mibrahimalpha commited on
Commit
3382434
·
verified ·
1 Parent(s): 34d590c

Upload 8 files

Browse files
assignment3/Models/README.md ADDED
@@ -0,0 +1,652 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - sentence-transformers
4
+ - sentence-similarity
5
+ - feature-extraction
6
+ - dense
7
+ - generated_from_trainer
8
+ - dataset_size:35100
9
+ - loss:SoftmaxLoss
10
+ base_model: AI-Growth-Lab/PatentSBERTa
11
+ widget:
12
+ - source_sentence: '1. A multi-modal monitor system to obtain quantitative, coordinated
13
+ measurement of emissions from a turbine having at least one of a blade and a rotor,
14
+ comprising: a first sensor for measuring at least one type of emission generated
15
+ by the turbine during movement of the at least one of the blade and the rotor
16
+ and generating a first emission signal; a second sensor for measuring a different
17
+ type of emission generated by the turbine and generating a second emission signal;
18
+ a third sensor for measuring a different type of emission than that measured by
19
+ the first and second sensors; a data storage unit capable of storing emission
20
+ signals over time; and a housing containing at least the first, second and third
21
+ sensors and capable of being placed operationally at a distance from the turbine
22
+ in an outdoor location to be monitored; wherein each of the first, second, and
23
+ third sensors measures one type of emission selected from mechanical wave, optical
24
+ radiation, electrical, vibration, audible sound, and infrasound.'
25
+ sentences:
26
+ - '1. An in-wheel motor installed inside a wheel disk of a wheel to rotationally
27
+ drive the wheel around a shaft of the wheel by way of applying a current thereto,
28
+ the in-wheel motor comprising: a coreless cylindrical coil body to which a lead
29
+ wire for applying a current is connected, the shaft being inserted in an inner
30
+ circumferential side of the coil body, the coil body supported at one end by a
31
+ coil body support member that is fixed to the shaft; a cylindrical outer yoke
32
+ that is disposed on an outer circumferential side of the coil body, and is fixed
33
+ to the wheel disk; a magnet that is fixed on an inner circumferential face of
34
+ the outer yoke, an inner surface of the magnet disposed proximate an outer circumferential
35
+ face of the coil body; a cylindrical inner yoke having an outer circumferential
36
+ face disposed proximate to an inner circumferential face of the coil body, the
37
+ inner yoke being fixed to the outer yoke and being rotatable around the shaft;
38
+ a brake disk that is fixed to an inner circumferential side of the inner yoke;
39
+ and a caliper that is provided on the inner circumferential side of the inner
40
+ yoke to brake the brake disk.'
41
+ - '1. A multi-modal monitor system to obtain quantitative, coordinated measurement
42
+ of emissions from a turbine having at least one of a blade and a rotor, comprising:
43
+ a first sensor for measuring at least one type of emission generated by the turbine
44
+ during movement of the at least one of the blade and the rotor and generating
45
+ a first emission signal; a second sensor for measuring a different type of emission
46
+ generated by the turbine and generating a second emission signal; a third sensor
47
+ for measuring a different type of emission than that measured by the first and
48
+ second sensors; a data storage unit capable of storing emission signals over time;
49
+ and a housing containing at least the first, second and third sensors and capable
50
+ of being placed operationally at a distance from the turbine in an outdoor location
51
+ to be monitored; wherein each of the first, second, and third sensors measures
52
+ one type of emission selected from mechanical wave, optical radiation, electrical,
53
+ vibration, audible sound, and infrasound.'
54
+ - 1. An identification medium comprising a cholesteric liquid crystal layer on which
55
+ a hologram is formed, a first supporting member and a second supporting member
56
+ between which the cholesteric liquid crystal layer is sandwiched, and at least
57
+ one thereof is made of transparent material which does not disturb circularly
58
+ polarized light reflected from the cholesteric liquid crystal layer, and a mounting
59
+ region to be sewn onto an object, the first supporting member and the second supporting
60
+ member extending to the mounting region and being adhered directly to each other
61
+ by an adhesive layer in the mounting region, wherein the first supporting member
62
+ is a polyurethane film or a cloth, and the cholesteric liquid crystal layer is
63
+ affixed to both of the first supporting member and the second supporting member
64
+ by adhesive layers.
65
+ - source_sentence: '1. A process of making light olefins, in a combined Oxygenate
66
+ to Olefin (XTO)-Olefin Cracking (OC) process, from an oxygen-containing, halogenide-containing
67
+ or sulphur-containing organic feedstock comprising: selecting a molecular sieve
68
+ having pores of 10- or more-membered rings, wherein the molecular sieve is a zeolite;
69
+ contacting the molecular sieve with a metal silicate, different from said molecular
70
+ sieve, comprising at least one alkaline earth metal to form a catalyst composite,
71
+ wherein the catalyst composite comprises at least 10 wt % of the zeolite and at
72
+ least 0.1 wt % of silicate based on a total weight of the catalyst composite;
73
+ providing a first portion and a second portion of a feedstock that is an oxygen-containing,
74
+ halogenide-containing, or sulphur-containing organic feedstock; providing an XTO
75
+ reaction zone, an OC reaction zone and a catalyst regeneration zone, wherein one
76
+ or more catalysts are in the XTO reaction zone and the same one or more catalysts
77
+ are in the OC reaction zone, wherein at least one of the one or more catalysts
78
+ is the catalyst composite; wherein the one or more catalysts circulate in the
79
+ three zones, such that at least a portion of the one or more catalysts from the
80
+ catalyst regeneration zone is passed to the OC reaction zone, at least a portion
81
+ of the one or more catalysts in the OC reaction zone is passed to the XTO reaction
82
+ zone and at least a portion of the one or more catalysts in the XTO reaction zone
83
+ is passed to the catalyst regeneration zone; contacting the first portion of the
84
+ feedstock in the XTO reactor with the one or more catalysts at conditions effective
85
+ to convert at least a portion of the feedstock to form an XTO reactor effluent
86
+ comprising light olefins and a heavy hydrocarbon fraction; separating the light
87
+ olefins from the heavy hydrocarbon fraction; and contacting the heavy hydrocarbon
88
+ fraction and the second portion of the feedstock in the OC reactor with the one
89
+ or more catalysts at conditions effective to convert at least a portion of the
90
+ heavy hydrocarbon fraction and the feedstock to light olefins.'
91
+ sentences:
92
+ - '1. A process of making light olefins, in a combined Oxygenate to Olefin (XTO)-Olefin
93
+ Cracking (OC) process, from an oxygen-containing, halogenide-containing or sulphur-containing
94
+ organic feedstock comprising: selecting a molecular sieve having pores of 10-
95
+ or more-membered rings, wherein the molecular sieve is a zeolite; contacting the
96
+ molecular sieve with a metal silicate, different from said molecular sieve, comprising
97
+ at least one alkaline earth metal to form a catalyst composite, wherein the catalyst
98
+ composite comprises at least 10 wt % of the zeolite and at least 0.1 wt % of silicate
99
+ based on a total weight of the catalyst composite; providing a first portion and
100
+ a second portion of a feedstock that is an oxygen-containing, halogenide-containing,
101
+ or sulphur-containing organic feedstock; providing an XTO reaction zone, an OC
102
+ reaction zone and a catalyst regeneration zone, wherein one or more catalysts
103
+ are in the XTO reaction zone and the same one or more catalysts are in the OC
104
+ reaction zone, wherein at least one of the one or more catalysts is the catalyst
105
+ composite; wherein the one or more catalysts circulate in the three zones, such
106
+ that at least a portion of the one or more catalysts from the catalyst regeneration
107
+ zone is passed to the OC reaction zone, at least a portion of the one or more
108
+ catalysts in the OC reaction zone is passed to the XTO reaction zone and at least
109
+ a portion of the one or more catalysts in the XTO reaction zone is passed to the
110
+ catalyst regeneration zone; contacting the first portion of the feedstock in the
111
+ XTO reactor with the one or more catalysts at conditions effective to convert
112
+ at least a portion of the feedstock to form an XTO reactor effluent comprising
113
+ light olefins and a heavy hydrocarbon fraction; separating the light olefins from
114
+ the heavy hydrocarbon fraction; and contacting the heavy hydrocarbon fraction
115
+ and the second portion of the feedstock in the OC reactor with the one or more
116
+ catalysts at conditions effective to convert at least a portion of the heavy hydrocarbon
117
+ fraction and the feedstock to light olefins.'
118
+ - '1. A needle assembly system comprising: a needle assembly including a needle
119
+ and a needle support; a cover including a distal portion adapted to house at least
120
+ a distal end of the needle and a proximal portion adapted to house the needle
121
+ support, wherein the proximal portion includes a first portion and a second portion,
122
+ wherein the first portion has a first inner diameter substantially equal to an
123
+ outer diameter of the needle support such that the first portion of the proximal
124
+ portion of the cover is frictionally engaged with the needle support in a first
125
+ position and the second portion has a second inner diameter greater than the diameter
126
+ of the needle support such that there is radial separation between the cover and
127
+ the needle support in a second position, wherein the second portion of the proximal
128
+ portion has a length greater than or equal to a length of the needle support,
129
+ wherein the needle support is configured to be axially advanced from the first
130
+ position to the second position such that a proximal end of the needle assembly
131
+ does not extend past a proximal end of the cover.'
132
+ - '1. A membrane electrode assembly for a polymer electrolyte fuel cell, comprising:
133
+ an electrolyte membrane; a catalyst layer; a conductive porous gas diffusion layer,
134
+ wherein the catalyst layer and the electrolyte membrane have common boundaries;
135
+ and grooves for allowing one of passage and retention of a fluid being formed
136
+ in the common boundaries, and wherein the grooves have a tapered shape such that
137
+ a width of each groove is largest at the common boundary, and wherein the catalyst
138
+ layer is disposed between the gas diffusion layer and the electrolyte membrane.'
139
+ - source_sentence: '1. A computer hardware-implemented method of preventing a cascading
140
+ failure in a complex stream computer system, wherein a cascading failure results
141
+ in an untrustworthy output from the complex stream computer system, and wherein
142
+ the computer hardware-implemented method comprises: receiving a first set of binary
143
+ data that identifies multiple subcomponents in a complex stream computer system,
144
+ wherein the identified multiple subcomponents comprise multiple upstream subcomponents
145
+ and a downstream subcomponent, and wherein the multiple upstream subcomponents
146
+ execute upstream computational processes; receiving a second set of binary data
147
+ that identifies multiple outputs generated by the multiple upstream subcomponents;
148
+ receiving a third set of binary data that identifies multiple inputs to the downstream
149
+ subcomponent, wherein the identified multiple inputs to the downstream subcomponent
150
+ are the identified multiple outputs generated by the multiple upstream subcomponents,
151
+ and wherein the identified multiple inputs are inputs to a downstream computational
152
+ process that is executed by the downstream subcomponent; examining, by computer
153
+ hardware, each of the upstream computational processes to determine an accuracy
154
+ of each of the identified multiple outputs based upon: generating, by computer
155
+ hardware, accuracy values by assigning a determined accuracy value to each of
156
+ the identified multiple outputs, wherein the determined accuracy value describes
157
+ a confidence level of an accuracy of each of the identified multiple outputs,
158
+ and wherein each of the identified multiple outputs are created by a separate
159
+ upstream computational process in separate upstream subcomponents from the multiple
160
+ upstream subcomponents; generating, by the computer hardware, weighting values
161
+ by assigning a weighting value to each of the identified multiple inputs to the
162
+ downstream subcomponent, wherein the weighting value describes a criticality level
163
+ of each of the identified multiple inputs when executing the downstream computational
164
+ process in the downstream subcomponent; and utilizing, by the computer hardware,
165
+ the determined accuracy values and the weighting values to dynamically adjust
166
+ which of the identified multiple inputs are used by the downstream subcomponent
167
+ until an output from the downstream subcomponent meets a predefined trustworthiness
168
+ level, wherein a trustworthiness of the output from the downstream subcomponent
169
+ is based on the determined accuracy value of each of the identified multiple outputs
170
+ and the weighting value of each of the identified multiple inputs to the downstream
171
+ subcomponent.'
172
+ sentences:
173
+ - '1. A method comprising: encoding, by a processing module of a computing device,
174
+ a data segment of a data object into a set of encoded data slices; determining,
175
+ by the processing module, storage requirements of the data object; determining,
176
+ by the processing module, memory device capabilities of a plurality of distributed
177
+ storage units based on types of memory devices, wherein at least one of the distributed
178
+ storage units of the plurality of distributed storage units includes multiple
179
+ types of memory devices, and wherein a first type of memory device has first memory
180
+ characteristics and a second type of memory device has second memory characteristics;
181
+ determining, by the processing module, a storage mode based on one or more of
182
+ the storage requirements of the data object, the memory device capabilities of
183
+ a dispersed storage network (DSN) memory, and a type of data, the storage mode
184
+ including a time phase indicator specifying one or more time intervals for a given
185
+ set of storage requirements; identifying, by the processing module, a set of distributed
186
+ storage units of the plurality of distributed storage units that have at least
187
+ one or more of the multiple types of memory devices based on the storage mode;
188
+ and sending, by the computing device, at least a write threshold number of encoded
189
+ data slices of the data segment to the set of distributed storage units for storage
190
+ in the at least one or more of the multiple types of memory devices in accordance
191
+ with the storage mode, wherein the write threshold number is greater than a decode
192
+ threshold number and less than a total number, wherein the decode threshold number
193
+ corresponds to a minimum number of encoded data slices of the set of encoded data
194
+ slices that is needed to recover the data segment, wherein the total number corresponds
195
+ to a number of encoded data slices in the set of encoded data slices.'
196
+ - '1. A chemical looping combustion apparatus for solid fuels using different oxygen
197
+ carriers, comprising: a solid fuel chemical looping combustor configured to receive
198
+ solid fuels and to produce carbon dioxide and steam by combustion of the solid
199
+ fuels; a gaseous fuel chemical looping combustor configured to receive gaseous
200
+ fuels and to produce carbon dioxide and steam by combustion of the gaseous fuels;
201
+ and a devolatilization reactor configured to produce solids and gases by devolatilizing
202
+ the solid fuels, wherein the solid fuels received by the solid fuel chemical looping
203
+ combustor and the gaseous fuels received by the gaseous fuel chemical looping
204
+ combustor are the solids and the gases produced by the devolatilization reactor,
205
+ respectively, wherein the solid fuel chemical looping combustor comprises: an
206
+ oxidation reactor; a loop seal configured to receive a metallic oxide from the
207
+ oxidation reactor; a reduction reactor configured to cause the solid fuels flowing
208
+ from the devolatilization reactor and the metallic oxide transferred from the
209
+ loop seal to react with each other, thereby reducing the oxygen carriers; a downcomer
210
+ connected to an outlet of the loop seal and extending to a lower portion of the
211
+ reduction reactor to receive the solid fuels, wherein the oxygen carriers reduced
212
+ in the reduction reactor are provided to the oxidation reactor such that the oxygen
213
+ carriers are re-circulated, and wherein the solid fuels are introduced into the
214
+ reduction reactor from a middle point of a longitudinal length of the downcomer.'
215
+ - '1. A computer hardware-implemented method of preventing a cascading failure in
216
+ a complex stream computer system, wherein a cascading failure results in an untrustworthy
217
+ output from the complex stream computer system, and wherein the computer hardware-implemented
218
+ method comprises: receiving a first set of binary data that identifies multiple
219
+ subcomponents in a complex stream computer system, wherein the identified multiple
220
+ subcomponents comprise multiple upstream subcomponents and a downstream subcomponent,
221
+ and wherein the multiple upstream subcomponents execute upstream computational
222
+ processes; receiving a second set of binary data that identifies multiple outputs
223
+ generated by the multiple upstream subcomponents; receiving a third set of binary
224
+ data that identifies multiple inputs to the downstream subcomponent, wherein the
225
+ identified multiple inputs to the downstream subcomponent are the identified multiple
226
+ outputs generated by the multiple upstream subcomponents, and wherein the identified
227
+ multiple inputs are inputs to a downstream computational process that is executed
228
+ by the downstream subcomponent; examining, by computer hardware, each of the upstream
229
+ computational processes to determine an accuracy of each of the identified multiple
230
+ outputs based upon: generating, by computer hardware, accuracy values by assigning
231
+ a determined accuracy value to each of the identified multiple outputs, wherein
232
+ the determined accuracy value describes a confidence level of an accuracy of each
233
+ of the identified multiple outputs, and wherein each of the identified multiple
234
+ outputs are created by a separate upstream computational process in separate upstream
235
+ subcomponents from the multiple upstream subcomponents; generating, by the computer
236
+ hardware, weighting values by assigning a weighting value to each of the identified
237
+ multiple inputs to the downstream subcomponent, wherein the weighting value describes
238
+ a criticality level of each of the identified multiple inputs when executing the
239
+ downstream computational process in the downstream subcomponent; and utilizing,
240
+ by the computer hardware, the determined accuracy values and the weighting values
241
+ to dynamically adjust which of the identified multiple inputs are used by the
242
+ downstream subcomponent until an output from the downstream subcomponent meets
243
+ a predefined trustworthiness level, wherein a trustworthiness of the output from
244
+ the downstream subcomponent is based on the determined accuracy value of each
245
+ of the identified multiple outputs and the weighting value of each of the identified
246
+ multiple inputs to the downstream subcomponent.'
247
+ - source_sentence: '1. A method comprising the steps of: (a) providing one or more
248
+ tissues, cell types, or a lysate thereof, obtained from a patient administered
249
+ at least one dose of a compound of formula I:  or a pharmaceutically acceptable
250
+ salt thereof, wherein: Ring A is selected from: Ring A is an optionally substituted
251
+ group selected from phenyl, an 8-10 membered bicyclic partially unsaturated or
252
+ aryl ring, a 5-6 membered monocyclic heteroaryl ring having 1-4 heteroatoms independently
253
+ selected from nitrogen, oxygen, or sulfur, or an 8-10 membered bicyclic heteroaryl
254
+ ring having 1-5 heteroatoms independently selected from nitrogen, oxygen, or sulfur;
255
+ Ring B is phenyl, a 5-6 membered heteroaryl ring having 1-3 heteroatoms independently
256
+ selected from N, O or S, a 5-6 membered saturated heterocyclic ring having 1-2
257
+ heteroatoms independently selected from N, O or S, or an 8-10 membered bicyclic
258
+ partially unsaturated or aryl ring having 1-3 heteroatoms independently selected
259
+ from N, O or S; R R L is a bivalent C L is a bivalent C L is a bivalent C L is
260
+ a bivalent C L is a bivalent C Y is hydrogen, C L is a bivalent C Y is C L is
261
+ a covalent bond and Y is selected from: L is —C(O)— and Y is selected from: L
262
+ is —N(R)C(O)— and Y is selected from: L is a bivalent C L is —CH each R R W is
263
+ a bivalent C R m is 0, 1, 2, 3 or 4; each R (b) contacting said tissue, cell type,
264
+ or a lysate thereof, with a compound of formula I, tethered to a detectable moiety
265
+ to form a probe compound, wherein at least one protein kinase present in said
266
+ tissue, cell type, or a lysate thereof, is covalently modified and the detectable
267
+ moiety is selected from the group consisting of a fluorescent label, mass-tag,
268
+ chemiluminescent group, chromophore, electron dense group, or an energy transfer
269
+ agent; and (c) measuring the amount of said protein kinase covalently modified
270
+ by the probe compound thereby to determine occupancy of said protein kinase by
271
+ said compound of formula I as compared to occupancy of said protein kinase by
272
+ said probe compound.'
273
+ sentences:
274
+ - '1. A detection circuit that is connectable to a magnetic sensor in which a first
275
+ sensor unit and a second sensor unit are arranged at a predetermined angle with
276
+ respect to each other, each sensor unit having a bridge circuit of magnetoresistance
277
+ elements, the detection circuit comprising: a first comparison circuit including:
278
+ a second comparison circuit including: a rotation angle calculation circuit that
279
+ calculates a rotation angle of a magnetic field based on one of the comparison
280
+ results of the first comparison circuit and a comparison result of the second
281
+ comparison circuit, the rotation angle calculation circuit including a logic circuit
282
+ that generates a third detection signal based on a comparison result of the third
283
+ comparator and a comparison result of the fourth comparator.'
284
+ - '1. A method comprising the steps of: (a) providing one or more tissues, cell
285
+ types, or a lysate thereof, obtained from a patient administered at least one
286
+ dose of a compound of formula I:  or a pharmaceutically acceptable salt thereof,
287
+ wherein: Ring A is selected from: Ring A is an optionally substituted group selected
288
+ from phenyl, an 8-10 membered bicyclic partially unsaturated or aryl ring, a 5-6
289
+ membered monocyclic heteroaryl ring having 1-4 heteroatoms independently selected
290
+ from nitrogen, oxygen, or sulfur, or an 8-10 membered bicyclic heteroaryl ring
291
+ having 1-5 heteroatoms independently selected from nitrogen, oxygen, or sulfur;
292
+ Ring B is phenyl, a 5-6 membered heteroaryl ring having 1-3 heteroatoms independently
293
+ selected from N, O or S, a 5-6 membered saturated heterocyclic ring having 1-2
294
+ heteroatoms independently selected from N, O or S, or an 8-10 membered bicyclic
295
+ partially unsaturated or aryl ring having 1-3 heteroatoms independently selected
296
+ from N, O or S; R R L is a bivalent C L is a bivalent C L is a bivalent C L is
297
+ a bivalent C L is a bivalent C Y is hydrogen, C L is a bivalent C Y is C L is
298
+ a covalent bond and Y is selected from: L is —C(O)— and Y is selected from: L
299
+ is —N(R)C(O)— and Y is selected from: L is a bivalent C L is —CH each R R W is
300
+ a bivalent C R m is 0, 1, 2, 3 or 4; each R (b) contacting said tissue, cell type,
301
+ or a lysate thereof, with a compound of formula I, tethered to a detectable moiety
302
+ to form a probe compound, wherein at least one protein kinase present in said
303
+ tissue, cell type, or a lysate thereof, is covalently modified and the detectable
304
+ moiety is selected from the group consisting of a fluorescent label, mass-tag,
305
+ chemiluminescent group, chromophore, electron dense group, or an energy transfer
306
+ agent; and (c) measuring the amount of said protein kinase covalently modified
307
+ by the probe compound thereby to determine occupancy of said protein kinase by
308
+ said compound of formula I as compared to occupancy of said protein kinase by
309
+ said probe compound.'
310
+ - 1. A method of treating lupus in a mammal, the method comprising administering
311
+ to the mammal an antibody which binds an interleukin 3 receptor α (IL-3Rα) chain
312
+ and which kills a plasmacytoid dendritic cell (pDC) or basophil to which it binds
313
+ to thereby treat lupus in the mammal, wherein the antibody comprises the variable
314
+ regions of antibody 7G3 or is a humanized form of antibody 7G3, and wherein the
315
+ antibody is not conjugated to a toxic compound that kills a cell to which the
316
+ antibody binds, and wherein the antibody is capable of inducing an enhanced level
317
+ of effector function, and wherein the effector function is antibody-dependent
318
+ cell cytotoxicity (ADCC) and/or antibody-dependent cell mediated phagocytosis
319
+ (ADCP).
320
+ - source_sentence: 1. A sputtering target having a component composition that contains
321
+ 1 to 40 at % of Ga, 0.05 to 2 at % of Na as metal element components, and the
322
+ balance composed of Cu and unavoidable impurities, wherein the sputtering target
323
+ contains Na in at least one form selected from among sodium fluoride, sodium sulfide,
324
+ and sodium selenide and the content of oxygen is from 100 to 1,000 ppm.
325
+ sentences:
326
+ - '1. An insulation bobbin unit of a stator, comprising: a first insulation bobbin
327
+ having a first body and a plurality of first extension members coupled with the
328
+ first body, wherein the first body has a first assembly hole, each of the extension
329
+ members has a first wound portion, the first wound portion has a first top plate
330
+ and one first side wall located on one side of the first top plate, and a thickness
331
+ of the first top plate is smaller than that of the first side wall; and a second
332
+ insulation bobbin having a second body and a plurality of second extension members,
333
+ wherein the second body is coupled with the first body and has a second assembly
334
+ hole aligning and communicating with the first assembly hole, the second extension
335
+ members are coupled with the second body and aligned with the first extension
336
+ members, each of the second extension members has a second wound portion, the
337
+ second wound portion has a second top plate and one second side wall located on
338
+ one side of the second top plate, and a room is defined by the first top plate,
339
+ the first side wall, the second top plate and the second side wall, wherein the
340
+ first side wall is aligned with one edge of the second top plate that is not mounted
341
+ with the second side wall, and the second side wall is aligned with one edge of
342
+ the first top plate that is not mounted with the first side wall.'
343
+ - 1. A sputtering target having a component composition that contains 1 to 40 at
344
+ % of Ga, 0.05 to 2 at % of Na as metal element components, and the balance composed
345
+ of Cu and unavoidable impurities, wherein the sputtering target contains Na in
346
+ at least one form selected from among sodium fluoride, sodium sulfide, and sodium
347
+ selenide and the content of oxygen is from 100 to 1,000 ppm.
348
+ - '1. An electrical energy supply system providing voltage to a first load, comprising:
349
+ an external power group providing an external voltage; and a DC supply device
350
+ receiving the external voltage and comprising: a first bus receiving the external
351
+ voltage and coupled to the first load; a first converting unit converting the
352
+ external voltage into a first converted voltage when a voltage level of the first
353
+ bus reaches a pre-determined level, and converting a first stored voltage to generate
354
+ a converted result when the voltage level of the first bus is less than the pre-determined
355
+ level; a first storage unit storing the first converted voltage when the voltage
356
+ level of the first bus reaches the pre-determined level and providing the first
357
+ stored voltage to the first converting unit when the voltage level of the first
358
+ bus is less than the pre-determined level; and a first smart energy management
359
+ system (SEMS) controlling at least one of the first converting unit, the external
360
+ power group and the first load according to at least one of the external voltage,
361
+ a voltage level of the first bus and a voltage level of the first storage unit,
362
+ wherein the first SEMS controls the external power group to adjust the external
363
+ voltage according to the voltage level of the first bus.'
364
+ pipeline_tag: sentence-similarity
365
+ library_name: sentence-transformers
366
+ ---
367
+
368
+ # SentenceTransformer based on AI-Growth-Lab/PatentSBERTa
369
+
370
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [AI-Growth-Lab/PatentSBERTa](https://huggingface.co/AI-Growth-Lab/PatentSBERTa). 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.
371
+
372
+ ## Model Details
373
+
374
+ ### Model Description
375
+ - **Model Type:** Sentence Transformer
376
+ - **Base model:** [AI-Growth-Lab/PatentSBERTa](https://huggingface.co/AI-Growth-Lab/PatentSBERTa) <!-- at revision 3ff1d553c861d8f5bfd902333d97fc95eb6b4c8f -->
377
+ - **Maximum Sequence Length:** 512 tokens
378
+ - **Output Dimensionality:** 768 dimensions
379
+ - **Similarity Function:** Cosine Similarity
380
+ <!-- - **Training Dataset:** Unknown -->
381
+ <!-- - **Language:** Unknown -->
382
+ <!-- - **License:** Unknown -->
383
+
384
+ ### Model Sources
385
+
386
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
387
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers)
388
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
389
+
390
+ ### Full Model Architecture
391
+
392
+ ```
393
+ SentenceTransformer(
394
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': 'MPNetModel'})
395
+ (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})
396
+ )
397
+ ```
398
+
399
+ ## Usage
400
+
401
+ ### Direct Usage (Sentence Transformers)
402
+
403
+ First install the Sentence Transformers library:
404
+
405
+ ```bash
406
+ pip install -U sentence-transformers
407
+ ```
408
+
409
+ Then you can load this model and run inference.
410
+ ```python
411
+ from sentence_transformers import SentenceTransformer
412
+
413
+ # Download from the 🤗 Hub
414
+ model = SentenceTransformer("sentence_transformers_model_id")
415
+ # Run inference
416
+ sentences = [
417
+ '1. A sputtering target having a component composition that contains 1 to 40 at % of Ga, 0.05 to 2 at % of Na as metal element components, and the balance composed of Cu and unavoidable impurities, wherein the sputtering target contains Na in at least one form selected from among sodium fluoride, sodium sulfide, and sodium selenide and the content of oxygen is from 100 to 1,000 ppm.',
418
+ '1. A sputtering target having a component composition that contains 1 to 40 at % of Ga, 0.05 to 2 at % of Na as metal element components, and the balance composed of Cu and unavoidable impurities, wherein the sputtering target contains Na in at least one form selected from among sodium fluoride, sodium sulfide, and sodium selenide and the content of oxygen is from 100 to 1,000 ppm.',
419
+ '1. An electrical energy supply system providing voltage to a first load, comprising: an external power group providing an external voltage; and a DC supply device receiving the external voltage and comprising: a first bus receiving the external voltage and coupled to the first load; a first converting unit converting the external voltage into a first converted voltage when a voltage level of the first bus reaches a pre-determined level, and converting a first stored voltage to generate a converted result when the voltage level of the first bus is less than the pre-determined level; a first storage unit storing the first converted voltage when the voltage level of the first bus reaches the pre-determined level and providing the first stored voltage to the first converting unit when the voltage level of the first bus is less than the pre-determined level; and a first smart energy management system (SEMS) controlling at least one of the first converting unit, the external power group and the first load according to at least one of the external voltage, a voltage level of the first bus and a voltage level of the first storage unit, wherein the first SEMS controls the external power group to adjust the external voltage according to the voltage level of the first bus.',
420
+ ]
421
+ embeddings = model.encode(sentences)
422
+ print(embeddings.shape)
423
+ # [3, 768]
424
+
425
+ # Get the similarity scores for the embeddings
426
+ similarities = model.similarity(embeddings, embeddings)
427
+ print(similarities)
428
+ # tensor([[1.0000, 1.0000, 0.0550],
429
+ # [1.0000, 1.0000, 0.0550],
430
+ # [0.0550, 0.0550, 1.0000]])
431
+ ```
432
+
433
+ <!--
434
+ ### Direct Usage (Transformers)
435
+
436
+ <details><summary>Click to see the direct usage in Transformers</summary>
437
+
438
+ </details>
439
+ -->
440
+
441
+ <!--
442
+ ### Downstream Usage (Sentence Transformers)
443
+
444
+ You can finetune this model on your own dataset.
445
+
446
+ <details><summary>Click to expand</summary>
447
+
448
+ </details>
449
+ -->
450
+
451
+ <!--
452
+ ### Out-of-Scope Use
453
+
454
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
455
+ -->
456
+
457
+ <!--
458
+ ## Bias, Risks and Limitations
459
+
460
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
461
+ -->
462
+
463
+ <!--
464
+ ### Recommendations
465
+
466
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
467
+ -->
468
+
469
+ ## Training Details
470
+
471
+ ### Training Dataset
472
+
473
+ #### Unnamed Dataset
474
+
475
+ * Size: 35,100 training samples
476
+ * Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
477
+ * Approximate statistics based on the first 1000 samples:
478
+ | | sentence_0 | sentence_1 | label |
479
+ |:--------|:-------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:------------------------------------------------|
480
+ | type | string | string | int |
481
+ | details | <ul><li>min: 13 tokens</li><li>mean: 192.87 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 13 tokens</li><li>mean: 192.87 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>0: ~50.10%</li><li>1: ~49.90%</li></ul> |
482
+ * Samples:
483
+ | sentence_0 | sentence_1 | label |
484
+ |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------|
485
+ | <code>1. A method for producing float glass, comprising: feeding air to a first ion transport membrane which produces a stream of pure oxygen and a stream of oxygen-depleted air; feeding the stream of pure oxygen to a glass melting furnace; feeding a mixture of steam and a hydrocarbon fuel to one side of a second ion transport membrane and the stream of oxygen-depleted air to the other side of the second oxygen transport membrane to produce a stream of syngas and a nitrogen-rich stream; feeding the stream of syngas to a third ion transport membrane to produce a stream of pure hydrogen and a stream of hydrogen-depleted syngas; feeding the nitrogen-rich stream the hydrogen-depleted syngas stream to a combustor to produce an oxygen-free stream of nitrogen and carbon dioxide; removing H mixing the stream of pure hydrogen and the purified stream of nitrogen and carbon dioxide; and feeding the mixed stream to the surface of a float glass bath downstream of the glass melting furnace.</code> | <code>1. A method for producing float glass, comprising: feeding air to a first ion transport membrane which produces a stream of pure oxygen and a stream of oxygen-depleted air; feeding the stream of pure oxygen to a glass melting furnace; feeding a mixture of steam and a hydrocarbon fuel to one side of a second ion transport membrane and the stream of oxygen-depleted air to the other side of the second oxygen transport membrane to produce a stream of syngas and a nitrogen-rich stream; feeding the stream of syngas to a third ion transport membrane to produce a stream of pure hydrogen and a stream of hydrogen-depleted syngas; feeding the nitrogen-rich stream the hydrogen-depleted syngas stream to a combustor to produce an oxygen-free stream of nitrogen and carbon dioxide; removing H mixing the stream of pure hydrogen and the purified stream of nitrogen and carbon dioxide; and feeding the mixed stream to the surface of a float glass bath downstream of the glass melting furnace.</code> | <code>1</code> |
486
+ | <code>1. An application device for a cosmetic product comprising: a holding member, an application member having a surface for application of the product, and a heating electric element; wherein the heating electric element is formed of at least one resistor mounted on a printed circuit positioned, at least in part at a distal end of the application member, and in that a surface area of the orthogonal projection of the resistor on a plane defined by the printed circuit is less than or equal to 10 mm</code> | <code>1. An application device for a cosmetic product comprising: a holding member, an application member having a surface for application of the product, and a heating electric element; wherein the heating electric element is formed of at least one resistor mounted on a printed circuit positioned, at least in part at a distal end of the application member, and in that a surface area of the orthogonal projection of the resistor on a plane defined by the printed circuit is less than or equal to 10 mm</code> | <code>0</code> |
487
+ | <code>1. A vehicle communication network comprises: a plurality of vehicle control modules; a network fabric, wherein the network fabric comprises: a network manager operably coupled to the network fabric, wherein the network manager is operable to: wherein the data bridge is operable to:</code> | <code>1. A vehicle communication network comprises: a plurality of vehicle control modules; a network fabric, wherein the network fabric comprises: a network manager operably coupled to the network fabric, wherein the network manager is operable to: wherein the data bridge is operable to:</code> | <code>1</code> |
488
+ * Loss: [<code>SoftmaxLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#softmaxloss)
489
+
490
+ ### Training Hyperparameters
491
+ #### Non-Default Hyperparameters
492
+
493
+ - `per_device_train_batch_size`: 16
494
+ - `per_device_eval_batch_size`: 16
495
+ - `num_train_epochs`: 1
496
+ - `multi_dataset_batch_sampler`: round_robin
497
+
498
+ #### All Hyperparameters
499
+ <details><summary>Click to expand</summary>
500
+
501
+ - `do_predict`: False
502
+ - `eval_strategy`: no
503
+ - `prediction_loss_only`: True
504
+ - `per_device_train_batch_size`: 16
505
+ - `per_device_eval_batch_size`: 16
506
+ - `gradient_accumulation_steps`: 1
507
+ - `eval_accumulation_steps`: None
508
+ - `torch_empty_cache_steps`: None
509
+ - `learning_rate`: 5e-05
510
+ - `weight_decay`: 0.0
511
+ - `adam_beta1`: 0.9
512
+ - `adam_beta2`: 0.999
513
+ - `adam_epsilon`: 1e-08
514
+ - `max_grad_norm`: 1
515
+ - `num_train_epochs`: 1
516
+ - `max_steps`: -1
517
+ - `lr_scheduler_type`: linear
518
+ - `lr_scheduler_kwargs`: None
519
+ - `warmup_ratio`: None
520
+ - `warmup_steps`: 0
521
+ - `log_level`: passive
522
+ - `log_level_replica`: warning
523
+ - `log_on_each_node`: True
524
+ - `logging_nan_inf_filter`: True
525
+ - `enable_jit_checkpoint`: False
526
+ - `save_on_each_node`: False
527
+ - `save_only_model`: False
528
+ - `restore_callback_states_from_checkpoint`: False
529
+ - `use_cpu`: False
530
+ - `seed`: 42
531
+ - `data_seed`: None
532
+ - `bf16`: False
533
+ - `fp16`: False
534
+ - `bf16_full_eval`: False
535
+ - `fp16_full_eval`: False
536
+ - `tf32`: None
537
+ - `local_rank`: -1
538
+ - `ddp_backend`: None
539
+ - `debug`: []
540
+ - `dataloader_drop_last`: False
541
+ - `dataloader_num_workers`: 0
542
+ - `dataloader_prefetch_factor`: None
543
+ - `disable_tqdm`: False
544
+ - `remove_unused_columns`: True
545
+ - `label_names`: None
546
+ - `load_best_model_at_end`: False
547
+ - `ignore_data_skip`: False
548
+ - `fsdp`: []
549
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
550
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
551
+ - `parallelism_config`: None
552
+ - `deepspeed`: None
553
+ - `label_smoothing_factor`: 0.0
554
+ - `optim`: adamw_torch_fused
555
+ - `optim_args`: None
556
+ - `group_by_length`: False
557
+ - `length_column_name`: length
558
+ - `project`: huggingface
559
+ - `trackio_space_id`: trackio
560
+ - `ddp_find_unused_parameters`: None
561
+ - `ddp_bucket_cap_mb`: None
562
+ - `ddp_broadcast_buffers`: False
563
+ - `dataloader_pin_memory`: True
564
+ - `dataloader_persistent_workers`: False
565
+ - `skip_memory_metrics`: True
566
+ - `push_to_hub`: False
567
+ - `resume_from_checkpoint`: None
568
+ - `hub_model_id`: None
569
+ - `hub_strategy`: every_save
570
+ - `hub_private_repo`: None
571
+ - `hub_always_push`: False
572
+ - `hub_revision`: None
573
+ - `gradient_checkpointing`: False
574
+ - `gradient_checkpointing_kwargs`: None
575
+ - `include_for_metrics`: []
576
+ - `eval_do_concat_batches`: True
577
+ - `auto_find_batch_size`: False
578
+ - `full_determinism`: False
579
+ - `ddp_timeout`: 1800
580
+ - `torch_compile`: False
581
+ - `torch_compile_backend`: None
582
+ - `torch_compile_mode`: None
583
+ - `include_num_input_tokens_seen`: no
584
+ - `neftune_noise_alpha`: None
585
+ - `optim_target_modules`: None
586
+ - `batch_eval_metrics`: False
587
+ - `eval_on_start`: False
588
+ - `use_liger_kernel`: False
589
+ - `liger_kernel_config`: None
590
+ - `eval_use_gather_object`: False
591
+ - `average_tokens_across_devices`: True
592
+ - `use_cache`: False
593
+ - `prompts`: None
594
+ - `batch_sampler`: batch_sampler
595
+ - `multi_dataset_batch_sampler`: round_robin
596
+ - `router_mapping`: {}
597
+ - `learning_rate_mapping`: {}
598
+
599
+ </details>
600
+
601
+ ### Training Logs
602
+ | Epoch | Step | Training Loss |
603
+ |:------:|:----:|:-------------:|
604
+ | 0.2279 | 500 | 0.5229 |
605
+ | 0.4558 | 1000 | 0.4447 |
606
+ | 0.6837 | 1500 | 0.4322 |
607
+ | 0.9116 | 2000 | 0.4234 |
608
+
609
+
610
+ ### Framework Versions
611
+ - Python: 3.10.12
612
+ - Sentence Transformers: 5.2.2
613
+ - Transformers: 5.1.0
614
+ - PyTorch: 2.10.0+cu128
615
+ - Accelerate: 1.12.0
616
+ - Datasets: 4.5.0
617
+ - Tokenizers: 0.22.2
618
+
619
+ ## Citation
620
+
621
+ ### BibTeX
622
+
623
+ #### Sentence Transformers and SoftmaxLoss
624
+ ```bibtex
625
+ @inproceedings{reimers-2019-sentence-bert,
626
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
627
+ author = "Reimers, Nils and Gurevych, Iryna",
628
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
629
+ month = "11",
630
+ year = "2019",
631
+ publisher = "Association for Computational Linguistics",
632
+ url = "https://arxiv.org/abs/1908.10084",
633
+ }
634
+ ```
635
+
636
+ <!--
637
+ ## Glossary
638
+
639
+ *Clearly define terms in order to be accessible across audiences.*
640
+ -->
641
+
642
+ <!--
643
+ ## Model Card Authors
644
+
645
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
646
+ -->
647
+
648
+ <!--
649
+ ## Model Card Contact
650
+
651
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
652
+ -->
assignment3/Models/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MPNetModel"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "dtype": "float32",
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
+ "tie_word_embeddings": true,
22
+ "transformers_version": "5.1.0",
23
+ "vocab_size": 30527
24
+ }
assignment3/Models/config_sentence_transformers.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "5.2.2",
4
+ "transformers": "5.1.0",
5
+ "pytorch": "2.10.0+cu128"
6
+ },
7
+ "model_type": "SentenceTransformer",
8
+ "prompts": {
9
+ "query": "",
10
+ "document": ""
11
+ },
12
+ "default_prompt_name": null,
13
+ "similarity_fn_name": "cosine"
14
+ }
assignment3/Models/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c19ae21bff7e56dd981c4637d95c73a22a1ad76c3e22fee6a00d9f03ed58ce63
3
+ size 437967648
assignment3/Models/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
+ ]
assignment3/Models/sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 512,
3
+ "do_lower_case": false
4
+ }
assignment3/Models/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
assignment3/Models/tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "do_lower_case": true,
6
+ "eos_token": "</s>",
7
+ "is_local": false,
8
+ "mask_token": "<mask>",
9
+ "model_max_length": 512,
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "MPNetTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }