Commit
•
4ad8185
1
Parent(s):
f59da82
Add new SentenceTransformer model.
Browse files- 1_Pooling/config.json +10 -0
- README.md +733 -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 +1,733 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
license: apache-2.0
|
5 |
+
library_name: sentence-transformers
|
6 |
+
tags:
|
7 |
+
- sentence-transformers
|
8 |
+
- sentence-similarity
|
9 |
+
- feature-extraction
|
10 |
+
- generated_from_trainer
|
11 |
+
- dataset_size:6300
|
12 |
+
- loss:MatryoshkaLoss
|
13 |
+
- loss:MultipleNegativesRankingLoss
|
14 |
+
base_model: BAAI/bge-base-en-v1.5
|
15 |
+
datasets: []
|
16 |
+
metrics:
|
17 |
+
- cosine_accuracy@1
|
18 |
+
- cosine_accuracy@3
|
19 |
+
- cosine_accuracy@5
|
20 |
+
- cosine_accuracy@10
|
21 |
+
- cosine_precision@1
|
22 |
+
- cosine_precision@3
|
23 |
+
- cosine_precision@5
|
24 |
+
- cosine_precision@10
|
25 |
+
- cosine_recall@1
|
26 |
+
- cosine_recall@3
|
27 |
+
- cosine_recall@5
|
28 |
+
- cosine_recall@10
|
29 |
+
- cosine_ndcg@10
|
30 |
+
- cosine_mrr@10
|
31 |
+
- cosine_map@100
|
32 |
+
widget:
|
33 |
+
- source_sentence: On December 15, 2022, the European Union Member States formally
|
34 |
+
adopted the EU’s Pillar Two Directive, which generally provides for a minimum
|
35 |
+
effective tax rate of 15%.
|
36 |
+
sentences:
|
37 |
+
- What were the key business segments of The Goldman Sachs Group, Inc. as reported
|
38 |
+
in their 2023 financial disclosures?
|
39 |
+
- What are the aspects of the EU Pillar Two Directive adopted in December 2022?
|
40 |
+
- How does customer size and geography affect the determination of SSP for products
|
41 |
+
and services?
|
42 |
+
- source_sentence: Schwab's management of credit risk involves policies and procedures
|
43 |
+
that include setting and reviewing credit limits, monitoring of credit limits
|
44 |
+
and quality of counterparties, and adjusting margin, PAL, option, and futures
|
45 |
+
requirements for certain securities and instruments.
|
46 |
+
sentences:
|
47 |
+
- What measures does Schwab take to manage credit risk?
|
48 |
+
- How might a 10% change in the obsolescence reserve percentage impact net earnings?
|
49 |
+
- How did the discount rates for Depop and Elo7 change during their 2022 impairments
|
50 |
+
analysis?
|
51 |
+
- source_sentence: While we believe that our ESG goals align with our long-term growth
|
52 |
+
strategy and financial and operational priorities, they are aspirational and may
|
53 |
+
change, and there is no guarantee or promise that they will be met.
|
54 |
+
sentences:
|
55 |
+
- What is the relationship between the ESG goals and the long-term growth strategy?
|
56 |
+
- What was the total revenue in millions for 2023 according to the disaggregated
|
57 |
+
revenue information by segment?
|
58 |
+
- How much did the net cumulative medical payments amount to in 2023?
|
59 |
+
- source_sentence: The total unrealized losses on U.S. Treasury securities amounted
|
60 |
+
to $134 million.
|
61 |
+
sentences:
|
62 |
+
- What critical audit matters were identified related to the revenue recognition
|
63 |
+
in the Connectivity & Platforms businesses at Comcast in 2023?
|
64 |
+
- What were the total unrealized losses on U.S. Treasury securities as of the last
|
65 |
+
reporting date?
|
66 |
+
- How is Revenue per Available Room (RevPAR) calculated and what does it indicate?
|
67 |
+
- source_sentence: The Chief Executive etc. does not manage segment results or allocate
|
68 |
+
resources to segments when considering these costs and they are therefore excluded
|
69 |
+
from our definition of segment income.
|
70 |
+
sentences:
|
71 |
+
- How are tax returns affecting the company's tax provisions when audited?
|
72 |
+
- What was the increase in sales and marketing expenses for the year ended December
|
73 |
+
31, 2023 compared to 2022?
|
74 |
+
- What components are excluded from segment income definition according to company
|
75 |
+
management?
|
76 |
+
pipeline_tag: sentence-similarity
|
77 |
+
model-index:
|
78 |
+
- name: BGE base Financial Matryoshka
|
79 |
+
results:
|
80 |
+
- task:
|
81 |
+
type: information-retrieval
|
82 |
+
name: Information Retrieval
|
83 |
+
dataset:
|
84 |
+
name: dim 768
|
85 |
+
type: dim_768
|
86 |
+
metrics:
|
87 |
+
- type: cosine_accuracy@1
|
88 |
+
value: 0.7142857142857143
|
89 |
+
name: Cosine Accuracy@1
|
90 |
+
- type: cosine_accuracy@3
|
91 |
+
value: 0.83
|
92 |
+
name: Cosine Accuracy@3
|
93 |
+
- type: cosine_accuracy@5
|
94 |
+
value: 0.8585714285714285
|
95 |
+
name: Cosine Accuracy@5
|
96 |
+
- type: cosine_accuracy@10
|
97 |
+
value: 0.9042857142857142
|
98 |
+
name: Cosine Accuracy@10
|
99 |
+
- type: cosine_precision@1
|
100 |
+
value: 0.7142857142857143
|
101 |
+
name: Cosine Precision@1
|
102 |
+
- type: cosine_precision@3
|
103 |
+
value: 0.27666666666666667
|
104 |
+
name: Cosine Precision@3
|
105 |
+
- type: cosine_precision@5
|
106 |
+
value: 0.1717142857142857
|
107 |
+
name: Cosine Precision@5
|
108 |
+
- type: cosine_precision@10
|
109 |
+
value: 0.09042857142857141
|
110 |
+
name: Cosine Precision@10
|
111 |
+
- type: cosine_recall@1
|
112 |
+
value: 0.7142857142857143
|
113 |
+
name: Cosine Recall@1
|
114 |
+
- type: cosine_recall@3
|
115 |
+
value: 0.83
|
116 |
+
name: Cosine Recall@3
|
117 |
+
- type: cosine_recall@5
|
118 |
+
value: 0.8585714285714285
|
119 |
+
name: Cosine Recall@5
|
120 |
+
- type: cosine_recall@10
|
121 |
+
value: 0.9042857142857142
|
122 |
+
name: Cosine Recall@10
|
123 |
+
- type: cosine_ndcg@10
|
124 |
+
value: 0.8098414318705203
|
125 |
+
name: Cosine Ndcg@10
|
126 |
+
- type: cosine_mrr@10
|
127 |
+
value: 0.7796729024943311
|
128 |
+
name: Cosine Mrr@10
|
129 |
+
- type: cosine_map@100
|
130 |
+
value: 0.7831593716959953
|
131 |
+
name: Cosine Map@100
|
132 |
+
- task:
|
133 |
+
type: information-retrieval
|
134 |
+
name: Information Retrieval
|
135 |
+
dataset:
|
136 |
+
name: dim 512
|
137 |
+
type: dim_512
|
138 |
+
metrics:
|
139 |
+
- type: cosine_accuracy@1
|
140 |
+
value: 0.7157142857142857
|
141 |
+
name: Cosine Accuracy@1
|
142 |
+
- type: cosine_accuracy@3
|
143 |
+
value: 0.8242857142857143
|
144 |
+
name: Cosine Accuracy@3
|
145 |
+
- type: cosine_accuracy@5
|
146 |
+
value: 0.8542857142857143
|
147 |
+
name: Cosine Accuracy@5
|
148 |
+
- type: cosine_accuracy@10
|
149 |
+
value: 0.8942857142857142
|
150 |
+
name: Cosine Accuracy@10
|
151 |
+
- type: cosine_precision@1
|
152 |
+
value: 0.7157142857142857
|
153 |
+
name: Cosine Precision@1
|
154 |
+
- type: cosine_precision@3
|
155 |
+
value: 0.27476190476190476
|
156 |
+
name: Cosine Precision@3
|
157 |
+
- type: cosine_precision@5
|
158 |
+
value: 0.17085714285714285
|
159 |
+
name: Cosine Precision@5
|
160 |
+
- type: cosine_precision@10
|
161 |
+
value: 0.08942857142857143
|
162 |
+
name: Cosine Precision@10
|
163 |
+
- type: cosine_recall@1
|
164 |
+
value: 0.7157142857142857
|
165 |
+
name: Cosine Recall@1
|
166 |
+
- type: cosine_recall@3
|
167 |
+
value: 0.8242857142857143
|
168 |
+
name: Cosine Recall@3
|
169 |
+
- type: cosine_recall@5
|
170 |
+
value: 0.8542857142857143
|
171 |
+
name: Cosine Recall@5
|
172 |
+
- type: cosine_recall@10
|
173 |
+
value: 0.8942857142857142
|
174 |
+
name: Cosine Recall@10
|
175 |
+
- type: cosine_ndcg@10
|
176 |
+
value: 0.805674034217217
|
177 |
+
name: Cosine Ndcg@10
|
178 |
+
- type: cosine_mrr@10
|
179 |
+
value: 0.7771672335600905
|
180 |
+
name: Cosine Mrr@10
|
181 |
+
- type: cosine_map@100
|
182 |
+
value: 0.7814319590791096
|
183 |
+
name: Cosine Map@100
|
184 |
+
- task:
|
185 |
+
type: information-retrieval
|
186 |
+
name: Information Retrieval
|
187 |
+
dataset:
|
188 |
+
name: dim 256
|
189 |
+
type: dim_256
|
190 |
+
metrics:
|
191 |
+
- type: cosine_accuracy@1
|
192 |
+
value: 0.7057142857142857
|
193 |
+
name: Cosine Accuracy@1
|
194 |
+
- type: cosine_accuracy@3
|
195 |
+
value: 0.8185714285714286
|
196 |
+
name: Cosine Accuracy@3
|
197 |
+
- type: cosine_accuracy@5
|
198 |
+
value: 0.8528571428571429
|
199 |
+
name: Cosine Accuracy@5
|
200 |
+
- type: cosine_accuracy@10
|
201 |
+
value: 0.8928571428571429
|
202 |
+
name: Cosine Accuracy@10
|
203 |
+
- type: cosine_precision@1
|
204 |
+
value: 0.7057142857142857
|
205 |
+
name: Cosine Precision@1
|
206 |
+
- type: cosine_precision@3
|
207 |
+
value: 0.27285714285714285
|
208 |
+
name: Cosine Precision@3
|
209 |
+
- type: cosine_precision@5
|
210 |
+
value: 0.17057142857142857
|
211 |
+
name: Cosine Precision@5
|
212 |
+
- type: cosine_precision@10
|
213 |
+
value: 0.08928571428571427
|
214 |
+
name: Cosine Precision@10
|
215 |
+
- type: cosine_recall@1
|
216 |
+
value: 0.7057142857142857
|
217 |
+
name: Cosine Recall@1
|
218 |
+
- type: cosine_recall@3
|
219 |
+
value: 0.8185714285714286
|
220 |
+
name: Cosine Recall@3
|
221 |
+
- type: cosine_recall@5
|
222 |
+
value: 0.8528571428571429
|
223 |
+
name: Cosine Recall@5
|
224 |
+
- type: cosine_recall@10
|
225 |
+
value: 0.8928571428571429
|
226 |
+
name: Cosine Recall@10
|
227 |
+
- type: cosine_ndcg@10
|
228 |
+
value: 0.7998364446362882
|
229 |
+
name: Cosine Ndcg@10
|
230 |
+
- type: cosine_mrr@10
|
231 |
+
value: 0.7700413832199544
|
232 |
+
name: Cosine Mrr@10
|
233 |
+
- type: cosine_map@100
|
234 |
+
value: 0.7739467761950781
|
235 |
+
name: Cosine Map@100
|
236 |
+
- task:
|
237 |
+
type: information-retrieval
|
238 |
+
name: Information Retrieval
|
239 |
+
dataset:
|
240 |
+
name: dim 128
|
241 |
+
type: dim_128
|
242 |
+
metrics:
|
243 |
+
- type: cosine_accuracy@1
|
244 |
+
value: 0.6871428571428572
|
245 |
+
name: Cosine Accuracy@1
|
246 |
+
- type: cosine_accuracy@3
|
247 |
+
value: 0.8057142857142857
|
248 |
+
name: Cosine Accuracy@3
|
249 |
+
- type: cosine_accuracy@5
|
250 |
+
value: 0.8385714285714285
|
251 |
+
name: Cosine Accuracy@5
|
252 |
+
- type: cosine_accuracy@10
|
253 |
+
value: 0.8871428571428571
|
254 |
+
name: Cosine Accuracy@10
|
255 |
+
- type: cosine_precision@1
|
256 |
+
value: 0.6871428571428572
|
257 |
+
name: Cosine Precision@1
|
258 |
+
- type: cosine_precision@3
|
259 |
+
value: 0.26857142857142857
|
260 |
+
name: Cosine Precision@3
|
261 |
+
- type: cosine_precision@5
|
262 |
+
value: 0.1677142857142857
|
263 |
+
name: Cosine Precision@5
|
264 |
+
- type: cosine_precision@10
|
265 |
+
value: 0.0887142857142857
|
266 |
+
name: Cosine Precision@10
|
267 |
+
- type: cosine_recall@1
|
268 |
+
value: 0.6871428571428572
|
269 |
+
name: Cosine Recall@1
|
270 |
+
- type: cosine_recall@3
|
271 |
+
value: 0.8057142857142857
|
272 |
+
name: Cosine Recall@3
|
273 |
+
- type: cosine_recall@5
|
274 |
+
value: 0.8385714285714285
|
275 |
+
name: Cosine Recall@5
|
276 |
+
- type: cosine_recall@10
|
277 |
+
value: 0.8871428571428571
|
278 |
+
name: Cosine Recall@10
|
279 |
+
- type: cosine_ndcg@10
|
280 |
+
value: 0.7864888199817319
|
281 |
+
name: Cosine Ndcg@10
|
282 |
+
- type: cosine_mrr@10
|
283 |
+
value: 0.7544109977324263
|
284 |
+
name: Cosine Mrr@10
|
285 |
+
- type: cosine_map@100
|
286 |
+
value: 0.7584408188949701
|
287 |
+
name: Cosine Map@100
|
288 |
+
---
|
289 |
+
|
290 |
+
# BGE base Financial Matryoshka
|
291 |
+
|
292 |
+
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.
|
293 |
+
|
294 |
+
## Model Details
|
295 |
+
|
296 |
+
### Model Description
|
297 |
+
- **Model Type:** Sentence Transformer
|
298 |
+
- **Base model:** [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) <!-- at revision a5beb1e3e68b9ab74eb54cfd186867f64f240e1a -->
|
299 |
+
- **Maximum Sequence Length:** 512 tokens
|
300 |
+
- **Output Dimensionality:** 768 tokens
|
301 |
+
- **Similarity Function:** Cosine Similarity
|
302 |
+
<!-- - **Training Dataset:** Unknown -->
|
303 |
+
- **Language:** en
|
304 |
+
- **License:** apache-2.0
|
305 |
+
|
306 |
+
### Model Sources
|
307 |
+
|
308 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
309 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
310 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
311 |
+
|
312 |
+
### Full Model Architecture
|
313 |
+
|
314 |
+
```
|
315 |
+
SentenceTransformer(
|
316 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel
|
317 |
+
(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})
|
318 |
+
(2): Normalize()
|
319 |
+
)
|
320 |
+
```
|
321 |
+
|
322 |
+
## Usage
|
323 |
+
|
324 |
+
### Direct Usage (Sentence Transformers)
|
325 |
+
|
326 |
+
First install the Sentence Transformers library:
|
327 |
+
|
328 |
+
```bash
|
329 |
+
pip install -U sentence-transformers
|
330 |
+
```
|
331 |
+
|
332 |
+
Then you can load this model and run inference.
|
333 |
+
```python
|
334 |
+
from sentence_transformers import SentenceTransformer
|
335 |
+
|
336 |
+
# Download from the 🤗 Hub
|
337 |
+
model = SentenceTransformer("pavanmantha/bge-base-en-sec10k-embed")
|
338 |
+
# Run inference
|
339 |
+
sentences = [
|
340 |
+
'The Chief Executive etc. does not manage segment results or allocate resources to segments when considering these costs and they are therefore excluded from our definition of segment income.',
|
341 |
+
'What components are excluded from segment income definition according to company management?',
|
342 |
+
'What was the increase in sales and marketing expenses for the year ended December 31, 2023 compared to 2022?',
|
343 |
+
]
|
344 |
+
embeddings = model.encode(sentences)
|
345 |
+
print(embeddings.shape)
|
346 |
+
# [3, 768]
|
347 |
+
|
348 |
+
# Get the similarity scores for the embeddings
|
349 |
+
similarities = model.similarity(embeddings, embeddings)
|
350 |
+
print(similarities.shape)
|
351 |
+
# [3, 3]
|
352 |
+
```
|
353 |
+
|
354 |
+
<!--
|
355 |
+
### Direct Usage (Transformers)
|
356 |
+
|
357 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
358 |
+
|
359 |
+
</details>
|
360 |
+
-->
|
361 |
+
|
362 |
+
<!--
|
363 |
+
### Downstream Usage (Sentence Transformers)
|
364 |
+
|
365 |
+
You can finetune this model on your own dataset.
|
366 |
+
|
367 |
+
<details><summary>Click to expand</summary>
|
368 |
+
|
369 |
+
</details>
|
370 |
+
-->
|
371 |
+
|
372 |
+
<!--
|
373 |
+
### Out-of-Scope Use
|
374 |
+
|
375 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
376 |
+
-->
|
377 |
+
|
378 |
+
## Evaluation
|
379 |
+
|
380 |
+
### Metrics
|
381 |
+
|
382 |
+
#### Information Retrieval
|
383 |
+
* Dataset: `dim_768`
|
384 |
+
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
|
385 |
+
|
386 |
+
| Metric | Value |
|
387 |
+
|:--------------------|:-----------|
|
388 |
+
| cosine_accuracy@1 | 0.7143 |
|
389 |
+
| cosine_accuracy@3 | 0.83 |
|
390 |
+
| cosine_accuracy@5 | 0.8586 |
|
391 |
+
| cosine_accuracy@10 | 0.9043 |
|
392 |
+
| cosine_precision@1 | 0.7143 |
|
393 |
+
| cosine_precision@3 | 0.2767 |
|
394 |
+
| cosine_precision@5 | 0.1717 |
|
395 |
+
| cosine_precision@10 | 0.0904 |
|
396 |
+
| cosine_recall@1 | 0.7143 |
|
397 |
+
| cosine_recall@3 | 0.83 |
|
398 |
+
| cosine_recall@5 | 0.8586 |
|
399 |
+
| cosine_recall@10 | 0.9043 |
|
400 |
+
| cosine_ndcg@10 | 0.8098 |
|
401 |
+
| cosine_mrr@10 | 0.7797 |
|
402 |
+
| **cosine_map@100** | **0.7832** |
|
403 |
+
|
404 |
+
#### Information Retrieval
|
405 |
+
* Dataset: `dim_512`
|
406 |
+
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
|
407 |
+
|
408 |
+
| Metric | Value |
|
409 |
+
|:--------------------|:-----------|
|
410 |
+
| cosine_accuracy@1 | 0.7157 |
|
411 |
+
| cosine_accuracy@3 | 0.8243 |
|
412 |
+
| cosine_accuracy@5 | 0.8543 |
|
413 |
+
| cosine_accuracy@10 | 0.8943 |
|
414 |
+
| cosine_precision@1 | 0.7157 |
|
415 |
+
| cosine_precision@3 | 0.2748 |
|
416 |
+
| cosine_precision@5 | 0.1709 |
|
417 |
+
| cosine_precision@10 | 0.0894 |
|
418 |
+
| cosine_recall@1 | 0.7157 |
|
419 |
+
| cosine_recall@3 | 0.8243 |
|
420 |
+
| cosine_recall@5 | 0.8543 |
|
421 |
+
| cosine_recall@10 | 0.8943 |
|
422 |
+
| cosine_ndcg@10 | 0.8057 |
|
423 |
+
| cosine_mrr@10 | 0.7772 |
|
424 |
+
| **cosine_map@100** | **0.7814** |
|
425 |
+
|
426 |
+
#### Information Retrieval
|
427 |
+
* Dataset: `dim_256`
|
428 |
+
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
|
429 |
+
|
430 |
+
| Metric | Value |
|
431 |
+
|:--------------------|:-----------|
|
432 |
+
| cosine_accuracy@1 | 0.7057 |
|
433 |
+
| cosine_accuracy@3 | 0.8186 |
|
434 |
+
| cosine_accuracy@5 | 0.8529 |
|
435 |
+
| cosine_accuracy@10 | 0.8929 |
|
436 |
+
| cosine_precision@1 | 0.7057 |
|
437 |
+
| cosine_precision@3 | 0.2729 |
|
438 |
+
| cosine_precision@5 | 0.1706 |
|
439 |
+
| cosine_precision@10 | 0.0893 |
|
440 |
+
| cosine_recall@1 | 0.7057 |
|
441 |
+
| cosine_recall@3 | 0.8186 |
|
442 |
+
| cosine_recall@5 | 0.8529 |
|
443 |
+
| cosine_recall@10 | 0.8929 |
|
444 |
+
| cosine_ndcg@10 | 0.7998 |
|
445 |
+
| cosine_mrr@10 | 0.77 |
|
446 |
+
| **cosine_map@100** | **0.7739** |
|
447 |
+
|
448 |
+
#### Information Retrieval
|
449 |
+
* Dataset: `dim_128`
|
450 |
+
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
|
451 |
+
|
452 |
+
| Metric | Value |
|
453 |
+
|:--------------------|:-----------|
|
454 |
+
| cosine_accuracy@1 | 0.6871 |
|
455 |
+
| cosine_accuracy@3 | 0.8057 |
|
456 |
+
| cosine_accuracy@5 | 0.8386 |
|
457 |
+
| cosine_accuracy@10 | 0.8871 |
|
458 |
+
| cosine_precision@1 | 0.6871 |
|
459 |
+
| cosine_precision@3 | 0.2686 |
|
460 |
+
| cosine_precision@5 | 0.1677 |
|
461 |
+
| cosine_precision@10 | 0.0887 |
|
462 |
+
| cosine_recall@1 | 0.6871 |
|
463 |
+
| cosine_recall@3 | 0.8057 |
|
464 |
+
| cosine_recall@5 | 0.8386 |
|
465 |
+
| cosine_recall@10 | 0.8871 |
|
466 |
+
| cosine_ndcg@10 | 0.7865 |
|
467 |
+
| cosine_mrr@10 | 0.7544 |
|
468 |
+
| **cosine_map@100** | **0.7584** |
|
469 |
+
|
470 |
+
<!--
|
471 |
+
## Bias, Risks and Limitations
|
472 |
+
|
473 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
474 |
+
-->
|
475 |
+
|
476 |
+
<!--
|
477 |
+
### Recommendations
|
478 |
+
|
479 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
480 |
+
-->
|
481 |
+
|
482 |
+
## Training Details
|
483 |
+
|
484 |
+
### Training Dataset
|
485 |
+
|
486 |
+
#### Unnamed Dataset
|
487 |
+
|
488 |
+
|
489 |
+
* Size: 6,300 training samples
|
490 |
+
* Columns: <code>positive</code> and <code>anchor</code>
|
491 |
+
* Approximate statistics based on the first 1000 samples:
|
492 |
+
| | positive | anchor |
|
493 |
+
|:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
|
494 |
+
| type | string | string |
|
495 |
+
| details | <ul><li>min: 9 tokens</li><li>mean: 46.84 tokens</li><li>max: 326 tokens</li></ul> | <ul><li>min: 8 tokens</li><li>mean: 20.44 tokens</li><li>max: 43 tokens</li></ul> |
|
496 |
+
* Samples:
|
497 |
+
| positive | anchor |
|
498 |
+
|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------|
|
499 |
+
| <code>The federal banking regulators’ guidance on sound incentive compensation practices sets forth three key principles for incentive compensation arrangements that are designed to help ensure such plans do not encourage imprudent risk-taking and align with the safety and soundness of the organization. These principles include balancing risk with financial results, compatibility with internal controls and risk management, and support from strong corporate governance with effective oversight by the board.</code> | <code>What are the three principles set forth by federal banking regulators' guidance on incentive compensation practices?</code> |
|
500 |
+
| <code>Delta Air Lines generated a free cash flow of $2,003 million in 2023. This figure was adjusted for several factors including net redemptions of short-term investments and a pilot agreement payment of $735 million.</code> | <code>How much free cash flow did Delta Air Lines generate in 2023?</code> |
|
501 |
+
| <code>Inherent in the qualitative assessment are estimates and assumptions about our consideration of events and circumstances that may indicate a potential impairment, including industry and market conditions, expected cost pressures, expected financial performance, and general macroeconomic conditions.</code> | <code>What does the qualitative assessment of goodwill consider regarding possible impairment?</code> |
|
502 |
+
* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
|
503 |
+
```json
|
504 |
+
{
|
505 |
+
"loss": "MultipleNegativesRankingLoss",
|
506 |
+
"matryoshka_dims": [
|
507 |
+
768,
|
508 |
+
512,
|
509 |
+
256,
|
510 |
+
128
|
511 |
+
],
|
512 |
+
"matryoshka_weights": [
|
513 |
+
1,
|
514 |
+
1,
|
515 |
+
1,
|
516 |
+
1
|
517 |
+
],
|
518 |
+
"n_dims_per_step": -1
|
519 |
+
}
|
520 |
+
```
|
521 |
+
|
522 |
+
### Training Hyperparameters
|
523 |
+
#### Non-Default Hyperparameters
|
524 |
+
|
525 |
+
- `eval_strategy`: epoch
|
526 |
+
- `per_device_train_batch_size`: 32
|
527 |
+
- `per_device_eval_batch_size`: 16
|
528 |
+
- `gradient_accumulation_steps`: 16
|
529 |
+
- `learning_rate`: 2e-05
|
530 |
+
- `num_train_epochs`: 4
|
531 |
+
- `lr_scheduler_type`: cosine
|
532 |
+
- `warmup_ratio`: 0.1
|
533 |
+
- `fp16`: True
|
534 |
+
- `tf32`: False
|
535 |
+
- `load_best_model_at_end`: True
|
536 |
+
- `optim`: adamw_torch_fused
|
537 |
+
- `batch_sampler`: no_duplicates
|
538 |
+
|
539 |
+
#### All Hyperparameters
|
540 |
+
<details><summary>Click to expand</summary>
|
541 |
+
|
542 |
+
- `overwrite_output_dir`: False
|
543 |
+
- `do_predict`: False
|
544 |
+
- `eval_strategy`: epoch
|
545 |
+
- `prediction_loss_only`: True
|
546 |
+
- `per_device_train_batch_size`: 32
|
547 |
+
- `per_device_eval_batch_size`: 16
|
548 |
+
- `per_gpu_train_batch_size`: None
|
549 |
+
- `per_gpu_eval_batch_size`: None
|
550 |
+
- `gradient_accumulation_steps`: 16
|
551 |
+
- `eval_accumulation_steps`: None
|
552 |
+
- `learning_rate`: 2e-05
|
553 |
+
- `weight_decay`: 0.0
|
554 |
+
- `adam_beta1`: 0.9
|
555 |
+
- `adam_beta2`: 0.999
|
556 |
+
- `adam_epsilon`: 1e-08
|
557 |
+
- `max_grad_norm`: 1.0
|
558 |
+
- `num_train_epochs`: 4
|
559 |
+
- `max_steps`: -1
|
560 |
+
- `lr_scheduler_type`: cosine
|
561 |
+
- `lr_scheduler_kwargs`: {}
|
562 |
+
- `warmup_ratio`: 0.1
|
563 |
+
- `warmup_steps`: 0
|
564 |
+
- `log_level`: passive
|
565 |
+
- `log_level_replica`: warning
|
566 |
+
- `log_on_each_node`: True
|
567 |
+
- `logging_nan_inf_filter`: True
|
568 |
+
- `save_safetensors`: True
|
569 |
+
- `save_on_each_node`: False
|
570 |
+
- `save_only_model`: False
|
571 |
+
- `restore_callback_states_from_checkpoint`: False
|
572 |
+
- `no_cuda`: False
|
573 |
+
- `use_cpu`: False
|
574 |
+
- `use_mps_device`: False
|
575 |
+
- `seed`: 42
|
576 |
+
- `data_seed`: None
|
577 |
+
- `jit_mode_eval`: False
|
578 |
+
- `use_ipex`: False
|
579 |
+
- `bf16`: False
|
580 |
+
- `fp16`: True
|
581 |
+
- `fp16_opt_level`: O1
|
582 |
+
- `half_precision_backend`: auto
|
583 |
+
- `bf16_full_eval`: False
|
584 |
+
- `fp16_full_eval`: False
|
585 |
+
- `tf32`: False
|
586 |
+
- `local_rank`: 0
|
587 |
+
- `ddp_backend`: None
|
588 |
+
- `tpu_num_cores`: None
|
589 |
+
- `tpu_metrics_debug`: False
|
590 |
+
- `debug`: []
|
591 |
+
- `dataloader_drop_last`: False
|
592 |
+
- `dataloader_num_workers`: 0
|
593 |
+
- `dataloader_prefetch_factor`: None
|
594 |
+
- `past_index`: -1
|
595 |
+
- `disable_tqdm`: False
|
596 |
+
- `remove_unused_columns`: True
|
597 |
+
- `label_names`: None
|
598 |
+
- `load_best_model_at_end`: True
|
599 |
+
- `ignore_data_skip`: False
|
600 |
+
- `fsdp`: []
|
601 |
+
- `fsdp_min_num_params`: 0
|
602 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
603 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
604 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
605 |
+
- `deepspeed`: None
|
606 |
+
- `label_smoothing_factor`: 0.0
|
607 |
+
- `optim`: adamw_torch_fused
|
608 |
+
- `optim_args`: None
|
609 |
+
- `adafactor`: False
|
610 |
+
- `group_by_length`: False
|
611 |
+
- `length_column_name`: length
|
612 |
+
- `ddp_find_unused_parameters`: None
|
613 |
+
- `ddp_bucket_cap_mb`: None
|
614 |
+
- `ddp_broadcast_buffers`: False
|
615 |
+
- `dataloader_pin_memory`: True
|
616 |
+
- `dataloader_persistent_workers`: False
|
617 |
+
- `skip_memory_metrics`: True
|
618 |
+
- `use_legacy_prediction_loop`: False
|
619 |
+
- `push_to_hub`: False
|
620 |
+
- `resume_from_checkpoint`: None
|
621 |
+
- `hub_model_id`: None
|
622 |
+
- `hub_strategy`: every_save
|
623 |
+
- `hub_private_repo`: False
|
624 |
+
- `hub_always_push`: False
|
625 |
+
- `gradient_checkpointing`: False
|
626 |
+
- `gradient_checkpointing_kwargs`: None
|
627 |
+
- `include_inputs_for_metrics`: False
|
628 |
+
- `eval_do_concat_batches`: True
|
629 |
+
- `fp16_backend`: auto
|
630 |
+
- `push_to_hub_model_id`: None
|
631 |
+
- `push_to_hub_organization`: None
|
632 |
+
- `mp_parameters`:
|
633 |
+
- `auto_find_batch_size`: False
|
634 |
+
- `full_determinism`: False
|
635 |
+
- `torchdynamo`: None
|
636 |
+
- `ray_scope`: last
|
637 |
+
- `ddp_timeout`: 1800
|
638 |
+
- `torch_compile`: False
|
639 |
+
- `torch_compile_backend`: None
|
640 |
+
- `torch_compile_mode`: None
|
641 |
+
- `dispatch_batches`: None
|
642 |
+
- `split_batches`: None
|
643 |
+
- `include_tokens_per_second`: False
|
644 |
+
- `include_num_input_tokens_seen`: False
|
645 |
+
- `neftune_noise_alpha`: None
|
646 |
+
- `optim_target_modules`: None
|
647 |
+
- `batch_eval_metrics`: False
|
648 |
+
- `batch_sampler`: no_duplicates
|
649 |
+
- `multi_dataset_batch_sampler`: proportional
|
650 |
+
|
651 |
+
</details>
|
652 |
+
|
653 |
+
### Training Logs
|
654 |
+
| Epoch | Step | Training Loss | dim_128_cosine_map@100 | dim_256_cosine_map@100 | dim_512_cosine_map@100 | dim_768_cosine_map@100 |
|
655 |
+
|:----------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|
|
656 |
+
| 0.8122 | 10 | 1.1625 | - | - | - | - |
|
657 |
+
| 0.9746 | 12 | - | 0.7429 | 0.7568 | 0.7688 | 0.7724 |
|
658 |
+
| 1.6244 | 20 | 0.4282 | - | - | - | - |
|
659 |
+
| 1.9492 | 24 | - | 0.7541 | 0.7691 | 0.7802 | 0.7828 |
|
660 |
+
| 2.4365 | 30 | 0.3086 | - | - | - | - |
|
661 |
+
| 2.9239 | 36 | - | 0.7581 | 0.7731 | 0.7810 | 0.7838 |
|
662 |
+
| 3.2487 | 40 | 0.2432 | - | - | - | - |
|
663 |
+
| **3.8985** | **48** | **-** | **0.7584** | **0.7739** | **0.7814** | **0.7832** |
|
664 |
+
|
665 |
+
* The bold row denotes the saved checkpoint.
|
666 |
+
|
667 |
+
### Framework Versions
|
668 |
+
- Python: 3.10.13
|
669 |
+
- Sentence Transformers: 3.0.1
|
670 |
+
- Transformers: 4.41.2
|
671 |
+
- PyTorch: 2.1.2
|
672 |
+
- Accelerate: 0.31.0
|
673 |
+
- Datasets: 2.19.1
|
674 |
+
- Tokenizers: 0.19.1
|
675 |
+
|
676 |
+
## Citation
|
677 |
+
|
678 |
+
### BibTeX
|
679 |
+
|
680 |
+
#### Sentence Transformers
|
681 |
+
```bibtex
|
682 |
+
@inproceedings{reimers-2019-sentence-bert,
|
683 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
684 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
685 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
686 |
+
month = "11",
|
687 |
+
year = "2019",
|
688 |
+
publisher = "Association for Computational Linguistics",
|
689 |
+
url = "https://arxiv.org/abs/1908.10084",
|
690 |
+
}
|
691 |
+
```
|
692 |
+
|
693 |
+
#### MatryoshkaLoss
|
694 |
+
```bibtex
|
695 |
+
@misc{kusupati2024matryoshka,
|
696 |
+
title={Matryoshka Representation Learning},
|
697 |
+
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},
|
698 |
+
year={2024},
|
699 |
+
eprint={2205.13147},
|
700 |
+
archivePrefix={arXiv},
|
701 |
+
primaryClass={cs.LG}
|
702 |
+
}
|
703 |
+
```
|
704 |
+
|
705 |
+
#### MultipleNegativesRankingLoss
|
706 |
+
```bibtex
|
707 |
+
@misc{henderson2017efficient,
|
708 |
+
title={Efficient Natural Language Response Suggestion for Smart Reply},
|
709 |
+
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},
|
710 |
+
year={2017},
|
711 |
+
eprint={1705.00652},
|
712 |
+
archivePrefix={arXiv},
|
713 |
+
primaryClass={cs.CL}
|
714 |
+
}
|
715 |
+
```
|
716 |
+
|
717 |
+
<!--
|
718 |
+
## Glossary
|
719 |
+
|
720 |
+
*Clearly define terms in order to be accessible across audiences.*
|
721 |
+
-->
|
722 |
+
|
723 |
+
<!--
|
724 |
+
## Model Card Authors
|
725 |
+
|
726 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
727 |
+
-->
|
728 |
+
|
729 |
+
<!--
|
730 |
+
## Model Card Contact
|
731 |
+
|
732 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
733 |
+
-->
|
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"
|
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 sha256:5733ad4b25e784a4ca5456eee35bdb7031c60e18ccf8d35902044612f9b83ed2
|
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
|
|