ashercn97 commited on
Commit
2566371
·
verified ·
1 Parent(s): 25b75ea

Add SetFit model

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 384,
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 +1,293 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - setfit
4
+ - sentence-transformers
5
+ - text-classification
6
+ - generated_from_setfit_trainer
7
+ widget:
8
+ - text: "The ruling allows for the introduction of the accuser's sexual history as\
9
+ \ a way to challenge credibility. This aspect of the law is often controversial\
10
+ \ and can revive debates about victim-blaming. Many believe that a woman's sexual\
11
+ \ history should not be used to undermine her testimony. However, some legal experts\
12
+ \ argue that this type of evidence is sometimes necessary for a fair trial. \n\
13
+ \nOn the other hand, critics of this ruling may assert that it perpetuates a culture\
14
+ \ of disbelief towards victims of sexual assault. They could argue that such evidence\
15
+ \ could deter future victims from coming forward, fearing their private lives\
16
+ \ may be exposed. Furthermore, the defense might leverage this"
17
+ - text: '03/10/2014: Policy reviewed; no changes to policy statement. Removed deleted
18
+ HCPCS codes J0560, J0570, and J0580 from the Code Reference section. Added HCPCS
19
+ code J0561. 02/18/2015: Policy description updated regarding polymerase chain
20
+ reaction and the evaluation of the Chemoattractant CXCL13. Medically necessary
21
+ policy statement regarding PCR-based direct detection of B. burgdorferi in CSF
22
+ samples updated to add "and may replace serologic documentation of infection"
23
+ to the policy statement.'
24
+ - text: 'In the case of a 17-year-old male with a stabbing injury, the physician has
25
+ an obligation to prioritize the patient''s immediate medical care and ensure his
26
+ safety. Once stabilized, the issue of confidentiality and reporting must be carefully
27
+ considered.
28
+
29
+
30
+ In this scenario, the law typically mandates that medical professionals report
31
+ injuries resulting from violent acts, such as stabbing, to law enforcement. This
32
+ requirement is in place to help protect the patient and address potential broader
33
+ safety concerns. Despite the patient''s fear of gang retaliation, the physician
34
+ must comply with legal obligations to report the injury.
35
+
36
+
37
+ It is crucial for the physician to have an open and empathetic conversation with
38
+ the patient. The physician should explain the legal requirements for reporting
39
+ such injuries, the rationale behind these laws, and the steps involved in the
40
+ process. Additionally, the physician can discuss the resources and support available
41
+ to the patient, such as counseling or protective services, to address his concerns
42
+ about safety and retaliation.
43
+
44
+
45
+ While this situation is challenging due to the patient''s fear, balancing ethical
46
+ obligations to the patient with legal responsibilities is essential. By reporting
47
+ the injury, the physician fulfills their legal duty while seeking to ensure both
48
+ the patient''s and the community''s safety.'
49
+ - text: 'The coverage guidelines outlined in the Medical Policy Manual should not
50
+ be used in lieu of the Member''s specific benefit plan language. POLICY HISTORY7/1992:
51
+ Approved by Medical Policy Advisory Committee (MPAC)
52
+
53
+ 12/30/1999: Policy Guidelines updated
54
+
55
+ 9/21/2001:Policy rewritten to be reflective of Blue Cross Blue Shield Association
56
+ policy # 7.01.05, Code Reference section updated, CPT code 92507, 92510 added
57
+
58
+ 11/2001: Reviewed by MPAC; revisions approved
59
+
60
+ 4/18/2002: Type of Service and Place of Service deleted
61
+
62
+ 5/29/2002: Code Reference section updated, CPT code 69949 added, HCPCS L8619,
63
+ V5269, V5273, V5299, V5336, V5362, V5363 added
64
+
65
+ 3/6/2003: Code Reference section updated, CPT code 92601, 92602, 92603, 92604
66
+ added
67
+
68
+ 7/15/2004: Reviewed by MPAC, bilateral cochlear implantation considered investigational,
69
+ Description section aligned with BCBSA policy # 7.01.05, definition of investigational
70
+ added Policy Guidelines, Sources updated
71
+
72
+ 10/5/2004: Code Reference section updated, CPT code 69949 deleted, CPT 92507 description
73
+ revised, CPT 92508 added, ICD-9 procedure code 20.96, 20.97, 20.99, 95.49 added,
74
+ ICD-9 diagnosis code range 389.10-389.18 listed separately, ICD-9 diagnosis 389.7
75
+ added, HCPCS L8619 note added, HCPCS V5269, V5273, V5299, V5336, V5362, V5363
76
+ deleted
77
+
78
+ 3/22/2005: Code Reference section updated, CPT code 92510 description revised,
79
+ HCPCS L8615, L8616, L8617, L8618 with Note: "See POLICY GUIDELINES for information
80
+ regarding replacement of the external component of the cochlear implant" and effective
81
+ date of 1/1/2005 added. 11/15/2005: HCPCS codes K0731, K0732, L8620 added
82
+
83
+ 03/10/2006: Coding updated. CPT4 / HCPCS 2006 revisions added to policy
84
+
85
+ 03/13/2006: Policy reviewed, no changes
86
+
87
+ 09/13/2006: Coding updated. ICD9 2006 revisions added to policy
88
+
89
+ 12/27/2006: Code Reference section updated per the 2007 HCPCS revisions
90
+
91
+ 3/27/2007: Policy reviewed, no changes to policy statement.'
92
+ - text: 'POLICY HISTORY1/1994: Approved by Medical Policy Advisory Committee (MPAC)
93
+
94
+ 5/1/2002: Type of Service and Place of Service deleted
95
+
96
+ 3/25/2004: Reviewed by MPAC, Policy title “Lyme Disease Treatment” renamed “Intravenous
97
+ Antiobiotic Therapy for Lyme Disease”, Description and Policy sections revised
98
+ to be consistent with BCBSA policy # 5.01.08, intravenous antibiotic therapy changed
99
+ from investigational to medically necessary for certain indications, investigation
100
+ definition added, Sources updated, tables added to Code Reference section
101
+
102
+ 5/5/2004: Code Reference section completed
103
+
104
+ 3/13/2006: Policy reviewed, no changes
105
+
106
+ 9/12/2006: Coding reviewed. ICD9 2006 revisions added to policy
107
+
108
+ 11/13/2006: Code Reference section updated: CPT codes 87475, 87476, and 87477
109
+ deleted from policy
110
+
111
+ 4/24/2007: Policy reviewed, policy statement rewritten for clarification
112
+
113
+ 6/21/2007: Policy reviewed, description updated. Policy statement revised; IV
114
+ antibiotic therapy is not medically necessary for uncomplicated cranial nerve
115
+ palsy associated with Lyme disease and antibiotic-refractory Lyme arthritis
116
+
117
+ 7/19/2007: Reviewed and approved by MPAC
118
+
119
+ 7/10/2009: Policy reviewed, no changes
120
+
121
+ 12/15/2009: Coding Section revised with 2010 CPT4 and HCPCS revisions
122
+
123
+ 02/23/2011: Added the following to the policy statement: Determination of levels
124
+ of the B lymphocyte chemoattractant CXCL13 for diagnosis or monitoring treatment
125
+ is considered investigational. No changes to other policy statements. Removed
126
+ deleted HCPCS codes J0530, J0540, and J0550 from the Code Reference section.'
127
+ metrics:
128
+ - accuracy
129
+ pipeline_tag: text-classification
130
+ library_name: setfit
131
+ inference: true
132
+ base_model: sentence-transformers/all-minilm-l6-v2
133
+ ---
134
+
135
+ # SetFit with sentence-transformers/all-minilm-l6-v2
136
+
137
+ This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/all-minilm-l6-v2](https://huggingface.co/sentence-transformers/all-minilm-l6-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.
138
+
139
+ The model has been trained using an efficient few-shot learning technique that involves:
140
+
141
+ 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
142
+ 2. Training a classification head with features from the fine-tuned Sentence Transformer.
143
+
144
+ ## Model Details
145
+
146
+ ### Model Description
147
+ - **Model Type:** SetFit
148
+ - **Sentence Transformer body:** [sentence-transformers/all-minilm-l6-v2](https://huggingface.co/sentence-transformers/all-minilm-l6-v2)
149
+ - **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
150
+ - **Maximum Sequence Length:** 256 tokens
151
+ - **Number of Classes:** 2 classes
152
+ <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
153
+ <!-- - **Language:** Unknown -->
154
+ <!-- - **License:** Unknown -->
155
+
156
+ ### Model Sources
157
+
158
+ - **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
159
+ - **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
160
+ - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
161
+
162
+ ### Model Labels
163
+ | Label | Examples |
164
+ |:---------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
165
+ | negative | <ul><li>'The decision to lower interest rates suggests that South Korea is attempting to stimulate economic activity. Lower interest rates usually make borrowing cheaper, encouraging businesses to invest and consumers to spend more. However, if consumers are already burdened with debt, they may be hesitant to take on more loans, negating some benefits of the rate cut. \n\nMeanwhile, there is a possibility that lowering rates too much could lead to inflation, as more money circulates in the economy. Alternatively, if the move is not met with increased spending, the central bank could find itself in a situation where it has to further reduce rates or implement unconventional monetary policies. \n\nIt’s'</li><li>"The urgency in the announcement suggests that this is a unique opportunity for investors. Investors who act quickly may benefit from purchasing shares at a favorable rate. However, one must consider that Google’s market valuation is likely already high, which could deter some potential bidders. The notion that Google may soon close the bidding process adds an element of scarcity, compelling investors to hurry. Yet, rushing into an investment without thorough research could lead to poor financial decisions. It is also possible that some investors might believe lucky charms or superstitions could influence the stock market's unpredictability. The competitive landscape in technology could also imply that other companies may soon surpass Google,"</li><li>'The most appropriate initial imaging test for a 28-year-old woman with a breast lump is an ultrasound. Given her age and the characteristics of the lump, an ultrasound is preferred because it effectively evaluates breast lumps in younger women who typically have denser breast tissue, where mammograms might not be as informative. Additionally, an ultrasound can help distinguish between solid masses, like fibroadenomas, and cystic lesions.'</li></ul> |
166
+ | positive | <ul><li>'POLICY HISTORY7/1992: Approved by Medical Policy Advisory Committee (MPAC)\n12/30/1999: Policy Guidelines updated\n9/21/2001:Policy rewritten to be reflective of Blue Cross Blue Shield Association policy # 7.01.05, Code Reference section updated, CPT code 92507, 92510 added\n11/2001: Reviewed by MPAC; revisions approved\n4/18/2002: Type of Service and Place of Service deleted\n5/29/2002: Code Reference section updated, CPT code 69949 added, HCPCS L8619, V5269, V5273, V5299, V5336, V5362, V5363 added\n3/6/2003: Code Reference section updated, CPT code 92601, 92602, 92603, 92604 added\n7/15/2004: Reviewed by MPAC, bilateral cochlear implantation considered investigational, Description section aligned with BCBSA policy # 7.01.05, definition of investigational added Policy Guidelines, Sources updated\n10/5/2004: Code Reference section updated, CPT code 69949 deleted, CPT 92507 description revised, CPT 92508 added, ICD-9 procedure code 20.96, 20.97, 20.99, 95.49 added, ICD-9 diagnosis code range 389.10-389.18 listed separately, ICD-9 diagnosis 389.7 added, HCPCS L8619 note added, HCPCS V5269, V5273, V5299, V5336, V5362, V5363 deleted\n3/22/2005: Code Reference section updated, CPT code 92510 description revised, HCPCS L8615, L8616, L8617, L8618 with Note: "See POLICY GUIDELINES for information regarding replacement of the external component of the cochlear implant" and effective date of 1/1/2005 added. 11/15/2005: HCPCS codes K0731, K0732, L8620 added\n03/10/2006: Coding updated. CPT4 / HCPCS 2006 revisions added to policy\n03/13/2006: Policy reviewed, no changes\n09/13/2006: Coding updated. ICD9 2006 revisions added to policy\n12/27/2006: Code Reference section updated per the 2007 HCPCS revisions\n3/27/2007: Policy reviewed, no changes to policy statement. Bilateral cochlear implantation added to Policy Guidelines section\n06/26/2007: Policy statement updated; bilateral cochlear implantation changed from investigational to may be considered medically necessary\n7/19/2007: Reviewed and approved by MPAC\n9/18/2007: Code reference section updated.'</li><li>'11/28/2012: Policy reviewed; no changes. 03/10/2014: Policy reviewed; no changes to policy statement. Removed deleted HCPCS codes J0560, J0570, and J0580 from the Code Reference section. Added HCPCS code J0561. 02/18/2015: Policy description updated regarding polymerase chain reaction and the evaluation of the Chemoattractant CXCL13.'</li><li>'In order for equipment, devices, drugs or supplies [i.e, technologies], to be considered not investigative, the technology must have final approval from the appropriate governmental bodies, and scientific evidence must permit conclusions concerning the effect of the technology on health outcomes, and the technology must improve the net health outcome, and the technology must be as beneficial as any established alternative and the improvement must be attainable outside the testing/investigational setting. The coverage guidelines outlined in the Medical Policy Manual should not be used in lieu of the Member\'s specific benefit plan language. POLICY HISTORY7/1992: Approved by Medical Policy Advisory Committee (MPAC)\n12/30/1999: Policy Guidelines updated\n9/21/2001:Policy rewritten to be reflective of Blue Cross Blue Shield Association policy # 7.01.05, Code Reference section updated, CPT code 92507, 92510 added\n11/2001: Reviewed by MPAC; revisions approved\n4/18/2002: Type of Service and Place of Service deleted\n5/29/2002: Code Reference section updated, CPT code 69949 added, HCPCS L8619, V5269, V5273, V5299, V5336, V5362, V5363 added\n3/6/2003: Code Reference section updated, CPT code 92601, 92602, 92603, 92604 added\n7/15/2004: Reviewed by MPAC, bilateral cochlear implantation considered investigational, Description section aligned with BCBSA policy # 7.01.05, definition of investigational added Policy Guidelines, Sources updated\n10/5/2004: Code Reference section updated, CPT code 69949 deleted, CPT 92507 description revised, CPT 92508 added, ICD-9 procedure code 20.96, 20.97, 20.99, 95.49 added, ICD-9 diagnosis code range 389.10-389.18 listed separately, ICD-9 diagnosis 389.7 added, HCPCS L8619 note added, HCPCS V5269, V5273, V5299, V5336, V5362, V5363 deleted\n3/22/2005: Code Reference section updated, CPT code 92510 description revised, HCPCS L8615, L8616, L8617, L8618 with Note: "See POLICY GUIDELINES for information regarding replacement of the external component of the cochlear implant" and effective date of 1/1/2005 added. 11/15/2005: HCPCS codes K0731, K0732, L8620 added\n03/10/2006: Coding updated. CPT4 / HCPCS 2006 revisions added to policy\n03/13/2006: Policy reviewed, no changes\n09/13/2006: Coding updated.'</li></ul> |
167
+
168
+ ## Uses
169
+
170
+ ### Direct Use for Inference
171
+
172
+ First install the SetFit library:
173
+
174
+ ```bash
175
+ pip install setfit
176
+ ```
177
+
178
+ Then you can load this model and run inference.
179
+
180
+ ```python
181
+ from setfit import SetFitModel
182
+
183
+ # Download from the 🤗 Hub
184
+ model = SetFitModel.from_pretrained("ashercn97/code-y-v2")
185
+ # Run inference
186
+ preds = model("03/10/2014: Policy reviewed; no changes to policy statement. Removed deleted HCPCS codes J0560, J0570, and J0580 from the Code Reference section. Added HCPCS code J0561. 02/18/2015: Policy description updated regarding polymerase chain reaction and the evaluation of the Chemoattractant CXCL13. Medically necessary policy statement regarding PCR-based direct detection of B. burgdorferi in CSF samples updated to add \"and may replace serologic documentation of infection\" to the policy statement.")
187
+ ```
188
+
189
+ <!--
190
+ ### Downstream Use
191
+
192
+ *List how someone could finetune this model on their own dataset.*
193
+ -->
194
+
195
+ <!--
196
+ ### Out-of-Scope Use
197
+
198
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
199
+ -->
200
+
201
+ <!--
202
+ ## Bias, Risks and Limitations
203
+
204
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
205
+ -->
206
+
207
+ <!--
208
+ ### Recommendations
209
+
210
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
211
+ -->
212
+
213
+ ## Training Details
214
+
215
+ ### Training Set Metrics
216
+ | Training set | Min | Median | Max |
217
+ |:-------------|:----|:--------|:----|
218
+ | Word count | 45 | 143.875 | 298 |
219
+
220
+ | Label | Training Sample Count |
221
+ |:---------|:----------------------|
222
+ | negative | 8 |
223
+ | positive | 8 |
224
+
225
+ ### Training Hyperparameters
226
+ - batch_size: (16, 16)
227
+ - num_epochs: (4, 4)
228
+ - max_steps: -1
229
+ - sampling_strategy: oversampling
230
+ - body_learning_rate: (2e-05, 1e-05)
231
+ - head_learning_rate: 0.01
232
+ - loss: CosineSimilarityLoss
233
+ - distance_metric: cosine_distance
234
+ - margin: 0.25
235
+ - end_to_end: False
236
+ - use_amp: False
237
+ - warmup_proportion: 0.1
238
+ - l2_weight: 0.01
239
+ - seed: 42
240
+ - eval_max_steps: -1
241
+ - load_best_model_at_end: True
242
+
243
+ ### Training Results
244
+ | Epoch | Step | Training Loss | Validation Loss |
245
+ |:------:|:----:|:-------------:|:---------------:|
246
+ | 0.1111 | 1 | 0.3269 | - |
247
+ | 1.0 | 9 | - | 0.2071 |
248
+ | 2.0 | 18 | - | 0.1190 |
249
+ | 3.0 | 27 | - | 0.0741 |
250
+ | 4.0 | 36 | - | 0.0629 |
251
+
252
+ ### Framework Versions
253
+ - Python: 3.11.10
254
+ - SetFit: 1.1.2
255
+ - Sentence Transformers: 4.0.2
256
+ - Transformers: 4.51.3
257
+ - PyTorch: 2.4.1+cu124
258
+ - Datasets: 3.5.0
259
+ - Tokenizers: 0.21.1
260
+
261
+ ## Citation
262
+
263
+ ### BibTeX
264
+ ```bibtex
265
+ @article{https://doi.org/10.48550/arxiv.2209.11055,
266
+ doi = {10.48550/ARXIV.2209.11055},
267
+ url = {https://arxiv.org/abs/2209.11055},
268
+ author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
269
+ keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
270
+ title = {Efficient Few-Shot Learning Without Prompts},
271
+ publisher = {arXiv},
272
+ year = {2022},
273
+ copyright = {Creative Commons Attribution 4.0 International}
274
+ }
275
+ ```
276
+
277
+ <!--
278
+ ## Glossary
279
+
280
+ *Clearly define terms in order to be accessible across audiences.*
281
+ -->
282
+
283
+ <!--
284
+ ## Model Card Authors
285
+
286
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
287
+ -->
288
+
289
+ <!--
290
+ ## Model Card Contact
291
+
292
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
293
+ -->
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertModel"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 384,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 1536,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 6,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "torch_dtype": "float32",
21
+ "transformers_version": "4.51.3",
22
+ "type_vocab_size": 2,
23
+ "use_cache": true,
24
+ "vocab_size": 30522
25
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "4.0.2",
4
+ "transformers": "4.51.3",
5
+ "pytorch": "2.4.1+cu124"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": "cosine"
10
+ }
config_setfit.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "normalize_embeddings": false,
3
+ "labels": [
4
+ "negative",
5
+ "positive"
6
+ ]
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4b356b83b8701d5ac569dfe4ccea9b1aaea3c24e2ae370087438b48af25d3a1
3
+ size 90864192
model_head.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b29f2032e1d64f28571de835185e824908b103e50c8acba6747bdfea109c13f
3
+ size 3983
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": 256,
3
+ "do_lower_case": false
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 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "max_length": 128,
51
+ "model_max_length": 256,
52
+ "never_split": null,
53
+ "pad_to_multiple_of": null,
54
+ "pad_token": "[PAD]",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
+ "sep_token": "[SEP]",
58
+ "stride": 0,
59
+ "strip_accents": null,
60
+ "tokenize_chinese_chars": true,
61
+ "tokenizer_class": "BertTokenizer",
62
+ "truncation_side": "right",
63
+ "truncation_strategy": "longest_first",
64
+ "unk_token": "[UNK]"
65
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff