Hugging Face's logo

dendimaki
/
few-shots-apeiron-model-v2

Text Classification
setfit
Safetensors
sentence-transformers
mpnet
generated_from_setfit_trainer
Model card Files Community
dendimaki commited on
Commit
167d38c
•
1 Parent(s): a14858a

Add SetFit model

Browse files
Files changed (13) hide show
  1. 1_Pooling/config.json +10 -0
  2. README.md +276 -0
  3. config.json +24 -0
  4. config_sentence_transformers.json +9 -0
  5. config_setfit.json +4 -0
  6. model.safetensors +3 -0
  7. model_head.pkl +3 -0
  8. modules.json +14 -0
  9. sentence_bert_config.json +4 -0
  10. special_tokens_map.json +51 -0
  11. tokenizer.json +0 -0
  12. tokenizer_config.json +59 -0
  13. vocab.txt +0 -0
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
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 +1,276 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: setfit
3
+ tags:
4
+ - setfit
5
+ - sentence-transformers
6
+ - text-classification
7
+ - generated_from_setfit_trainer
8
+ base_model: sentence-transformers/paraphrase-mpnet-base-v2
9
+ datasets:
10
+ - dendimaki/v1
11
+ metrics:
12
+ - accuracy
13
+ widget:
14
+ - text: so you know you said that layer three maybe sounded interesting
15
+ - text: just this like sense of energy thats aliveness and aliveness tingly aliveness
16
+ - text: id say is pretty or really the dominant state unless i really focus on location
17
+ one and even then
18
+ - text: pervading presence
19
+ - text: nonduality for you
20
+ pipeline_tag: text-classification
21
+ inference: true
22
+ model-index:
23
+ - name: SetFit with sentence-transformers/paraphrase-mpnet-base-v2
24
+ results:
25
+ - task:
26
+ type: text-classification
27
+ name: Text Classification
28
+ dataset:
29
+ name: dendimaki/v1
30
+ type: dendimaki/v1
31
+ split: test
32
+ metrics:
33
+ - type: accuracy
34
+ value: 0.23529411764705882
35
+ name: Accuracy
36
+ ---
37
+
38
+ # SetFit with sentence-transformers/paraphrase-mpnet-base-v2
39
+
40
+ This is a [SetFit](https://github.com/huggingface/setfit) model trained on the [dendimaki/v1](https://huggingface.co/datasets/dendimaki/v1) dataset that can be used for Text Classification. This SetFit model uses [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
41
+
42
+ The model has been trained using an efficient few-shot learning technique that involves:
43
+
44
+ 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
45
+ 2. Training a classification head with features from the fine-tuned Sentence Transformer.
46
+
47
+ ## Model Details
48
+
49
+ ### Model Description
50
+ - **Model Type:** SetFit
51
+ - **Sentence Transformer body:** [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2)
52
+ - **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
53
+ - **Maximum Sequence Length:** 512 tokens
54
+ - **Number of Classes:** 29 classes
55
+ - **Training Dataset:** [dendimaki/v1](https://huggingface.co/datasets/dendimaki/v1)
56
+ <!-- - **Language:** Unknown -->
57
+ <!-- - **License:** Unknown -->
58
+
59
+ ### Model Sources
60
+
61
+ - **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
62
+ - **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
63
+ - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
64
+
65
+ ### Model Labels
66
+ | Label | Examples |
67
+ |:------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
68
+ | 0 | <ul><li>'yeah i would think probably not too it can really feel like a return to layer one if youve become more established'</li><li>'that which is aware of the space and the presence and the stuckness like kind of all of them'</li><li>'most of the time curious and open rather than fearful'</li></ul> |
69
+ | 1 | <ul><li>'and its very its not what i am you know like theres no continuity between me and that spaciousness you know i can feel some spaciousness maybe but man theres you know no continuity between me and that and that would be fine that would be a location one layer two type experience certainly fine'</li><li>'the dominant quality of layer 2 is the sense of allcontaining spaciousness emptiness expansiveness space nothingness openness and so on'</li><li>'location one of layer two'</li></ul> |
70
+ | 2 | <ul><li>'and help us sort of get a general context of where youre at and so you know i think in some cases youre probably getting glimpses of layer three in location one'</li><li>'layer 3 feels like a profound fullness rather than feeling as though it contains everything like layer 2 this feels as though it pervades and infuses everything'</li><li>'at the early end of layer 3 it feels like an essence or presence infusing but different from experience this is typically initially perceived as beginning to infuse the spaciousness of layer 2'</li></ul> |
71
+ | 3 | <ul><li>'expanded sense of self where my attention is most of the time feels more real than anything previous'</li><li>'in location 1 layer 4 every drop of rain is a melody a harmonious blend of natures song and the rhythms of existence'</li><li>'in location 1 layer 4 the setting sun doesnt signify an end but a gentle closure a pause for reflection and gratitude'</li></ul> |
72
+ | 4 | <ul><li>'when subjective experience is centered in layer 1 the activity of the mind will predominate momenttomoment experience'</li><li>'finders often assume this is something to go beyond but it is just the nature of layer 1 and if subjective experience is centered there this quality of a more individualized or personal self naturally arises'</li><li>'ive still probably because of you know heavy conditioning with that ive prioritized you know as of the past couple of years so i have conditioned in addition to this you know a lot of fear based layer early layer one'</li></ul> |
73
+ | 5 | <ul><li>'my goal is to to get to to be fluent between layer two or location two'</li><li>'location 2 somewhat paradoxically the quality of self in layer 2 and later is impersonal'</li><li>'shifting into layer two'</li></ul> |
74
+ | 6 | <ul><li>'and a sense of separation possibly creeps in you know in the middle of the city its hard to say its not as intense i still do feel connected but not to the intensity as when im with the trees'</li><li>'location two layer three'</li><li>'rather than just having a really deep experience of layer three in location two where theres still nondual experience for divine'</li></ul> |
75
+ | 7 | <ul><li>'when it is accessed it is usually mixed with other layers typically the deepest portion of layer 3 because one is generally unable to fully deepen into it in earlier locations it tends to be experienced as a mystery or unknowable'</li><li>'that you had mentioned that location two layer four is like not that likely to happen um and this this sense of like just what is or just you know everything is just the way it is or whatever um that doesnt seem to go in and out um but you know theres theres no perceptual difference to it its just you know its just like not an understanding but its just like it feels like once thats there why would you think otherwise you know'</li><li>'deeper forms of layer 4 are typically only experienced temporarily in location 2 and often do not allow someone to be functional while they last when it is only touched upon temporarily it does not necessarily feel as though it is not a state because the sense of individual self remains partially intact in earlier locations'</li></ul> |
76
+ | 8 | <ul><li>' it will often be experienced from perception being centered in deeper layers'</li><li>'layer one in lay one is existential focusing on meaning and purpose with thought streams and highs and lows in energetic variation'</li><li>'layer 1 is not the default layer that people transition to or experience in location 3 however it can remainquite accessible'</li></ul> |
77
+ | 9 | <ul><li>'the quality of spaciousness emptiness expansiveness openness and so on feels as though it pervades everything as the presence of divinity or as the panpsychist presence depending on how location 3 is showing up for that person'</li><li>'sympathy'</li><li>'so if it were like for instance location three layer two you know it would be a spacious emptiness mixed with the divine or the panpsychist presence or whatever which is kind of a distance from god you know kind of a separation in a way'</li></ul> |
78
+ | 10 | <ul><li>'the main thing was a sense of a kind of strong gravitational pull'</li><li>'you can just play with it for a bit and see like add it as something you can use for deconditioning and then spend the next session really deepening into the location three type direction of layer three and see if you can make that switch'</li><li>'the fieldlike presence of layer 3 feels powerful and penetrating and being deep in layer 3 can seem to have a noticeable influence on other people'</li></ul> |
79
+ | 11 | <ul><li>'this is partly because one is unable to deepen into it and stabilize in it and partly because it cannot be known objectivelyor even subjectively in the usual sense'</li><li>'when it is accessed it is usually mixed with other layers most typically the deepest portions of layer 3 because one is generally unable to fully deepen into it it tends to be experienced as a mystery or unknowable'</li><li>'like initially you cant see anything its just an unknowable'</li></ul> |
80
+ | 12 | <ul><li>'someone is just watching the process unfold without feeling as though they are doing any of it'</li><li>'the extensive compassion and ethical training in some spiritual systems may be designed less for seekers and more to condition finders systems to express these more positive qualities once they are subjectively no longer able to act volitionally'</li><li>'gravity of silence tends to preclude thinking'</li></ul> |
81
+ | 13 | <ul><li>'no mans land'</li><li>'layer 2 is not readily accessible in later locations which tend to gravitate strongly to layer 4'</li><li>'dont feel it'</li></ul> |
82
+ | 14 | <ul><li>'people suppress their peace a little'</li><li>'highly functioning'</li><li>'layer 3 can remain accessible in location 4 though usually only the deepest centerless aspects of it'</li></ul> |
83
+ | 15 | <ul><li>'this diminishes the dimensionality of perception which becomes progressively flat in later locations although someone is not likely to notice unless they come back to an earlier location'</li><li>'there is an ever greater depth of stillnesssilence and an incomparable quality of freedom and peace which is the classical freedom from suffering pursued by spiritual traditions for millennia'</li><li>'nothing appears to have independent or essential existence and there is only undifferentiated realityv'</li></ul> |
84
+ | 16 | <ul><li>'sensory glitches'</li><li>'remained unconscious or who had serious difficulties with the function of their bodies for periods of days weeks and even longer after moving into one of these locations'</li><li>'you know theyre still luminous objects'</li></ul> |
85
+ | 17 | <ul><li>'seer'</li><li>'one of the things most finders notice first is a reduction in their interest in nearly all stories'</li><li>'location one is sort of ideal you know for your life right now'</li></ul> |
86
+ | 18 | <ul><li>'i think its definitely more no emotion than any specific type of emotion but sometimes emotions arise like anger anxiety and sometimes affection'</li><li>'it doesnt sound like you have a very clear memory of that experience of union or dissolving into the divine so it might still have been location two'</li><li>'and so now we would say about location two is and we probably would have been more nuanced even back then'</li></ul> |
87
+ | 19 | <ul><li>'and so in location three there is and youre going between the two most subtle possible places you know potentially location wise'</li><li>'panpsychist sense'</li><li>'usually but not totally'</li></ul> |
88
+ | 20 | <ul><li>'no sense of a personal self'</li><li>'and then you reference location four for like days off like walks in the forest parks'</li><li>'disassembled'</li></ul> |
89
+ | 21 | <ul><li>'psychedelics'</li><li>'myersbriggs cognitive functions'</li><li>'glitch'</li></ul> |
90
+ | 22 | <ul><li>'fundamental well being feels like resisting'</li><li>'how long have you been in fundamental wellbeing'</li><li>'many different potential trajectories within fundamental wellbeing'</li></ul> |
91
+ | 23 | <ul><li>'seekers'</li><li>'deep and profound presentmoment experience'</li><li>'but really turning your attention to whatever deeper qualities of fundamental wellbeing are accessible to you and sinking into those as deeply as you can'</li></ul> |
92
+ | 24 | <ul><li>'was able to settle back into fundamental wellbeing after it got shaken up'</li><li>'so even in fundamental well being its so funny'</li><li>'you know obviously if youve been in fundamental wellbeing since i think youre you might have said 2017 or somewhere around there'</li></ul> |
93
+ | 25 | <ul><li>'when something is very beautiful there is still this sense of im noticing its very beautiful'</li><li>'so you said that you werent sure whether at times your you were viewing layer one'</li><li>'layer one is going to be very present and subjective experience and you know the quality'</li></ul> |
94
+ | 26 | <ul><li>'emptiness of vastness'</li><li>'i was very spacious'</li><li>'in one spot i am spaciousness'</li></ul> |
95
+ | 27 | <ul><li>'so did it have a sense of senselessness'</li><li>'theres a significant amount of richness in the human experience'</li><li>'im more on the layer three since the feeling is really really sunny right now'</li></ul> |
96
+ | 28 | <ul><li>'dimensional flatness'</li><li>'the disappearance of the presence and all of that'</li><li>'i think its further and i also think there are way more layers than four'</li></ul> |
97
+
98
+ ## Evaluation
99
+
100
+ ### Metrics
101
+ | Label | Accuracy |
102
+ |:--------|:---------|
103
+ | **all** | 0.2353 |
104
+
105
+ ## Uses
106
+
107
+ ### Direct Use for Inference
108
+
109
+ First install the SetFit library:
110
+
111
+ ```bash
112
+ pip install setfit
113
+ ```
114
+
115
+ Then you can load this model and run inference.
116
+
117
+ ```python
118
+ from setfit import SetFitModel
119
+
120
+ # Download from the 🤗 Hub
121
+ model = SetFitModel.from_pretrained("dendimaki/few-shots-apeiron-model-v2")
122
+ # Run inference
123
+ preds = model("pervading presence")
124
+ ```
125
+
126
+ <!--
127
+ ### Downstream Use
128
+
129
+ *List how someone could finetune this model on their own dataset.*
130
+ -->
131
+
132
+ <!--
133
+ ### Out-of-Scope Use
134
+
135
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
136
+ -->
137
+
138
+ <!--
139
+ ## Bias, Risks and Limitations
140
+
141
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
142
+ -->
143
+
144
+ <!--
145
+ ### Recommendations
146
+
147
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
148
+ -->
149
+
150
+ ## Training Details
151
+
152
+ ### Training Set Metrics
153
+ | Training set | Min | Median | Max |
154
+ |:-------------|:----|:--------|:----|
155
+ | Word count | 1 | 21.1422 | 146 |
156
+
157
+ | Label | Training Sample Count |
158
+ |:------|:----------------------|
159
+ | 0 | 8 |
160
+ | 1 | 8 |
161
+ | 2 | 8 |
162
+ | 3 | 8 |
163
+ | 4 | 8 |
164
+ | 5 | 8 |
165
+ | 6 | 8 |
166
+ | 7 | 8 |
167
+ | 8 | 8 |
168
+ | 9 | 8 |
169
+ | 10 | 8 |
170
+ | 11 | 8 |
171
+ | 12 | 8 |
172
+ | 13 | 8 |
173
+ | 14 | 8 |
174
+ | 15 | 8 |
175
+ | 16 | 8 |
176
+ | 17 | 8 |
177
+ | 18 | 8 |
178
+ | 19 | 8 |
179
+ | 20 | 8 |
180
+ | 21 | 8 |
181
+ | 22 | 8 |
182
+ | 23 | 8 |
183
+ | 24 | 8 |
184
+ | 25 | 8 |
185
+ | 26 | 8 |
186
+ | 27 | 8 |
187
+ | 28 | 8 |
188
+
189
+ ### Training Hyperparameters
190
+ - batch_size: (16, 16)
191
+ - num_epochs: (2, 2)
192
+ - max_steps: -1
193
+ - sampling_strategy: oversampling
194
+ - num_iterations: 20
195
+ - body_learning_rate: (2e-05, 2e-05)
196
+ - head_learning_rate: 2e-05
197
+ - loss: CosineSimilarityLoss
198
+ - distance_metric: cosine_distance
199
+ - margin: 0.25
200
+ - end_to_end: False
201
+ - use_amp: False
202
+ - warmup_proportion: 0.1
203
+ - seed: 42
204
+ - eval_max_steps: -1
205
+ - load_best_model_at_end: False
206
+
207
+ ### Training Results
208
+ | Epoch | Step | Training Loss | Validation Loss |
209
+ |:------:|:----:|:-------------:|:---------------:|
210
+ | 0.0017 | 1 | 0.2303 | - |
211
+ | 0.0862 | 50 | 0.2167 | - |
212
+ | 0.1724 | 100 | 0.1755 | - |
213
+ | 0.2586 | 150 | 0.1366 | - |
214
+ | 0.3448 | 200 | 0.2175 | - |
215
+ | 0.4310 | 250 | 0.0876 | - |
216
+ | 0.5172 | 300 | 0.1048 | - |
217
+ | 0.6034 | 350 | 0.101 | - |
218
+ | 0.6897 | 400 | 0.0339 | - |
219
+ | 0.7759 | 450 | 0.0466 | - |
220
+ | 0.8621 | 500 | 0.0966 | - |
221
+ | 0.9483 | 550 | 0.0525 | - |
222
+ | 1.0345 | 600 | 0.0266 | - |
223
+ | 1.1207 | 650 | 0.0136 | - |
224
+ | 1.2069 | 700 | 0.0132 | - |
225
+ | 1.2931 | 750 | 0.0625 | - |
226
+ | 1.3793 | 800 | 0.0084 | - |
227
+ | 1.4655 | 850 | 0.0069 | - |
228
+ | 1.5517 | 900 | 0.0163 | - |
229
+ | 1.6379 | 950 | 0.0314 | - |
230
+ | 1.7241 | 1000 | 0.0208 | - |
231
+ | 1.8103 | 1050 | 0.0076 | - |
232
+ | 1.8966 | 1100 | 0.0231 | - |
233
+ | 1.9828 | 1150 | 0.0791 | - |
234
+
235
+ ### Framework Versions
236
+ - Python: 3.10.12
237
+ - SetFit: 1.0.3
238
+ - Sentence Transformers: 2.7.0
239
+ - Transformers: 4.40.0
240
+ - PyTorch: 2.2.1+cu121
241
+ - Datasets: 2.19.0
242
+ - Tokenizers: 0.19.1
243
+
244
+ ## Citation
245
+
246
+ ### BibTeX
247
+ ```bibtex
248
+ @article{https://doi.org/10.48550/arxiv.2209.11055,
249
+ doi = {10.48550/ARXIV.2209.11055},
250
+ url = {https://arxiv.org/abs/2209.11055},
251
+ author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
252
+ keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
253
+ title = {Efficient Few-Shot Learning Without Prompts},
254
+ publisher = {arXiv},
255
+ year = {2022},
256
+ copyright = {Creative Commons Attribution 4.0 International}
257
+ }
258
+ ```
259
+
260
+ <!--
261
+ ## Glossary
262
+
263
+ *Clearly define terms in order to be accessible across audiences.*
264
+ -->
265
+
266
+ <!--
267
+ ## Model Card Authors
268
+
269
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
270
+ -->
271
+
272
+ <!--
273
+ ## Model Card Contact
274
+
275
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
276
+ -->
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sentence-transformers/paraphrase-mpnet-base-v2",
3
+ "architectures": [
4
+ "MPNetModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "mpnet",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
+ "relative_attention_num_buckets": 32,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.40.0",
23
+ "vocab_size": 30527
24
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.0.0",
4
+ "transformers": "4.7.0",
5
+ "pytorch": "1.9.0+cu102"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null
9
+ }
config_setfit.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "normalize_embeddings": false,
3
+ "labels": null
4
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:656fd03dace3a7c416f17970897f911140bcdb6dcca2ba81826bce02a62b70f2
3
+ size 437967672
model_head.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa117aa95697ea85510e5495a9acf7d4e12c1ef3a8bcd029711a22ec339aa689
3
+ size 179487
modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ }
14
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 512,
3
+ "do_lower_case": false
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "104": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "30526": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "do_basic_tokenize": true,
48
+ "do_lower_case": true,
49
+ "eos_token": "</s>",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 512,
52
+ "never_split": null,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "strip_accents": null,
56
+ "tokenize_chinese_chars": true,
57
+ "tokenizer_class": "MPNetTokenizer",
58
+ "unk_token": "[UNK]"
59
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff