to that presented for the NP-completeness of ASP, and
|
35 |
+
is based on reduction from PLANAR-P3( 6), hence we simply provide the main idea
|
36 |
+
of the proof
|
37 |
+
- source_sentence: ', Hough" Pattern Recognition, Vol'
|
38 |
+
sentences:
|
39 |
+
- 9 Station Keeping scores
|
40 |
+
- "\t\tAGARD CD-410"
|
41 |
+
- ', "Generalizing the Hough Transform to Detect Arbitrary Shapes," Pattern Recognition,
|
42 |
+
Vol'
|
43 |
+
- source_sentence: Airlines often ferry from locations fuel prices
|
44 |
+
sentences:
|
45 |
+
- Scheduler Inputs and Order of ConsiderationThe surface model provides EOBT, UOBT,
|
46 |
+
UTOT and other detailed flight-specific modeled input
|
47 |
+
- "\t\t\tKeithWichman"
|
48 |
+
- Airlines often ferry fuel from locations where fuel prices are cheapest
|
49 |
+
---
|
50 |
+
|
51 |
+
# SentenceTransformer based on google-bert/bert-base-uncased
|
52 |
+
|
53 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased). 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.
|
54 |
+
|
55 |
+
## Model Details
|
56 |
+
|
57 |
+
### Model Description
|
58 |
+
- **Model Type:** Sentence Transformer
|
59 |
+
- **Base model:** [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) <!-- at revision 86b5e0934494bd15c9632b12f734a8a67f723594 -->
|
60 |
+
- **Maximum Sequence Length:** 512 tokens
|
61 |
+
- **Output Dimensionality:** 768 tokens
|
62 |
+
- **Similarity Function:** Cosine Similarity
|
63 |
+
<!-- - **Training Dataset:** Unknown -->
|
64 |
+
<!-- - **Language:** Unknown -->
|
65 |
+
<!-- - **License:** Unknown -->
|
66 |
+
|
67 |
+
### Model Sources
|
68 |
+
|
69 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
70 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
71 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
72 |
+
|
73 |
+
### Full Model Architecture
|
74 |
+
|
75 |
+
```
|
76 |
+
SentenceTransformer(
|
77 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
|
78 |
+
(1): Pooling({'word_embedding_dimension': 768, '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})
|
79 |
+
)
|
80 |
+
```
|
81 |
+
|
82 |
+
## Usage
|
83 |
+
|
84 |
+
### Direct Usage (Sentence Transformers)
|
85 |
+
|
86 |
+
First install the Sentence Transformers library:
|
87 |
+
|
88 |
+
```bash
|
89 |
+
pip install -U sentence-transformers
|
90 |
+
```
|
91 |
+
|
92 |
+
Then you can load this model and run inference.
|
93 |
+
```python
|
94 |
+
from sentence_transformers import SentenceTransformer
|
95 |
+
|
96 |
+
# Download from the 🤗 Hub
|
97 |
+
model = SentenceTransformer("kathleenge/tsdae-bert-base-uncased")
|
98 |
+
# Run inference
|
99 |
+
sentences = [
|
100 |
+
'Airlines often ferry from locations fuel prices',
|
101 |
+
'Airlines often ferry fuel from locations where fuel prices are cheapest',
|
102 |
+
'\t\t\tKeithWichman',
|
103 |
+
]
|
104 |
+
embeddings = model.encode(sentences)
|
105 |
+
print(embeddings.shape)
|
106 |
+
# [3, 768]
|
107 |
+
|
108 |
+
# Get the similarity scores for the embeddings
|
109 |
+
similarities = model.similarity(embeddings, embeddings)
|
110 |
+
print(similarities.shape)
|
111 |
+
# [3, 3]
|
112 |
+
```
|
113 |
+
|
114 |
+
<!--
|
115 |
+
### Direct Usage (Transformers)
|
116 |
+
|
117 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
118 |
+
|
119 |
+
</details>
|
120 |
+
-->
|
121 |
+
|
122 |
+
<!--
|
123 |
+
### Downstream Usage (Sentence Transformers)
|
124 |
+
|
125 |
+
You can finetune this model on your own dataset.
|
126 |
+
|
127 |
+
<details><summary>Click to expand</summary>
|
128 |
+
|
129 |
+
</details>
|
130 |
+
-->
|
131 |
+
|
132 |
+
<!--
|
133 |
+
### Out-of-Scope Use
|
134 |
+
|
135 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
136 |
+
-->
|
137 |
+
|
138 |
+
<!--
|
139 |
+
## Bias, Risks and Limitations
|
140 |
+
|
141 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
142 |
+
-->
|
143 |
+
|
144 |
+
<!--
|
145 |
+
### Recommendations
|
146 |
+
|
147 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
148 |
+
-->
|
149 |
+
|
150 |
+
## Training Details
|
151 |
+
|
152 |
+
### Training Dataset
|
153 |
+
|
154 |
+
#### Unnamed Dataset
|
155 |
+
|
156 |
+
|
157 |
+
* Size: 100,000 training samples
|
158 |
+
* Columns: <code>sentence_0</code> and <code>sentence_1</code>
|
159 |
+
* Approximate statistics based on the first 1000 samples:
|
160 |
+
| | sentence_0 | sentence_1 |
|
161 |
+
|:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
|
162 |
+
| type | string | string |
|
163 |
+
| details | <ul><li>min: 3 tokens</li><li>mean: 10.95 tokens</li><li>max: 106 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 23.39 tokens</li><li>max: 239 tokens</li></ul> |
|
164 |
+
* Samples:
|
165 |
+
| sentence_0 | sentence_1 |
|
166 |
+
|:------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------|
|
167 |
+
| <code>selected and reviewed for value current on metroplex</code> | <code>The literature was selected and reviewed for its value to the current research on metroplex operations</code> |
|
168 |
+
| <code>and</code> | <code>, and Dulchinos, V</code> |
|
169 |
+
| <code>,</code> | <code>, Atkins, S</code> |
|
170 |
+
* Loss: [<code>DenoisingAutoEncoderLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#denoisingautoencoderloss)
|
171 |
+
|
172 |
+
### Training Hyperparameters
|
173 |
+
#### Non-Default Hyperparameters
|
174 |
+
|
175 |
+
- `num_train_epochs`: 1
|
176 |
+
- `multi_dataset_batch_sampler`: round_robin
|
177 |
+
|
178 |
+
#### All Hyperparameters
|
179 |
+
<details><summary>Click to expand</summary>
|
180 |
+
|
181 |
+
- `overwrite_output_dir`: False
|
182 |
+
- `do_predict`: False
|
183 |
+
- `eval_strategy`: no
|
184 |
+
- `prediction_loss_only`: True
|
185 |
+
- `per_device_train_batch_size`: 8
|
186 |
+
- `per_device_eval_batch_size`: 8
|
187 |
+
- `per_gpu_train_batch_size`: None
|
188 |
+
- `per_gpu_eval_batch_size`: None
|
189 |
+
- `gradient_accumulation_steps`: 1
|
190 |
+
- `eval_accumulation_steps`: None
|
191 |
+
- `learning_rate`: 5e-05
|
192 |
+
- `weight_decay`: 0.0
|
193 |
+
- `adam_beta1`: 0.9
|
194 |
+
- `adam_beta2`: 0.999
|
195 |
+
- `adam_epsilon`: 1e-08
|
196 |
+
- `max_grad_norm`: 1
|
197 |
+
- `num_train_epochs`: 1
|
198 |
+
- `max_steps`: -1
|
199 |
+
- `lr_scheduler_type`: linear
|
200 |
+
- `lr_scheduler_kwargs`: {}
|
201 |
+
- `warmup_ratio`: 0.0
|
202 |
+
- `warmup_steps`: 0
|
203 |
+
- `log_level`: passive
|
204 |
+
- `log_level_replica`: warning
|
205 |
+
- `log_on_each_node`: True
|
206 |
+
- `logging_nan_inf_filter`: True
|
207 |
+
- `save_safetensors`: True
|
208 |
+
- `save_on_each_node`: False
|
209 |
+
- `save_only_model`: False
|
210 |
+
- `restore_callback_states_from_checkpoint`: False
|
211 |
+
- `no_cuda`: False
|
212 |
+
- `use_cpu`: False
|
213 |
+
- `use_mps_device`: False
|
214 |
+
- `seed`: 42
|
215 |
+
- `data_seed`: None
|
216 |
+
- `jit_mode_eval`: False
|
217 |
+
- `use_ipex`: False
|
218 |
+
- `bf16`: False
|
219 |
+
- `fp16`: False
|
220 |
+
- `fp16_opt_level`: O1
|
221 |
+
- `half_precision_backend`: auto
|
222 |
+
- `bf16_full_eval`: False
|
223 |
+
- `fp16_full_eval`: False
|
224 |
+
- `tf32`: None
|
225 |
+
- `local_rank`: 0
|
226 |
+
- `ddp_backend`: None
|
227 |
+
- `tpu_num_cores`: None
|
228 |
+
- `tpu_metrics_debug`: False
|
229 |
+
- `debug`: []
|
230 |
+
- `dataloader_drop_last`: False
|
231 |
+
- `dataloader_num_workers`: 0
|
232 |
+
- `dataloader_prefetch_factor`: None
|
233 |
+
- `past_index`: -1
|
234 |
+
- `disable_tqdm`: False
|
235 |
+
- `remove_unused_columns`: True
|
236 |
+
- `label_names`: None
|
237 |
+
- `load_best_model_at_end`: False
|
238 |
+
- `ignore_data_skip`: False
|
239 |
+
- `fsdp`: []
|
240 |
+
- `fsdp_min_num_params`: 0
|
241 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
242 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
243 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
244 |
+
- `deepspeed`: None
|
245 |
+
- `label_smoothing_factor`: 0.0
|
246 |
+
- `optim`: adamw_torch
|
247 |
+
- `optim_args`: None
|
248 |
+
- `adafactor`: False
|
249 |
+
- `group_by_length`: False
|
250 |
+
- `length_column_name`: length
|
251 |
+
- `ddp_find_unused_parameters`: None
|
252 |
+
- `ddp_bucket_cap_mb`: None
|
253 |
+
- `ddp_broadcast_buffers`: False
|
254 |
+
- `dataloader_pin_memory`: True
|
255 |
+
- `dataloader_persistent_workers`: False
|
256 |
+
- `skip_memory_metrics`: True
|
257 |
+
- `use_legacy_prediction_loop`: False
|
258 |
+
- `push_to_hub`: False
|
259 |
+
- `resume_from_checkpoint`: None
|
260 |
+
- `hub_model_id`: None
|
261 |
+
- `hub_strategy`: every_save
|
262 |
+
- `hub_private_repo`: False
|
263 |
+
- `hub_always_push`: False
|
264 |
+
- `gradient_checkpointing`: False
|
265 |
+
- `gradient_checkpointing_kwargs`: None
|
266 |
+
- `include_inputs_for_metrics`: False
|
267 |
+
- `eval_do_concat_batches`: True
|
268 |
+
- `fp16_backend`: auto
|
269 |
+
- `push_to_hub_model_id`: None
|
270 |
+
- `push_to_hub_organization`: None
|
271 |
+
- `mp_parameters`:
|
272 |
+
- `auto_find_batch_size`: False
|
273 |
+
- `full_determinism`: False
|
274 |
+
- `torchdynamo`: None
|
275 |
+
- `ray_scope`: last
|
276 |
+
- `ddp_timeout`: 1800
|
277 |
+
- `torch_compile`: False
|
278 |
+
- `torch_compile_backend`: None
|
279 |
+
- `torch_compile_mode`: None
|
280 |
+
- `dispatch_batches`: None
|
281 |
+
- `split_batches`: None
|
282 |
+
- `include_tokens_per_second`: False
|
283 |
+
- `include_num_input_tokens_seen`: False
|
284 |
+
- `neftune_noise_alpha`: None
|
285 |
+
- `optim_target_modules`: None
|
286 |
+
- `batch_eval_metrics`: False
|
287 |
+
- `eval_on_start`: False
|
288 |
+
- `batch_sampler`: batch_sampler
|
289 |
+
- `multi_dataset_batch_sampler`: round_robin
|
290 |
+
|
291 |
+
</details>
|
292 |
+
|
293 |
+
### Training Logs
|
294 |
+
| Epoch | Step | Training Loss |
|
295 |
+
|:-----:|:-----:|:-------------:|
|
296 |
+
| 0.04 | 500 | 7.3777 |
|
297 |
+
| 0.08 | 1000 | 6.9771 |
|
298 |
+
| 0.12 | 1500 | 6.8481 |
|
299 |
+
| 0.16 | 2000 | 6.7737 |
|
300 |
+
| 0.2 | 2500 | 6.6935 |
|
301 |
+
| 0.24 | 3000 | 6.6264 |
|
302 |
+
| 0.28 | 3500 | 6.5918 |
|
303 |
+
| 0.32 | 4000 | 6.5504 |
|
304 |
+
| 0.36 | 4500 | 6.4805 |
|
305 |
+
| 0.4 | 5000 | 6.4539 |
|
306 |
+
| 0.44 | 5500 | 6.4242 |
|
307 |
+
| 0.48 | 6000 | 6.4017 |
|
308 |
+
| 0.52 | 6500 | 6.3808 |
|
309 |
+
| 0.56 | 7000 | 6.3595 |
|
310 |
+
| 0.6 | 7500 | 6.3174 |
|
311 |
+
| 0.64 | 8000 | 6.2911 |
|
312 |
+
| 0.68 | 8500 | 6.2917 |
|
313 |
+
| 0.72 | 9000 | 6.2555 |
|
314 |
+
| 0.76 | 9500 | 6.2314 |
|
315 |
+
| 0.8 | 10000 | 6.2223 |
|
316 |
+
| 0.84 | 10500 | 6.1852 |
|
317 |
+
| 0.88 | 11000 | 6.2067 |
|
318 |
+
| 0.92 | 11500 | 6.1562 |
|
319 |
+
| 0.96 | 12000 | 6.1563 |
|
320 |
+
| 1.0 | 12500 | 6.092 |
|
321 |
+
|
322 |
+
|
323 |
+
### Framework Versions
|
324 |
+
- Python: 3.10.12
|
325 |
+
- Sentence Transformers: 3.0.1
|
326 |
+
- Transformers: 4.42.4
|
327 |
+
- PyTorch: 2.3.1+cu121
|
328 |
+
- Accelerate: 0.32.1
|
329 |
+
- Datasets: 2.20.0
|
330 |
+
- Tokenizers: 0.19.1
|
331 |
+
|
332 |
+
## Citation
|
333 |
+
|
334 |
+
### BibTeX
|
335 |
+
|
336 |
+
#### Sentence Transformers
|
337 |
+
```bibtex
|
338 |
+
@inproceedings{reimers-2019-sentence-bert,
|
339 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
340 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
341 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
342 |
+
month = "11",
|
343 |
+
year = "2019",
|
344 |
+
publisher = "Association for Computational Linguistics",
|
345 |
+
url = "https://arxiv.org/abs/1908.10084",
|
346 |
+
}
|
347 |
+
```
|
348 |
+
|
349 |
+
#### DenoisingAutoEncoderLoss
|
350 |
+
```bibtex
|
351 |
+
@inproceedings{wang-2021-TSDAE,
|
352 |
+
title = "TSDAE: Using Transformer-based Sequential Denoising Auto-Encoderfor Unsupervised Sentence Embedding Learning",
|
353 |
+
author = "Wang, Kexin and Reimers, Nils and Gurevych, Iryna",
|
354 |
+
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
|
355 |
+
month = nov,
|
356 |
+
year = "2021",
|
357 |
+
address = "Punta Cana, Dominican Republic",
|
358 |
+
publisher = "Association for Computational Linguistics",
|
359 |
+
pages = "671--688",
|
360 |
+
url = "https://arxiv.org/abs/2104.06979",
|
361 |
+
}
|
362 |
+
```
|
363 |
+
|
364 |
+
<!--
|
365 |
+
## Glossary
|
366 |
+
|
367 |
+
*Clearly define terms in order to be accessible across audiences.*
|
368 |
+
-->
|
369 |
+
|
370 |
+
<!--
|
371 |
+
## Model Card Authors
|
372 |
+
|
373 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
374 |
+
-->
|
375 |
+
|
376 |
+
<!--
|
377 |
+
## Model Card Contact
|
378 |
+
|
379 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
380 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
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-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.42.4",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 30522
|
26 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "3.0.1",
|
4 |
+
"transformers": "4.42.4",
|
5 |
+
"pytorch": "2.3.1+cu121"
|
6 |
+
},
|
7 |
+
"prompts": {},
|
8 |
+
"default_prompt_name": null,
|
9 |
+
"similarity_fn_name": null
|
10 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8cf533c168592d6d49509431cffa1ce06a3cf8a62097efc0ec76a3e625e0d58
|
3 |
+
size 437951328
|
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": 512,
|
3 |
+
"do_lower_case": false
|
4 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "BertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|