Add new SentenceTransformer model.
Browse files- 1_Pooling/config.json +10 -0
- README.md +407 -0
- config.json +32 -0
- config_sentence_transformers.json +10 -0
- model.safetensors +3 -0
- modules.json +20 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -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 +1,407 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: BAAI/bge-base-en-v1.5
|
3 |
+
datasets: []
|
4 |
+
language:
|
5 |
+
- en
|
6 |
+
library_name: sentence-transformers
|
7 |
+
license: apache-2.0
|
8 |
+
pipeline_tag: sentence-similarity
|
9 |
+
tags:
|
10 |
+
- sentence-transformers
|
11 |
+
- sentence-similarity
|
12 |
+
- feature-extraction
|
13 |
+
- generated_from_trainer
|
14 |
+
- dataset_size:6300
|
15 |
+
- loss:MatryoshkaLoss
|
16 |
+
- loss:MultipleNegativesRankingLoss
|
17 |
+
widget:
|
18 |
+
- source_sentence: Additionally, we sell the ALLDATA brand of automotive diagnostic,
|
19 |
+
repair, collision, and shop management software through www.alldata.com.
|
20 |
+
sentences:
|
21 |
+
- What was the percentage change in total revenue from fiscal year 2022 to fiscal
|
22 |
+
year 2023?
|
23 |
+
- What type of software is sold through the website alldata.com?
|
24 |
+
- What tax implications apply to the future repatriation of incremental undistributed
|
25 |
+
earnings by a REIT from its foreign subsidiaries?
|
26 |
+
- source_sentence: As of October 31, 2023, the principal payments on debt were $9,585
|
27 |
+
million in total, with $216 million due as short-term and $9,369 million as long-term
|
28 |
+
obligations.
|
29 |
+
sentences:
|
30 |
+
- How is mall net operating income (NOI) useful in evaluating mall operating performance?
|
31 |
+
- What are the principal amounts for short-term and long-term debts to be paid as
|
32 |
+
of October 31, 2023?
|
33 |
+
- What was the main reason for the increase in the company's valuation allowance
|
34 |
+
during fiscal 2023?
|
35 |
+
- source_sentence: Revenues derived in the United States were $22,007 million, $18,749
|
36 |
+
million and $17,363 million for the fiscal years ended May 31, 2023, 2022 and
|
37 |
+
2021, respectively.
|
38 |
+
sentences:
|
39 |
+
- What were the revenues derived in the United States for the fiscal years ended
|
40 |
+
May 31, 2021, 2022, and 2023?
|
41 |
+
- When was the auditors' report on the financial statements dated?
|
42 |
+
- What was Richard C. Smith's role in AutoZone before being named Senior Vice President
|
43 |
+
– Human Resources?
|
44 |
+
- source_sentence: As of December 31, 2023, the accrued employee compensation and
|
45 |
+
benefits amounted to $592 million.
|
46 |
+
sentences:
|
47 |
+
- What was the outcome of the litigation regarding the Vermont net neutrality statute?
|
48 |
+
- What are included immediately following Part IV in the Annual Report on Form 10-K?
|
49 |
+
- What was the accrued employee compensation and benefits as of December 31, 2023?
|
50 |
+
- source_sentence: Diluted earnings per share were $16.69 in fiscal 2022 compared
|
51 |
+
to $15.53 in fiscal 2021.
|
52 |
+
sentences:
|
53 |
+
- By what amount did fiscal 2022 diluted earnings per share increase from fiscal
|
54 |
+
2021?
|
55 |
+
- What are the total noncancelable purchase commitments as of December 31, 2023,
|
56 |
+
and how are they distributed over different time periods?
|
57 |
+
- What is the purpose of internal control over financial reporting as implemented
|
58 |
+
by a company?
|
59 |
+
---
|
60 |
+
|
61 |
+
# BGE base Financial Matryoshka
|
62 |
+
|
63 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5). 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.
|
64 |
+
|
65 |
+
## Model Details
|
66 |
+
|
67 |
+
### Model Description
|
68 |
+
- **Model Type:** Sentence Transformer
|
69 |
+
- **Base model:** [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) <!-- at revision a5beb1e3e68b9ab74eb54cfd186867f64f240e1a -->
|
70 |
+
- **Maximum Sequence Length:** 512 tokens
|
71 |
+
- **Output Dimensionality:** 768 tokens
|
72 |
+
- **Similarity Function:** Cosine Similarity
|
73 |
+
<!-- - **Training Dataset:** Unknown -->
|
74 |
+
- **Language:** en
|
75 |
+
- **License:** apache-2.0
|
76 |
+
|
77 |
+
### Model Sources
|
78 |
+
|
79 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
80 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
81 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
82 |
+
|
83 |
+
### Full Model Architecture
|
84 |
+
|
85 |
+
```
|
86 |
+
SentenceTransformer(
|
87 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel
|
88 |
+
(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})
|
89 |
+
(2): Normalize()
|
90 |
+
)
|
91 |
+
```
|
92 |
+
|
93 |
+
## Usage
|
94 |
+
|
95 |
+
### Direct Usage (Sentence Transformers)
|
96 |
+
|
97 |
+
First install the Sentence Transformers library:
|
98 |
+
|
99 |
+
```bash
|
100 |
+
pip install -U sentence-transformers
|
101 |
+
```
|
102 |
+
|
103 |
+
Then you can load this model and run inference.
|
104 |
+
```python
|
105 |
+
from sentence_transformers import SentenceTransformer
|
106 |
+
|
107 |
+
# Download from the 🤗 Hub
|
108 |
+
model = SentenceTransformer("asprenger/bge-base-financial-matryoshka")
|
109 |
+
# Run inference
|
110 |
+
sentences = [
|
111 |
+
'Diluted earnings per share were $16.69 in fiscal 2022 compared to $15.53 in fiscal 2021.',
|
112 |
+
'By what amount did fiscal 2022 diluted earnings per share increase from fiscal 2021?',
|
113 |
+
'What are the total noncancelable purchase commitments as of December 31, 2023, and how are they distributed over different time periods?',
|
114 |
+
]
|
115 |
+
embeddings = model.encode(sentences)
|
116 |
+
print(embeddings.shape)
|
117 |
+
# [3, 768]
|
118 |
+
|
119 |
+
# Get the similarity scores for the embeddings
|
120 |
+
similarities = model.similarity(embeddings, embeddings)
|
121 |
+
print(similarities.shape)
|
122 |
+
# [3, 3]
|
123 |
+
```
|
124 |
+
|
125 |
+
<!--
|
126 |
+
### Direct Usage (Transformers)
|
127 |
+
|
128 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
129 |
+
|
130 |
+
</details>
|
131 |
+
-->
|
132 |
+
|
133 |
+
<!--
|
134 |
+
### Downstream Usage (Sentence Transformers)
|
135 |
+
|
136 |
+
You can finetune this model on your own dataset.
|
137 |
+
|
138 |
+
<details><summary>Click to expand</summary>
|
139 |
+
|
140 |
+
</details>
|
141 |
+
-->
|
142 |
+
|
143 |
+
<!--
|
144 |
+
### Out-of-Scope Use
|
145 |
+
|
146 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
147 |
+
-->
|
148 |
+
|
149 |
+
<!--
|
150 |
+
## Bias, Risks and Limitations
|
151 |
+
|
152 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
153 |
+
-->
|
154 |
+
|
155 |
+
<!--
|
156 |
+
### Recommendations
|
157 |
+
|
158 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
159 |
+
-->
|
160 |
+
|
161 |
+
## Training Details
|
162 |
+
|
163 |
+
### Training Dataset
|
164 |
+
|
165 |
+
#### Unnamed Dataset
|
166 |
+
|
167 |
+
|
168 |
+
* Size: 6,300 training samples
|
169 |
+
* Columns: <code>positive</code> and <code>anchor</code>
|
170 |
+
* Approximate statistics based on the first 1000 samples:
|
171 |
+
| | positive | anchor |
|
172 |
+
|:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
|
173 |
+
| type | string | string |
|
174 |
+
| details | <ul><li>min: 6 tokens</li><li>mean: 44.8 tokens</li><li>max: 260 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 20.57 tokens</li><li>max: 45 tokens</li></ul> |
|
175 |
+
* Samples:
|
176 |
+
| positive | anchor |
|
177 |
+
|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------|
|
178 |
+
| <code>Item 8 includes Financial Statements and Supplementary Data.</code> | <code>What does Item 8 in a financial document typically contain?</code> |
|
179 |
+
| <code>Intellectual property rights are important to Nike's brand, success, and competitive position. The company strategically pursues protections of these rights and vigorously protects them against third-party theft and infringement.</code> | <code>What role does intellectual property play in Nike's competitive position?</code> |
|
180 |
+
| <code>If the Company determines that it is more likely than not that the fair value of the reporting unit is less than its carrying amount, then the Company is required to perform a quantitative assessment for impairment. Under the quantitative goodwill impairment test, if a reporting unit’s carrying amount exceeds its fair value, an impairment loss is recognized in an amount equal to the excess, not to exceed the total amount of goodwill allocated to that reporting unit.</code> | <code>What process does a company follow if it determines that the fair value of a reporting unit is less than its carrying amount?</code> |
|
181 |
+
* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
|
182 |
+
```json
|
183 |
+
{
|
184 |
+
"loss": "MultipleNegativesRankingLoss",
|
185 |
+
"matryoshka_dims": [
|
186 |
+
768,
|
187 |
+
512,
|
188 |
+
256,
|
189 |
+
128,
|
190 |
+
64
|
191 |
+
],
|
192 |
+
"matryoshka_weights": [
|
193 |
+
1,
|
194 |
+
1,
|
195 |
+
1,
|
196 |
+
1,
|
197 |
+
1
|
198 |
+
],
|
199 |
+
"n_dims_per_step": -1
|
200 |
+
}
|
201 |
+
```
|
202 |
+
|
203 |
+
### Training Hyperparameters
|
204 |
+
#### Non-Default Hyperparameters
|
205 |
+
|
206 |
+
- `per_device_train_batch_size`: 32
|
207 |
+
- `per_device_eval_batch_size`: 16
|
208 |
+
- `gradient_accumulation_steps`: 16
|
209 |
+
- `learning_rate`: 2e-05
|
210 |
+
- `num_train_epochs`: 4
|
211 |
+
- `lr_scheduler_type`: cosine
|
212 |
+
- `warmup_ratio`: 0.1
|
213 |
+
- `bf16`: True
|
214 |
+
- `tf32`: True
|
215 |
+
- `optim`: adamw_torch_fused
|
216 |
+
- `batch_sampler`: no_duplicates
|
217 |
+
|
218 |
+
#### All Hyperparameters
|
219 |
+
<details><summary>Click to expand</summary>
|
220 |
+
|
221 |
+
- `overwrite_output_dir`: False
|
222 |
+
- `do_predict`: False
|
223 |
+
- `eval_strategy`: no
|
224 |
+
- `prediction_loss_only`: True
|
225 |
+
- `per_device_train_batch_size`: 32
|
226 |
+
- `per_device_eval_batch_size`: 16
|
227 |
+
- `per_gpu_train_batch_size`: None
|
228 |
+
- `per_gpu_eval_batch_size`: None
|
229 |
+
- `gradient_accumulation_steps`: 16
|
230 |
+
- `eval_accumulation_steps`: None
|
231 |
+
- `learning_rate`: 2e-05
|
232 |
+
- `weight_decay`: 0.0
|
233 |
+
- `adam_beta1`: 0.9
|
234 |
+
- `adam_beta2`: 0.999
|
235 |
+
- `adam_epsilon`: 1e-08
|
236 |
+
- `max_grad_norm`: 1.0
|
237 |
+
- `num_train_epochs`: 4
|
238 |
+
- `max_steps`: -1
|
239 |
+
- `lr_scheduler_type`: cosine
|
240 |
+
- `lr_scheduler_kwargs`: {}
|
241 |
+
- `warmup_ratio`: 0.1
|
242 |
+
- `warmup_steps`: 0
|
243 |
+
- `log_level`: passive
|
244 |
+
- `log_level_replica`: warning
|
245 |
+
- `log_on_each_node`: True
|
246 |
+
- `logging_nan_inf_filter`: True
|
247 |
+
- `save_safetensors`: True
|
248 |
+
- `save_on_each_node`: False
|
249 |
+
- `save_only_model`: False
|
250 |
+
- `restore_callback_states_from_checkpoint`: False
|
251 |
+
- `no_cuda`: False
|
252 |
+
- `use_cpu`: False
|
253 |
+
- `use_mps_device`: False
|
254 |
+
- `seed`: 42
|
255 |
+
- `data_seed`: None
|
256 |
+
- `jit_mode_eval`: False
|
257 |
+
- `use_ipex`: False
|
258 |
+
- `bf16`: True
|
259 |
+
- `fp16`: False
|
260 |
+
- `fp16_opt_level`: O1
|
261 |
+
- `half_precision_backend`: auto
|
262 |
+
- `bf16_full_eval`: False
|
263 |
+
- `fp16_full_eval`: False
|
264 |
+
- `tf32`: True
|
265 |
+
- `local_rank`: 0
|
266 |
+
- `ddp_backend`: None
|
267 |
+
- `tpu_num_cores`: None
|
268 |
+
- `tpu_metrics_debug`: False
|
269 |
+
- `debug`: []
|
270 |
+
- `dataloader_drop_last`: False
|
271 |
+
- `dataloader_num_workers`: 0
|
272 |
+
- `dataloader_prefetch_factor`: None
|
273 |
+
- `past_index`: -1
|
274 |
+
- `disable_tqdm`: False
|
275 |
+
- `remove_unused_columns`: True
|
276 |
+
- `label_names`: None
|
277 |
+
- `load_best_model_at_end`: False
|
278 |
+
- `ignore_data_skip`: False
|
279 |
+
- `fsdp`: []
|
280 |
+
- `fsdp_min_num_params`: 0
|
281 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
282 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
283 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
284 |
+
- `deepspeed`: None
|
285 |
+
- `label_smoothing_factor`: 0.0
|
286 |
+
- `optim`: adamw_torch_fused
|
287 |
+
- `optim_args`: None
|
288 |
+
- `adafactor`: False
|
289 |
+
- `group_by_length`: False
|
290 |
+
- `length_column_name`: length
|
291 |
+
- `ddp_find_unused_parameters`: None
|
292 |
+
- `ddp_bucket_cap_mb`: None
|
293 |
+
- `ddp_broadcast_buffers`: False
|
294 |
+
- `dataloader_pin_memory`: True
|
295 |
+
- `dataloader_persistent_workers`: False
|
296 |
+
- `skip_memory_metrics`: True
|
297 |
+
- `use_legacy_prediction_loop`: False
|
298 |
+
- `push_to_hub`: False
|
299 |
+
- `resume_from_checkpoint`: None
|
300 |
+
- `hub_model_id`: None
|
301 |
+
- `hub_strategy`: every_save
|
302 |
+
- `hub_private_repo`: False
|
303 |
+
- `hub_always_push`: False
|
304 |
+
- `gradient_checkpointing`: False
|
305 |
+
- `gradient_checkpointing_kwargs`: None
|
306 |
+
- `include_inputs_for_metrics`: False
|
307 |
+
- `eval_do_concat_batches`: True
|
308 |
+
- `fp16_backend`: auto
|
309 |
+
- `push_to_hub_model_id`: None
|
310 |
+
- `push_to_hub_organization`: None
|
311 |
+
- `mp_parameters`:
|
312 |
+
- `auto_find_batch_size`: False
|
313 |
+
- `full_determinism`: False
|
314 |
+
- `torchdynamo`: None
|
315 |
+
- `ray_scope`: last
|
316 |
+
- `ddp_timeout`: 1800
|
317 |
+
- `torch_compile`: False
|
318 |
+
- `torch_compile_backend`: None
|
319 |
+
- `torch_compile_mode`: None
|
320 |
+
- `dispatch_batches`: None
|
321 |
+
- `split_batches`: None
|
322 |
+
- `include_tokens_per_second`: False
|
323 |
+
- `include_num_input_tokens_seen`: False
|
324 |
+
- `neftune_noise_alpha`: None
|
325 |
+
- `optim_target_modules`: None
|
326 |
+
- `batch_eval_metrics`: False
|
327 |
+
- `batch_sampler`: no_duplicates
|
328 |
+
- `multi_dataset_batch_sampler`: proportional
|
329 |
+
|
330 |
+
</details>
|
331 |
+
|
332 |
+
### Training Logs
|
333 |
+
| Epoch | Step | Training Loss |
|
334 |
+
|:------:|:----:|:-------------:|
|
335 |
+
| 0.8122 | 10 | 1.5567 |
|
336 |
+
| 1.6244 | 20 | 0.6836 |
|
337 |
+
| 2.4365 | 30 | 0.473 |
|
338 |
+
| 3.2487 | 40 | 0.3917 |
|
339 |
+
|
340 |
+
|
341 |
+
### Framework Versions
|
342 |
+
- Python: 3.10.12
|
343 |
+
- Sentence Transformers: 3.0.1
|
344 |
+
- Transformers: 4.41.2
|
345 |
+
- PyTorch: 2.1.2+cu121
|
346 |
+
- Accelerate: 0.32.1
|
347 |
+
- Datasets: 2.19.1
|
348 |
+
- Tokenizers: 0.19.1
|
349 |
+
|
350 |
+
## Citation
|
351 |
+
|
352 |
+
### BibTeX
|
353 |
+
|
354 |
+
#### Sentence Transformers
|
355 |
+
```bibtex
|
356 |
+
@inproceedings{reimers-2019-sentence-bert,
|
357 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
358 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
359 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
360 |
+
month = "11",
|
361 |
+
year = "2019",
|
362 |
+
publisher = "Association for Computational Linguistics",
|
363 |
+
url = "https://arxiv.org/abs/1908.10084",
|
364 |
+
}
|
365 |
+
```
|
366 |
+
|
367 |
+
#### MatryoshkaLoss
|
368 |
+
```bibtex
|
369 |
+
@misc{kusupati2024matryoshka,
|
370 |
+
title={Matryoshka Representation Learning},
|
371 |
+
author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
|
372 |
+
year={2024},
|
373 |
+
eprint={2205.13147},
|
374 |
+
archivePrefix={arXiv},
|
375 |
+
primaryClass={cs.LG}
|
376 |
+
}
|
377 |
+
```
|
378 |
+
|
379 |
+
#### MultipleNegativesRankingLoss
|
380 |
+
```bibtex
|
381 |
+
@misc{henderson2017efficient,
|
382 |
+
title={Efficient Natural Language Response Suggestion for Smart Reply},
|
383 |
+
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},
|
384 |
+
year={2017},
|
385 |
+
eprint={1705.00652},
|
386 |
+
archivePrefix={arXiv},
|
387 |
+
primaryClass={cs.CL}
|
388 |
+
}
|
389 |
+
```
|
390 |
+
|
391 |
+
<!--
|
392 |
+
## Glossary
|
393 |
+
|
394 |
+
*Clearly define terms in order to be accessible across audiences.*
|
395 |
+
-->
|
396 |
+
|
397 |
+
<!--
|
398 |
+
## Model Card Authors
|
399 |
+
|
400 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
401 |
+
-->
|
402 |
+
|
403 |
+
<!--
|
404 |
+
## Model Card Contact
|
405 |
+
|
406 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
407 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "BAAI/bge-base-en-v1.5",
|
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 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 3072,
|
17 |
+
"label2id": {
|
18 |
+
"LABEL_0": 0
|
19 |
+
},
|
20 |
+
"layer_norm_eps": 1e-12,
|
21 |
+
"max_position_embeddings": 512,
|
22 |
+
"model_type": "bert",
|
23 |
+
"num_attention_heads": 12,
|
24 |
+
"num_hidden_layers": 12,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"position_embedding_type": "absolute",
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.41.2",
|
29 |
+
"type_vocab_size": 2,
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 30522
|
32 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "3.0.1",
|
4 |
+
"transformers": "4.41.2",
|
5 |
+
"pytorch": "2.1.2+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:ec4b2b716220a597ca340d50aa35372588beb5b29e5229d84e36f7358125228b
|
3 |
+
size 437951328
|
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 |
+
]
|
sentence_bert_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"max_seq_length": 512,
|
3 |
+
"do_lower_case": true
|
4 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "BertTokenizer",
|
56 |
+
"unk_token": "[UNK]"
|
57 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|