MugheesAwan11
commited on
Commit
•
da0b33e
1
Parent(s):
222d680
Add new SentenceTransformer model.
Browse files- 1_Pooling/config.json +10 -0
- README.md +616 -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 +1,616 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
metrics:
|
9 |
+
- cosine_accuracy@1
|
10 |
+
- cosine_accuracy@3
|
11 |
+
- cosine_accuracy@5
|
12 |
+
- cosine_accuracy@10
|
13 |
+
- cosine_precision@1
|
14 |
+
- cosine_precision@3
|
15 |
+
- cosine_precision@5
|
16 |
+
- cosine_precision@10
|
17 |
+
- cosine_recall@1
|
18 |
+
- cosine_recall@3
|
19 |
+
- cosine_recall@5
|
20 |
+
- cosine_recall@10
|
21 |
+
- cosine_ndcg@10
|
22 |
+
- cosine_ndcg@100
|
23 |
+
- cosine_mrr@10
|
24 |
+
- cosine_map@100
|
25 |
+
pipeline_tag: sentence-similarity
|
26 |
+
tags:
|
27 |
+
- sentence-transformers
|
28 |
+
- sentence-similarity
|
29 |
+
- feature-extraction
|
30 |
+
- generated_from_trainer
|
31 |
+
- dataset_size:10000
|
32 |
+
- loss:MatryoshkaLoss
|
33 |
+
- loss:MultipleNegativesRankingLoss
|
34 |
+
widget:
|
35 |
+
- source_sentence: Enzalutamide ( brand name Xtandi ) is a synthetic non-steroidal
|
36 |
+
antiandrogen ( NSAA ) which was developed by the pharmaceutical company Medivation
|
37 |
+
for the treatment of metastatic , castration-resistant prostate cancer . Medivation
|
38 |
+
has reported up to an 89 % decrease in serum prostate specific antigen ( PSA )
|
39 |
+
levels after a month of taking the drug . Research suggests that enzalutamide
|
40 |
+
may also be effective in the treatment of certain types of breast cancer . In
|
41 |
+
August 2012 , the United States ( U.S. ) Food and Drug Administration ( FDA )
|
42 |
+
approved enzalutamide for the treatment of castration-resistant prostate cancer
|
43 |
+
.
|
44 |
+
sentences:
|
45 |
+
- what type of cancer is enzalutamide
|
46 |
+
- who is simon cho
|
47 |
+
- who is dr william farone
|
48 |
+
- source_sentence: Sohel Rana is a Bangladeshi footballer who plays as a midfielder
|
49 |
+
. He currently plays for Sheikh Jamal Dhanmondi Club .
|
50 |
+
sentences:
|
51 |
+
- who is sohel rana
|
52 |
+
- who is olympicos
|
53 |
+
- who is roberto laserna
|
54 |
+
- source_sentence: Qarah Qayeh ( قره قيه , also Romanized as Qareh Qīyeh ) is a village
|
55 |
+
in Chaharduli Rural District , Keshavarz District , Shahin Dezh County , West
|
56 |
+
Azerbaijan Province , Iran . At the 2006 census , its population was 465 , in
|
57 |
+
93 families .
|
58 |
+
sentences:
|
59 |
+
- what was the knoxville riot
|
60 |
+
- what language is kbif
|
61 |
+
- where is qarah qayeh
|
62 |
+
- source_sentence: Martin Severin Janus From ( 8 April 1828 -- 6 May 1895 ) was a
|
63 |
+
Danish chess master . Born in Nakskov , From received his first education at
|
64 |
+
the grammar school of Nykøbing Falster . He entered the army as a volunteer during
|
65 |
+
the Prussian-Danish War ( Schleswig-Holstein War of Succession ) , where he served
|
66 |
+
in the brigade of Major-General Olaf Rye and partook in the Battle of Fredericia
|
67 |
+
on July 6 , 1849 . After the war From settled in Copenhagen . He was employed
|
68 |
+
by the Statistical Bureau , where he met Magnus Oscar Møllerstrøm , then the strongest
|
69 |
+
chess player in Copenhagen . Next , he worked in the central office for prison
|
70 |
+
management , and in 1890 he became an inspector of the penitentiary of Christianshavn
|
71 |
+
. In 1891 he received the order Ridder af Dannebrog ( `` Knight of the Danish
|
72 |
+
cloth '' , i.e. flag of Denmark ) , which is the second highest of Danish orders
|
73 |
+
. In 1895 Severin From died of cancer . He is interred at Vestre Cemetery ,
|
74 |
+
Copenhagen .
|
75 |
+
sentences:
|
76 |
+
- when did martin from die
|
77 |
+
- what is hymenoxys lemmonii
|
78 |
+
- where is macomb square il
|
79 |
+
- source_sentence: The Recession of 1937 -- 1938 was an economic downturn that occurred
|
80 |
+
during the Great Depression in the United States . By the spring of 1937 , production
|
81 |
+
, profits , and wages had regained their 1929 levels . Unemployment remained high
|
82 |
+
, but it was slightly lower than the 25 % rate seen in 1933 . The American economy
|
83 |
+
took a sharp downturn in mid-1937 , lasting for 13 months through most of 1938
|
84 |
+
. Industrial production declined almost 30 percent and production of durable goods
|
85 |
+
fell even faster . Unemployment jumped from 14.3 % in 1937 to 19.0 % in 1938
|
86 |
+
. Manufacturing output fell by 37 % from the 1937 peak and was back to 1934 levels
|
87 |
+
. Producers reduced their expenditures on durable goods , and inventories declined
|
88 |
+
, but personal income was only 15 % lower than it had been at the peak in 1937
|
89 |
+
. In most sectors , hourly earnings continued to rise throughout the recession
|
90 |
+
, which partly compensated for the reduction in the number of hours worked . As
|
91 |
+
unemployment rose , consumers expenditures declined , thereby leading to further
|
92 |
+
cutbacks in production .
|
93 |
+
sentences:
|
94 |
+
- when did the great depression peak in the u.s. economy?
|
95 |
+
- what is tom mount's specialty
|
96 |
+
- where is poulton
|
97 |
+
model-index:
|
98 |
+
- name: SentenceTransformer based on BAAI/bge-base-en-v1.5
|
99 |
+
results:
|
100 |
+
- task:
|
101 |
+
type: information-retrieval
|
102 |
+
name: Information Retrieval
|
103 |
+
dataset:
|
104 |
+
name: dim 768
|
105 |
+
type: dim_768
|
106 |
+
metrics:
|
107 |
+
- type: cosine_accuracy@1
|
108 |
+
value: 0.906
|
109 |
+
name: Cosine Accuracy@1
|
110 |
+
- type: cosine_accuracy@3
|
111 |
+
value: 0.954
|
112 |
+
name: Cosine Accuracy@3
|
113 |
+
- type: cosine_accuracy@5
|
114 |
+
value: 0.962
|
115 |
+
name: Cosine Accuracy@5
|
116 |
+
- type: cosine_accuracy@10
|
117 |
+
value: 0.975
|
118 |
+
name: Cosine Accuracy@10
|
119 |
+
- type: cosine_precision@1
|
120 |
+
value: 0.906
|
121 |
+
name: Cosine Precision@1
|
122 |
+
- type: cosine_precision@3
|
123 |
+
value: 0.31799999999999995
|
124 |
+
name: Cosine Precision@3
|
125 |
+
- type: cosine_precision@5
|
126 |
+
value: 0.19240000000000004
|
127 |
+
name: Cosine Precision@5
|
128 |
+
- type: cosine_precision@10
|
129 |
+
value: 0.09750000000000003
|
130 |
+
name: Cosine Precision@10
|
131 |
+
- type: cosine_recall@1
|
132 |
+
value: 0.906
|
133 |
+
name: Cosine Recall@1
|
134 |
+
- type: cosine_recall@3
|
135 |
+
value: 0.954
|
136 |
+
name: Cosine Recall@3
|
137 |
+
- type: cosine_recall@5
|
138 |
+
value: 0.962
|
139 |
+
name: Cosine Recall@5
|
140 |
+
- type: cosine_recall@10
|
141 |
+
value: 0.975
|
142 |
+
name: Cosine Recall@10
|
143 |
+
- type: cosine_ndcg@10
|
144 |
+
value: 0.9422297521305668
|
145 |
+
name: Cosine Ndcg@10
|
146 |
+
- type: cosine_ndcg@100
|
147 |
+
value: 0.9458947974911144
|
148 |
+
name: Cosine Ndcg@100
|
149 |
+
- type: cosine_mrr@10
|
150 |
+
value: 0.9315763888888889
|
151 |
+
name: Cosine Mrr@10
|
152 |
+
- type: cosine_map@100
|
153 |
+
value: 0.9323383888065935
|
154 |
+
name: Cosine Map@100
|
155 |
+
---
|
156 |
+
|
157 |
+
# SentenceTransformer based on BAAI/bge-base-en-v1.5
|
158 |
+
|
159 |
+
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.
|
160 |
+
|
161 |
+
## Model Details
|
162 |
+
|
163 |
+
### Model Description
|
164 |
+
- **Model Type:** Sentence Transformer
|
165 |
+
- **Base model:** [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) <!-- at revision a5beb1e3e68b9ab74eb54cfd186867f64f240e1a -->
|
166 |
+
- **Maximum Sequence Length:** 512 tokens
|
167 |
+
- **Output Dimensionality:** 768 tokens
|
168 |
+
- **Similarity Function:** Cosine Similarity
|
169 |
+
<!-- - **Training Dataset:** Unknown -->
|
170 |
+
- **Language:** en
|
171 |
+
- **License:** apache-2.0
|
172 |
+
|
173 |
+
### Model Sources
|
174 |
+
|
175 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
176 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
177 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
178 |
+
|
179 |
+
### Full Model Architecture
|
180 |
+
|
181 |
+
```
|
182 |
+
SentenceTransformer(
|
183 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel
|
184 |
+
(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})
|
185 |
+
(2): Normalize()
|
186 |
+
)
|
187 |
+
```
|
188 |
+
|
189 |
+
## Usage
|
190 |
+
|
191 |
+
### Direct Usage (Sentence Transformers)
|
192 |
+
|
193 |
+
First install the Sentence Transformers library:
|
194 |
+
|
195 |
+
```bash
|
196 |
+
pip install -U sentence-transformers
|
197 |
+
```
|
198 |
+
|
199 |
+
Then you can load this model and run inference.
|
200 |
+
```python
|
201 |
+
from sentence_transformers import SentenceTransformer
|
202 |
+
|
203 |
+
# Download from the 🤗 Hub
|
204 |
+
model = SentenceTransformer("MugheesAwan11/bge-base-climate_fever-dataset-10k-2k-e2")
|
205 |
+
# Run inference
|
206 |
+
sentences = [
|
207 |
+
'The Recession of 1937 -- 1938 was an economic downturn that occurred during the Great Depression in the United States . By the spring of 1937 , production , profits , and wages had regained their 1929 levels . Unemployment remained high , but it was slightly lower than the 25 % rate seen in 1933 . The American economy took a sharp downturn in mid-1937 , lasting for 13 months through most of 1938 . Industrial production declined almost 30 percent and production of durable goods fell even faster . Unemployment jumped from 14.3 % in 1937 to 19.0 % in 1938 . Manufacturing output fell by 37 % from the 1937 peak and was back to 1934 levels . Producers reduced their expenditures on durable goods , and inventories declined , but personal income was only 15 % lower than it had been at the peak in 1937 . In most sectors , hourly earnings continued to rise throughout the recession , which partly compensated for the reduction in the number of hours worked . As unemployment rose , consumers expenditures declined , thereby leading to further cutbacks in production .',
|
208 |
+
'when did the great depression peak in the u.s. economy?',
|
209 |
+
'where is poulton',
|
210 |
+
]
|
211 |
+
embeddings = model.encode(sentences)
|
212 |
+
print(embeddings.shape)
|
213 |
+
# [3, 768]
|
214 |
+
|
215 |
+
# Get the similarity scores for the embeddings
|
216 |
+
similarities = model.similarity(embeddings, embeddings)
|
217 |
+
print(similarities.shape)
|
218 |
+
# [3, 3]
|
219 |
+
```
|
220 |
+
|
221 |
+
<!--
|
222 |
+
### Direct Usage (Transformers)
|
223 |
+
|
224 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
225 |
+
|
226 |
+
</details>
|
227 |
+
-->
|
228 |
+
|
229 |
+
<!--
|
230 |
+
### Downstream Usage (Sentence Transformers)
|
231 |
+
|
232 |
+
You can finetune this model on your own dataset.
|
233 |
+
|
234 |
+
<details><summary>Click to expand</summary>
|
235 |
+
|
236 |
+
</details>
|
237 |
+
-->
|
238 |
+
|
239 |
+
<!--
|
240 |
+
### Out-of-Scope Use
|
241 |
+
|
242 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
243 |
+
-->
|
244 |
+
|
245 |
+
## Evaluation
|
246 |
+
|
247 |
+
### Metrics
|
248 |
+
|
249 |
+
#### Information Retrieval
|
250 |
+
* Dataset: `dim_768`
|
251 |
+
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
|
252 |
+
|
253 |
+
| Metric | Value |
|
254 |
+
|:--------------------|:-----------|
|
255 |
+
| cosine_accuracy@1 | 0.906 |
|
256 |
+
| cosine_accuracy@3 | 0.954 |
|
257 |
+
| cosine_accuracy@5 | 0.962 |
|
258 |
+
| cosine_accuracy@10 | 0.975 |
|
259 |
+
| cosine_precision@1 | 0.906 |
|
260 |
+
| cosine_precision@3 | 0.318 |
|
261 |
+
| cosine_precision@5 | 0.1924 |
|
262 |
+
| cosine_precision@10 | 0.0975 |
|
263 |
+
| cosine_recall@1 | 0.906 |
|
264 |
+
| cosine_recall@3 | 0.954 |
|
265 |
+
| cosine_recall@5 | 0.962 |
|
266 |
+
| cosine_recall@10 | 0.975 |
|
267 |
+
| cosine_ndcg@10 | 0.9422 |
|
268 |
+
| cosine_ndcg@100 | 0.9459 |
|
269 |
+
| cosine_mrr@10 | 0.9316 |
|
270 |
+
| **cosine_map@100** | **0.9323** |
|
271 |
+
|
272 |
+
<!--
|
273 |
+
## Bias, Risks and Limitations
|
274 |
+
|
275 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
276 |
+
-->
|
277 |
+
|
278 |
+
<!--
|
279 |
+
### Recommendations
|
280 |
+
|
281 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
282 |
+
-->
|
283 |
+
|
284 |
+
## Training Details
|
285 |
+
|
286 |
+
### Training Dataset
|
287 |
+
|
288 |
+
#### Unnamed Dataset
|
289 |
+
|
290 |
+
|
291 |
+
* Size: 10,000 training samples
|
292 |
+
* Columns: <code>positive</code> and <code>anchor</code>
|
293 |
+
* Approximate statistics based on the first 1000 samples:
|
294 |
+
| | positive | anchor |
|
295 |
+
|:--------|:------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|
|
296 |
+
| type | string | string |
|
297 |
+
| details | <ul><li>min: 2 tokens</li><li>mean: 116.45 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 8.6 tokens</li><li>max: 19 tokens</li></ul> |
|
298 |
+
* Samples:
|
299 |
+
| positive | anchor |
|
300 |
+
|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------|
|
301 |
+
| <code>Professor Maurice Cockrill , RA , FBA ( 8 October 1936 -- 1 December 2013 ) was a British painter and poet . Born in Hartlepool , County Durham , he studied at Wrexham School of Art , north east Wales , then Denbigh Technical College and later the University of Reading from 1960 -- 64 . In Liverpool , where he lived for nearly twenty years from 1964 , he taught at Liverpool College of Art and Liverpool Polytechnic . He was a central figure in Liverpool 's artistic life , regularly exhibiting at the Walker Art Gallery , before his departure for London in 1982 . Cockrill 's Liverpool work was in line with that of John Baum , Sam Walsh and Adrian Henri , employing Pop and Photo-Realist styles , but later he moved towards Romantic Expressionism , as it was shown in his retrospective at the Walker Art Gallery , Liverpool in 1995 . His poetry was published in magazines such as `` Ambit '' and `` Poetry Review '' . He was formerly the Keeper of the Royal Academy , and as such managed the RA Schools of the Establishment as well as being a member of the Board and Executive Committee .</code> | <code>who was maurice cockrill</code> |
|
302 |
+
| <code>Nowa Dąbrowa -LSB- ` nowa-dom ` browa -RSB- is a village in the administrative district of Gmina Kwilcz , within Międzychód County , Greater Poland Voivodeship , in west-central Poland . It lies approximately 16 km south-east of Międzychód and 59 km west of the regional capital Poznań . The village has a population of 40 .</code> | <code>where is nowa dbrowa poland</code> |
|
303 |
+
| <code>Hymenoxys lemmonii is a species of flowering plant in the daisy family known by the common names Lemmon 's rubberweed , Lemmon 's bitterweed , and alkali hymenoxys . It is native to the western United States in and around the Great Basin in Utah , Nevada , northern California , and southeastern Oregon . Hymenoxys lemmonii is a biennial or perennial herb with one or more branching stems growing erect to a maximum height near 50 centimeters ( 20 inches ) . It produces straight , dark green leaves up to 9 centimeters ( 3.6 inches ) long and divided into a number of narrow , pointed lobes . The foliage and stem may be hairless to quite woolly . The daisy-like flower head is generally at least 1.5 centimeters ( 0.6 inches ) wide , with a center of 50 -- 125 thick golden disc florets and a shaggy fringe of 9 -- 12 golden ray florets . The species is named for John Gill Lemmon , husband of prominent American botanist Sarah Plummer Lemmon .</code> | <code>what is hymenoxys lemmonii</code> |
|
304 |
+
* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
|
305 |
+
```json
|
306 |
+
{
|
307 |
+
"loss": "MultipleNegativesRankingLoss",
|
308 |
+
"matryoshka_dims": [
|
309 |
+
768
|
310 |
+
],
|
311 |
+
"matryoshka_weights": [
|
312 |
+
1
|
313 |
+
],
|
314 |
+
"n_dims_per_step": -1
|
315 |
+
}
|
316 |
+
```
|
317 |
+
|
318 |
+
### Training Hyperparameters
|
319 |
+
#### Non-Default Hyperparameters
|
320 |
+
|
321 |
+
- `eval_strategy`: epoch
|
322 |
+
- `per_device_train_batch_size`: 32
|
323 |
+
- `per_device_eval_batch_size`: 16
|
324 |
+
- `learning_rate`: 2e-05
|
325 |
+
- `num_train_epochs`: 2
|
326 |
+
- `lr_scheduler_type`: cosine
|
327 |
+
- `warmup_ratio`: 0.1
|
328 |
+
- `bf16`: True
|
329 |
+
- `tf32`: True
|
330 |
+
- `load_best_model_at_end`: True
|
331 |
+
- `optim`: adamw_torch_fused
|
332 |
+
- `batch_sampler`: no_duplicates
|
333 |
+
|
334 |
+
#### All Hyperparameters
|
335 |
+
<details><summary>Click to expand</summary>
|
336 |
+
|
337 |
+
- `overwrite_output_dir`: False
|
338 |
+
- `do_predict`: False
|
339 |
+
- `eval_strategy`: epoch
|
340 |
+
- `prediction_loss_only`: True
|
341 |
+
- `per_device_train_batch_size`: 32
|
342 |
+
- `per_device_eval_batch_size`: 16
|
343 |
+
- `per_gpu_train_batch_size`: None
|
344 |
+
- `per_gpu_eval_batch_size`: None
|
345 |
+
- `gradient_accumulation_steps`: 1
|
346 |
+
- `eval_accumulation_steps`: None
|
347 |
+
- `learning_rate`: 2e-05
|
348 |
+
- `weight_decay`: 0.0
|
349 |
+
- `adam_beta1`: 0.9
|
350 |
+
- `adam_beta2`: 0.999
|
351 |
+
- `adam_epsilon`: 1e-08
|
352 |
+
- `max_grad_norm`: 1.0
|
353 |
+
- `num_train_epochs`: 2
|
354 |
+
- `max_steps`: -1
|
355 |
+
- `lr_scheduler_type`: cosine
|
356 |
+
- `lr_scheduler_kwargs`: {}
|
357 |
+
- `warmup_ratio`: 0.1
|
358 |
+
- `warmup_steps`: 0
|
359 |
+
- `log_level`: passive
|
360 |
+
- `log_level_replica`: warning
|
361 |
+
- `log_on_each_node`: True
|
362 |
+
- `logging_nan_inf_filter`: True
|
363 |
+
- `save_safetensors`: True
|
364 |
+
- `save_on_each_node`: False
|
365 |
+
- `save_only_model`: False
|
366 |
+
- `restore_callback_states_from_checkpoint`: False
|
367 |
+
- `no_cuda`: False
|
368 |
+
- `use_cpu`: False
|
369 |
+
- `use_mps_device`: False
|
370 |
+
- `seed`: 42
|
371 |
+
- `data_seed`: None
|
372 |
+
- `jit_mode_eval`: False
|
373 |
+
- `use_ipex`: False
|
374 |
+
- `bf16`: True
|
375 |
+
- `fp16`: False
|
376 |
+
- `fp16_opt_level`: O1
|
377 |
+
- `half_precision_backend`: auto
|
378 |
+
- `bf16_full_eval`: False
|
379 |
+
- `fp16_full_eval`: False
|
380 |
+
- `tf32`: True
|
381 |
+
- `local_rank`: 0
|
382 |
+
- `ddp_backend`: None
|
383 |
+
- `tpu_num_cores`: None
|
384 |
+
- `tpu_metrics_debug`: False
|
385 |
+
- `debug`: []
|
386 |
+
- `dataloader_drop_last`: False
|
387 |
+
- `dataloader_num_workers`: 0
|
388 |
+
- `dataloader_prefetch_factor`: None
|
389 |
+
- `past_index`: -1
|
390 |
+
- `disable_tqdm`: False
|
391 |
+
- `remove_unused_columns`: True
|
392 |
+
- `label_names`: None
|
393 |
+
- `load_best_model_at_end`: True
|
394 |
+
- `ignore_data_skip`: False
|
395 |
+
- `fsdp`: []
|
396 |
+
- `fsdp_min_num_params`: 0
|
397 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
398 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
399 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
400 |
+
- `deepspeed`: None
|
401 |
+
- `label_smoothing_factor`: 0.0
|
402 |
+
- `optim`: adamw_torch_fused
|
403 |
+
- `optim_args`: None
|
404 |
+
- `adafactor`: False
|
405 |
+
- `group_by_length`: False
|
406 |
+
- `length_column_name`: length
|
407 |
+
- `ddp_find_unused_parameters`: None
|
408 |
+
- `ddp_bucket_cap_mb`: None
|
409 |
+
- `ddp_broadcast_buffers`: False
|
410 |
+
- `dataloader_pin_memory`: True
|
411 |
+
- `dataloader_persistent_workers`: False
|
412 |
+
- `skip_memory_metrics`: True
|
413 |
+
- `use_legacy_prediction_loop`: False
|
414 |
+
- `push_to_hub`: False
|
415 |
+
- `resume_from_checkpoint`: None
|
416 |
+
- `hub_model_id`: None
|
417 |
+
- `hub_strategy`: every_save
|
418 |
+
- `hub_private_repo`: False
|
419 |
+
- `hub_always_push`: False
|
420 |
+
- `gradient_checkpointing`: False
|
421 |
+
- `gradient_checkpointing_kwargs`: None
|
422 |
+
- `include_inputs_for_metrics`: False
|
423 |
+
- `eval_do_concat_batches`: True
|
424 |
+
- `fp16_backend`: auto
|
425 |
+
- `push_to_hub_model_id`: None
|
426 |
+
- `push_to_hub_organization`: None
|
427 |
+
- `mp_parameters`:
|
428 |
+
- `auto_find_batch_size`: False
|
429 |
+
- `full_determinism`: False
|
430 |
+
- `torchdynamo`: None
|
431 |
+
- `ray_scope`: last
|
432 |
+
- `ddp_timeout`: 1800
|
433 |
+
- `torch_compile`: False
|
434 |
+
- `torch_compile_backend`: None
|
435 |
+
- `torch_compile_mode`: None
|
436 |
+
- `dispatch_batches`: None
|
437 |
+
- `split_batches`: None
|
438 |
+
- `include_tokens_per_second`: False
|
439 |
+
- `include_num_input_tokens_seen`: False
|
440 |
+
- `neftune_noise_alpha`: None
|
441 |
+
- `optim_target_modules`: None
|
442 |
+
- `batch_eval_metrics`: False
|
443 |
+
- `batch_sampler`: no_duplicates
|
444 |
+
- `multi_dataset_batch_sampler`: proportional
|
445 |
+
|
446 |
+
</details>
|
447 |
+
|
448 |
+
### Training Logs
|
449 |
+
| Epoch | Step | Training Loss | dim_768_cosine_map@100 |
|
450 |
+
|:-------:|:-------:|:-------------:|:----------------------:|
|
451 |
+
| 0.0319 | 10 | 0.1626 | - |
|
452 |
+
| 0.0639 | 20 | 0.1168 | - |
|
453 |
+
| 0.0958 | 30 | 0.0543 | - |
|
454 |
+
| 0.1278 | 40 | 0.1227 | - |
|
455 |
+
| 0.1597 | 50 | 0.061 | - |
|
456 |
+
| 0.1917 | 60 | 0.0537 | - |
|
457 |
+
| 0.2236 | 70 | 0.0693 | - |
|
458 |
+
| 0.2556 | 80 | 0.1115 | - |
|
459 |
+
| 0.2875 | 90 | 0.0541 | - |
|
460 |
+
| 0.3195 | 100 | 0.0774 | - |
|
461 |
+
| 0.3514 | 110 | 0.0639 | - |
|
462 |
+
| 0.3834 | 120 | 0.0639 | - |
|
463 |
+
| 0.4153 | 130 | 0.0567 | - |
|
464 |
+
| 0.4473 | 140 | 0.0385 | - |
|
465 |
+
| 0.4792 | 150 | 0.0452 | - |
|
466 |
+
| 0.5112 | 160 | 0.0641 | - |
|
467 |
+
| 0.5431 | 170 | 0.042 | - |
|
468 |
+
| 0.5751 | 180 | 0.0243 | - |
|
469 |
+
| 0.6070 | 190 | 0.0405 | - |
|
470 |
+
| 0.6390 | 200 | 0.062 | - |
|
471 |
+
| 0.6709 | 210 | 0.0366 | - |
|
472 |
+
| 0.7029 | 220 | 0.0399 | - |
|
473 |
+
| 0.7348 | 230 | 0.0382 | - |
|
474 |
+
| 0.7668 | 240 | 0.0387 | - |
|
475 |
+
| 0.7987 | 250 | 0.0575 | - |
|
476 |
+
| 0.8307 | 260 | 0.0391 | - |
|
477 |
+
| 0.8626 | 270 | 0.0776 | - |
|
478 |
+
| 0.8946 | 280 | 0.0258 | - |
|
479 |
+
| 0.9265 | 290 | 0.0493 | - |
|
480 |
+
| 0.9585 | 300 | 0.037 | - |
|
481 |
+
| 0.9904 | 310 | 0.0499 | - |
|
482 |
+
| **1.0** | **313** | **-** | **0.9397** |
|
483 |
+
| 0.0319 | 10 | 0.0111 | - |
|
484 |
+
| 0.0639 | 20 | 0.007 | - |
|
485 |
+
| 0.0958 | 30 | 0.0023 | - |
|
486 |
+
| 0.1278 | 40 | 0.0109 | - |
|
487 |
+
| 0.1597 | 50 | 0.0046 | - |
|
488 |
+
| 0.1917 | 60 | 0.0043 | - |
|
489 |
+
| 0.2236 | 70 | 0.0037 | - |
|
490 |
+
| 0.2556 | 80 | 0.0118 | - |
|
491 |
+
| 0.2875 | 90 | 0.0026 | - |
|
492 |
+
| 0.3195 | 100 | 0.0079 | - |
|
493 |
+
| 0.3514 | 110 | 0.0045 | - |
|
494 |
+
| 0.3834 | 120 | 0.0163 | - |
|
495 |
+
| 0.4153 | 130 | 0.0058 | - |
|
496 |
+
| 0.4473 | 140 | 0.0154 | - |
|
497 |
+
| 0.4792 | 150 | 0.0051 | - |
|
498 |
+
| 0.5112 | 160 | 0.0152 | - |
|
499 |
+
| 0.5431 | 170 | 0.0058 | - |
|
500 |
+
| 0.5751 | 180 | 0.0041 | - |
|
501 |
+
| 0.6070 | 190 | 0.0118 | - |
|
502 |
+
| 0.6390 | 200 | 0.0165 | - |
|
503 |
+
| 0.6709 | 210 | 0.0088 | - |
|
504 |
+
| 0.7029 | 220 | 0.014 | - |
|
505 |
+
| 0.7348 | 230 | 0.0195 | - |
|
506 |
+
| 0.7668 | 240 | 0.024 | - |
|
507 |
+
| 0.7987 | 250 | 0.0472 | - |
|
508 |
+
| 0.8307 | 260 | 0.0341 | - |
|
509 |
+
| 0.8626 | 270 | 0.0684 | - |
|
510 |
+
| 0.8946 | 280 | 0.0193 | - |
|
511 |
+
| 0.9265 | 290 | 0.0488 | - |
|
512 |
+
| 0.9585 | 300 | 0.0388 | - |
|
513 |
+
| 0.9904 | 310 | 0.0485 | - |
|
514 |
+
| **1.0** | **313** | **-** | **0.9349** |
|
515 |
+
| 1.0224 | 320 | 0.0119 | - |
|
516 |
+
| 1.0543 | 330 | 0.013 | - |
|
517 |
+
| 1.0863 | 340 | 0.0024 | - |
|
518 |
+
| 1.1182 | 350 | 0.012 | - |
|
519 |
+
| 1.1502 | 360 | 0.0042 | - |
|
520 |
+
| 1.1821 | 370 | 0.0091 | - |
|
521 |
+
| 1.2141 | 380 | 0.0041 | - |
|
522 |
+
| 1.2460 | 390 | 0.0096 | - |
|
523 |
+
| 1.2780 | 400 | 0.0053 | - |
|
524 |
+
| 1.3099 | 410 | 0.0043 | - |
|
525 |
+
| 1.3419 | 420 | 0.0059 | - |
|
526 |
+
| 1.3738 | 430 | 0.0138 | - |
|
527 |
+
| 1.4058 | 440 | 0.0132 | - |
|
528 |
+
| 1.4377 | 450 | 0.0124 | - |
|
529 |
+
| 1.4696 | 460 | 0.0049 | - |
|
530 |
+
| 1.5016 | 470 | 0.0043 | - |
|
531 |
+
| 1.5335 | 480 | 0.0045 | - |
|
532 |
+
| 1.5655 | 490 | 0.0037 | - |
|
533 |
+
| 1.5974 | 500 | 0.0081 | - |
|
534 |
+
| 1.6294 | 510 | 0.0038 | - |
|
535 |
+
| 1.6613 | 520 | 0.0055 | - |
|
536 |
+
| 1.6933 | 530 | 0.003 | - |
|
537 |
+
| 1.7252 | 540 | 0.0022 | - |
|
538 |
+
| 1.7572 | 550 | 0.0042 | - |
|
539 |
+
| 1.7891 | 560 | 0.0158 | - |
|
540 |
+
| 1.8211 | 570 | 0.0088 | - |
|
541 |
+
| 1.8530 | 580 | 0.0154 | - |
|
542 |
+
| 1.8850 | 590 | 0.0057 | - |
|
543 |
+
| 1.9169 | 600 | 0.0086 | - |
|
544 |
+
| 1.9489 | 610 | 0.0069 | - |
|
545 |
+
| 1.9808 | 620 | 0.0076 | - |
|
546 |
+
| 2.0 | 626 | - | 0.9323 |
|
547 |
+
|
548 |
+
* The bold row denotes the saved checkpoint.
|
549 |
+
|
550 |
+
### Framework Versions
|
551 |
+
- Python: 3.10.14
|
552 |
+
- Sentence Transformers: 3.0.1
|
553 |
+
- Transformers: 4.41.2
|
554 |
+
- PyTorch: 2.1.2+cu121
|
555 |
+
- Accelerate: 0.31.0
|
556 |
+
- Datasets: 2.19.1
|
557 |
+
- Tokenizers: 0.19.1
|
558 |
+
|
559 |
+
## Citation
|
560 |
+
|
561 |
+
### BibTeX
|
562 |
+
|
563 |
+
#### Sentence Transformers
|
564 |
+
```bibtex
|
565 |
+
@inproceedings{reimers-2019-sentence-bert,
|
566 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
567 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
568 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
569 |
+
month = "11",
|
570 |
+
year = "2019",
|
571 |
+
publisher = "Association for Computational Linguistics",
|
572 |
+
url = "https://arxiv.org/abs/1908.10084",
|
573 |
+
}
|
574 |
+
```
|
575 |
+
|
576 |
+
#### MatryoshkaLoss
|
577 |
+
```bibtex
|
578 |
+
@misc{kusupati2024matryoshka,
|
579 |
+
title={Matryoshka Representation Learning},
|
580 |
+
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},
|
581 |
+
year={2024},
|
582 |
+
eprint={2205.13147},
|
583 |
+
archivePrefix={arXiv},
|
584 |
+
primaryClass={cs.LG}
|
585 |
+
}
|
586 |
+
```
|
587 |
+
|
588 |
+
#### MultipleNegativesRankingLoss
|
589 |
+
```bibtex
|
590 |
+
@misc{henderson2017efficient,
|
591 |
+
title={Efficient Natural Language Response Suggestion for Smart Reply},
|
592 |
+
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},
|
593 |
+
year={2017},
|
594 |
+
eprint={1705.00652},
|
595 |
+
archivePrefix={arXiv},
|
596 |
+
primaryClass={cs.CL}
|
597 |
+
}
|
598 |
+
```
|
599 |
+
|
600 |
+
<!--
|
601 |
+
## Glossary
|
602 |
+
|
603 |
+
*Clearly define terms in order to be accessible across audiences.*
|
604 |
+
-->
|
605 |
+
|
606 |
+
<!--
|
607 |
+
## Model Card Authors
|
608 |
+
|
609 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
610 |
+
-->
|
611 |
+
|
612 |
+
<!--
|
613 |
+
## Model Card Contact
|
614 |
+
|
615 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
616 |
+
-->
|
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:ee3075ea0530ffc64ed00cc2c79521f3ac0362395f8ce932637df2586bb26876
|
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
|
|