JTh34 commited on
Commit
a782339
·
verified ·
1 Parent(s): f05280c

Add new SentenceTransformer model

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 1024,
3
+ "pooling_mode_cls_token": true,
4
+ "pooling_mode_mean_tokens": false,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
README.md ADDED
@@ -0,0 +1,894 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - sentence-transformers
4
+ - sentence-similarity
5
+ - feature-extraction
6
+ - generated_from_trainer
7
+ - dataset_size:700
8
+ - loss:MatryoshkaLoss
9
+ - loss:MultipleNegativesRankingLoss
10
+ base_model: Snowflake/snowflake-arctic-embed-l
11
+ widget:
12
+ - source_sentence: How can I ensure that my puppy's emotional and psychological needs
13
+ are being met during training to promote better social skills and emotional stability?
14
+ sentences:
15
+ - Look for wiggling body language, happy faces, and play bows from both dogs. Bouncy
16
+ exaggerated rocking-horse type movements are a sign the dogs are having fun. Determine
17
+ whether your dog wants to run back and play with another dog by giving a consent
18
+ test. Separate the dogs, remove your dog some distance away, then observe whether
19
+ your dog wants to run back and play with the other dog or not. Dogs should be
20
+ self-imposing breaks from play to rest or get a small drink. Breaks may include
21
+ sniffing. If one dog wants a break the other dog shows respect by not persisting
22
+ in perpetual play inducements. If your dog comes and lies down near you, take
23
+ the lead, and protect your dog from further interaction until your dog desires
24
+ another round of play. Sniffing may be in order. Puppies and adult dogs must be
25
+ monitored very carefully as should small dogs vs. large dogs. Not all adult dogs
26
+ like puppies. Large adult dogs should change levels, that is voluntarily self-
27
+ handicap, and let the puppy or smaller dog “win” regularly during role reversals.
28
+ These behaviors balance inequalities in size, strength, and health. If role-reversals
29
+ or self-handicapping are not occurring, do not allow your puppy or small dog continued
30
+ interaction with an adult or much larger dog who may show aggression or cause
31
+ physical or emotional injury. One dog may be either the victim or the bully in
32
+ different contexts. Roles may also change when playing with different play partners.
33
+ Dogs should take turns happily chasing each other where neither dog is a bully
34
+ or a target, so play goes back and forth. With puppies, adult dogs should be willing
35
+ to let the puppy win now and again and should always back off if the puppy squeals.
36
+ - 'The priorities, best practices and the exclusions define what force-free training
37
+ is and in addition what it is not. Force-free training is categorically and qualitatively
38
+ different and unique from traditional or so-called “balance training” by virtue
39
+ of the operational definition of what we do and what we do not do as described
40
+ below.
41
+
42
+
43
+ No shock No prong No choke No pain No fear No dominance or intimidation No compulsion
44
+ methods No physical force No hitting with any object, including rolled up towels
45
+ No throwing items No swatting with a newspaper No shaking cans of coins or rocks
46
+ in our dogs’ sensitive ears No spraying water in the face or body No yelling
47
+
48
+
49
+ Nurturing biological health and psychological well-being enhances emotional stability,
50
+ social skills, and cognitive abilities by meeting our dogs’ real needs. The Hierarchy
51
+ of Dog Needs describes the emotional and behavioral modification methods that force-free
52
+ behavior modification consultants and trainers endorse. Effectively using these
53
+ techniques serves to increase, decrease, and redirect behavior, and also to change
54
+ emotional responses. We set the stage for optimal well-being by using force-free
55
+ training, and eliminating the potentiality for fear, stress, and aggression.'
56
+ - 'Many properties of commercially prepared dog food are not sufficiently regulated.
57
+ We suggest that you
58
+
59
+
60
+ Read the ingredients on labels and choose a food with a specifically named protein
61
+ source as the first ingredient. Avoid the vague term “meat,” by-products, corn
62
+ syrup, and sugar. Meat meal is generally rendered meat made of by-products and
63
+ that is why you will not see meat meals in human foods. Avoid meat meals when
64
+ there are higher quality alternatives. Avoid artificial flavors, colors, and preservatives,
65
+ especially BHA, BHT, and ethoxyquin that may be linked to carcinogens. Artificial
66
+
67
+
68
+ preservatives may be toxic to your dogs: Some artificial preservatives are also
69
+ used as pesticides.
70
+
71
+
72
+ Consider the following questions when choosing a brand of dog food
73
+
74
+
75
+ Sources. Where do the ingredients come from? Recalls. What is the manufacturer’s
76
+ safety record? Marketing and customer service. Is the company transparent about
77
+ its products and responsive to inquiries?'
78
+ - source_sentence: How can I ensure my puppy doesn't have potty accidents when I'm
79
+ not watching her closely?
80
+ sentences:
81
+ - 'attached to you by a leash so she canʼt wander off to potty in the house
82
+
83
+
84
+ or under your direct supervision in an enclosed area. Direct supervision means
85
+ you are looking at her at all times. The minute you turn away, sheʼll have a potty
86
+ accident.
87
+
88
+
89
+ Stick to this plan for a month straight and sheʼll reliably develop the habit
90
+ of going outside and holding it inside. Then continue keeping a close eye on her
91
+ for another couple of months, especially when you take her on outings to other
92
+ peopleʼs homes, before declaring her completely potty trained.
93
+
94
+
95
+ The goal of crate training is that your puppy learns to love resting in her crate.
96
+
97
+
98
+ Crate: Your puppy should sleep in her crate at night and take naps in it during
99
+ the day. To train her to love her crate, you can make it comfortable with a blanket
100
+ and
101
+
102
+
103
+ place treats inside at random times. Then give her toys and pet her when sheʼs
104
+ in it
105
+
106
+
107
+ before you close the door. The ultimate goal of crate training is that she goes
108
+ into
109
+
110
+
111
+ the crate on her own or when you give her a verbal cue, rather than needing to
112
+ be
113
+
114
+
115
+ shoved or coaxed in. And once sheʼs in, she remains calm, relaxed and quiet. (If
116
+
117
+
118
+ you have problems with this, download the crate training handout at
119
+
120
+
121
+ Crate size: The crate should be big enough for the puppy to lie down and turn
122
+ around but not big enough for a separate potty area. You can make the crate
123
+
124
+
125
+ smaller by placing a box in it and, as the puppy grows, enlarge the crate by using
126
+ a
127
+
128
+
129
+ “The goal of crate training is that your puppy learns to love resting in her crate.”'
130
+ - 'Does your puppy love their food? If so, use it to reward them throughout the
131
+ day. Portion out some or all of the food and use it to motivate quick responses
132
+ and self-control. (For more on how to use food to inspire learning, check out
133
+ Part 4 of this book.)
134
+
135
+
136
+ Water is critically important for your puppy’s well-being: it should be left out
137
+ and available at all times. That said, try to monitor their drinking habits while
138
+ house- training them. Establish a drinking station for your puppy and keep their
139
+ dish there, whether it’s empty or full. Give water with meals, after playing,
140
+ chewing, or napping, and as you’re on your way to the potty area.
141
+
142
+
143
+ Restrict water after 7:30 p.m., unless you want to be up all night taking your
144
+ puppy outside. If your puppy needs a drink, either give them a small amount or
145
+ offer a couple of ice cubes.
146
+
147
+
148
+ Although dogs have many fewer taste buds overall (humans have 9,000 to their 1,700),
149
+ your puppy has a ring of taste buds on the tip of their tongue that make water
150
+ taste sweet. Pretty cool.
151
+
152
+
153
+ I don’t think house-training can be summed up any better than with the wonder-
154
+ ful maxim “Whatever goes in must come out.” Your puppy’s biological clock will
155
+ have them eliminating on demand. When their bladder or bowels are pressed, they’ll
156
+ let loose whether they’re outside or on the papers — or the rug, if you’re not
157
+ watching.'
158
+ - 'After a puppy’s peak socialization period, around 16 weeks of age, it’s impos-
159
+ sible to turn back the clock. People, places, sights, and smells that your puppy
160
+ would have conditioned to naturally at an early age will seem suspicious to an
161
+ older puppy. Do you want a dog who can’t warm up to everyday stimulations?
162
+
163
+
164
+ Puppies who are overisolated or stressed during infancy are shown to chew more
165
+ destructively and may wreck your furnishings if they aren’t conditioned to chew
166
+ their toys. The early turmoil created nervous energy that needs to be displaced,
167
+ and because running to the refrigerator is off limits and nail-biting
168
+
169
+
170
+ isn’t an option, your puppy will chew on whatever is available. Provide plenty
171
+ of satisfying options or else you may see your sofa disappear, one cushion at
172
+ a time.
173
+
174
+
175
+ » Shelter: If you find an older puppy at a shelter, ask about their history and
176
+ try to find out why they were left there. Were they found on the side of the street,
177
+ or have they grown up in the system? Has the puppy in question been returned more
178
+ than once? Ask what the reasons were — you may be adopting a dog who couldn’t
179
+ be house-trained, was fearful of kids, or showed aggression when chewing a bone.
180
+ Find out what the staff thinks of the puppy’s personality. » Pet store, puppy
181
+ broker, craigslist, and other sources: Discount shopping isn’t for puppies. Do
182
+ not buy a puppy without meeting and talking to the breeder or rescuers first.
183
+ Though you may read a phrase that makes you feel like you’ll be the winner, there
184
+ are no winners in the online puppy shopping game. Buying a puppy in this manner
185
+ ensures that more puppies will be bred this way, which doesn’t take their interests
186
+ to heart.'
187
+ - source_sentence: What steps should I follow to transition my puppy from walking
188
+ in a low-distraction area to more crowded places while using a Halti?
189
+ sentences:
190
+ - examine teeth and inside the mouth. This will desensitize your dog to people touching
191
+ your dog’s mouth. Make sure your dog has proper dental care. Proper dental care
192
+ is so often overlooked! Massage the sacral joint where the spine meets the tail
193
+ and lift the tail to desensitize your dog to handling. Teach your dog how to give
194
+ consent, how to ask for a break, and how to ask you to stop. Choice and consent
195
+ are the wave of the future in modern cooperative care.
196
+ - 'If your adolescent puppy is still pulling on the leash despite all the basic
197
+ leash walking training I’ve taken you through, you might choose to try a Halti
198
+ leash. I’m a big fan of Haltis, as they make a massive difference with dogs who
199
+ continue to have pulling problems, especially reactive dogs who can pull unexpectedly.
200
+ A Halti is a gentle head harness that controls the dog by the snout and takes
201
+ all the pressure off the throat.
202
+
203
+
204
+ To introduce a Halti, you must first make sure your puppy is comfortable putting
205
+ their nose into the Halti. Do this by simply slipping it on and off and rewarding
206
+ your puppy heavily for this (YES, and a treat). You’ll then need to get your puppy
207
+ comfortable with having the Halti done up, so again, go heavy on the rewards and
208
+ praise. Then you need to master walking your puppy with a Halti on in a low-distraction
209
+ environment (i.e., your garden or somewhere else familiar, without loads of other
210
+ dogs and people). Once your dog is comfortable moving around your garden, you
211
+ can move to outside; get your dog comfortable in your street before moving on
212
+ to high- distraction-level areas, such as parks. A decent structured walk should
213
+ be ten minutes, with your dog nicely walking by your side, followed by five minutes
214
+ where you allow your puppy to sniff and explore a little, before returning to
215
+ a more structured HEEL walk.
216
+
217
+
218
+ TIP: Haltis can be tricky to put on at first, so watch a few online videos or ask
219
+ a friend
220
+
221
+
222
+ to demonstrate theirs just to get a feel for how they work. Waving a Halti around
223
+ and'
224
+ - 'Think of your dog’s veterinarian as being on par with your doctor or your child’s
225
+ pediatrician. Medical knowledge is essential, but a good bedside manner is the
226
+ cherry on top of the sundae. Speak with the receptionists and bring in your pup
227
+ for a cheerful social call before their initial visit. Talk to the doctor like
228
+ they’re a neighbor. Do you feel comfortable sharing all your canine concerns with
229
+ them?
230
+
231
+
232
+ If you’re unsure of which veterinarian to use, ask around. You can narrow your
233
+ search by asking your friends and family whom they use and why.
234
+
235
+
236
+ Puppies can be quite impulsive — they often swallow things that look edible before
237
+ even considering whether they are. So, at your puppy’s first veterinary visit,
238
+ ask the doctor for a recommended method for inducing vomiting. You should also
239
+ find out the poison-control hotline number and always keep it on your phone in
240
+ case of an emergency. Seek out a 24-hour emergency veterinary hospital in your
241
+ area as well. Keep the hospital’s number by or on your phone. Accidents can happen
242
+ during off hours, so have a plan.
243
+
244
+
245
+ Whether your life demands consistent hours away from home or circumstance steps
246
+ in to temporarily rearrange your schedule, knowing a dog walker can make the difference
247
+ between a happy puppy and a stressed-out one. Puppies are like human babies in
248
+ that they have a strong need dependency. Even though an adult dog can hold their
249
+ bladder until you get home or can survive until a late meal, your puppy may well
250
+ eat the walls of your house if you get stuck in traffic. A reliable dog walker
251
+ can be a godsend in times like these.'
252
+ - source_sentence: What breeds of dogs might struggle more with swimming, and how
253
+ can I support them if they are hesitant to enter the water?
254
+ sentences:
255
+ - 'Never throw your dog into the water to “see how it goes”—because your dog can
256
+ easily drown, struggle or thrash and any trust you may have established will be
257
+ broken. The safest, least stressful, and most effective way to teach a dog to
258
+ swim is to use a properly-fitted life jacket. A life jacket often helps new swimmers
259
+ relax enough to paddle with all four legs.
260
+
261
+
262
+ Desensitize your dog to wearing a dog life jacket to keep him afloat and to provide
263
+ peace of mind for you. Your dog’s innate ability to swim or ease in learning to
264
+ swim is, in part, determined by breed and body morphology. Even some retrievers
265
+ need a helping hand to learn and find the confidence to swim for fun and exercise.
266
+ Breeds with short legs and wide chests such as Bulldogs, Boston Terriers, Corgis,
267
+ and Pugs, simply were not bred for swimming. Large, muscled breeds such as the
268
+ bully breeds, require a great deal of energy expenditure in the water due to their
269
+ significant body mass. Sight hounds, such as Salukis, Whippets, Italian Greyhounds
270
+ and Greyhounds, have the disadvantage of both large muscles and little body fat
271
+ to keep them afloat.'
272
+ - 'The key to etiquette training is to set your goals and share them with family
273
+ and friends — and even with strangers who interact with your pup. Think of this
274
+ last training chapter of Part 3 as sending your puppy off to Miss Sarah’s School
275
+ of Dog Etiquette, which is a short-term course with long-term freedoms and rewards.
276
+
277
+
278
+ To develop the all-important canine consciousness, you must do two things:
279
+
280
+
281
+ » Decide what you want when you give a direction. » Follow through — if your expectations
282
+ are unclear, your puppy’s reaction will
283
+
284
+
285
+ When debuting that almost-grown puppy of yours, follow these five essential rules:
286
+
287
+
288
+ 1. Make sure your puppy is familiar and comfortable with the setting before you
289
+ attempt to introduce them to anyone. Don’t greet people your first day out.
290
+
291
+
292
+ 2. Before each introduction, insist that your puppy stand still at your side.
293
+ Gently hold still or bring them back to your side and instruct “Wait.”
294
+
295
+
296
+ 3. Tell admirers “We’re in training.” This statement will help them respect your
297
+ efforts and contain their excitement (hopefully).
298
+
299
+
300
+ 4. Stay more focused on your puppy than on the admirer. Insist that your puppy
301
+ use good manners before you let them approach a new dog or person. 5. Put faith
302
+ in your knowledge. Just because everyone has advice doesn’t mean they’re right.
303
+ “I don’t mind if they jump” doesn’t hold water. You mind if they jump, so don’t
304
+ give in.
305
+
306
+
307
+ Under and back: Helpful commands when you’re out and about
308
+
309
+
310
+ Have you ever marveled at the sight of a dog lying patiently under the table or
311
+ their human’s legs? It’s calming on all fronts because the dog is at peace knowing
312
+ that the person is safe and in charge. Fortunately for you, it couldn’t be easier
313
+ to teach your pup this skill.'
314
+ - 'exposed to an aversive stimulus that it cannot escape or avoid, and which nothing
315
+ it does has any effect on, eventually its avoidance responses will extinguish.
316
+ It will stop reacting to the stimulus, pay no attention, and apparently become
317
+ unaware of it. This is called habituation. In my New York apartment I found the
318
+ street noise unbearable at first, but eventually, like most New Yorkers, I learned
319
+ to sleep through the sirens, yelling, garbage trucks, even car crashes. I became
320
+ habituated. Police horses are sometimes trained by subjecting them to all kinds
321
+ of harmless but alarming events, such as opening umbrellas, flapping papers, being
322
+ tapped all over with rattling tin cans, and so on. The horses become so habituated
323
+ to startling sights and sounds that they remain unflappable no matter what events
324
+ the city streets have to offer.
325
+
326
+
327
+ Method 4 is not useful for getting rid of well-learned, self-rewarding behavior
328
+ patterns. It is good, however, for whining, sulking, or teasing. Even small children
329
+ can learn - and are gratified to discover - that they can stop older children from
330
+ teasing them merely by not reacting in any way, good or bad.
331
+
332
+
333
+ BEHAVIOR Roommate leaves dirty laundry all over the place. Dog in yard barks all
334
+ night.
335
+
336
+
337
+ This behavior is self-reinforcing and seldom extinguishes spontaneously. A certain
338
+ amount of noise is natural and harmless; let it be, they''ll get tired of it.
339
+ See to it that his or her harsh words have no results, either good or bad. Work
340
+ on other strokes, footwork, and so on, and try to let the specific error die down
341
+ from lack of concentrating on it. If the misbehavior is a way of getting attention,
342
+ remove the attention; shirking,'
343
+ - source_sentence: What should I do if I notice signs of an ear infection in my puppy?
344
+ sentences:
345
+ - 'Puppies love interactive games, especially as they mature. Tug is a great game
346
+ for puppies and can be used to teach your puppy to Give on command, as well as
347
+ learning what is and isn’t okay to tug on — your hair or slippers, for example.
348
+ Here’s a quick lesson on playing tug with a young puppy:
349
+
350
+
351
+ » Start with a rope or doggie play pole, which can also be fashioned out of a
352
+
353
+
354
+ » Bounce the toy in front of your puppy or wait until they show interest in
355
+
356
+
357
+ playing with it. Reward their interest by saying “Tug” and providing resistance.
358
+ » Take a smelly food treat in your hand (like liver, hot dog, or jerky-type treat)
359
+
360
+
361
+ » Let your puppy have the toy back right away and continue playing or say “You
362
+
363
+
364
+ Soon your puppy will learn that sharing and releasing toys means more fun and
365
+ interaction, not less.
366
+
367
+
368
+ When picking out self-soothing toys for your puppy (objects they can play with
369
+ alone), keep the analogy of giving a child your smartphone to keep them busy when
370
+ you’re present but not accessible. Self-soothing objects come in many forms: What
371
+ calms your puppy best?
372
+
373
+
374
+ Though you generally can’t go wrong with indestructible plastic bones, some puppies
375
+ find them, well, boring. Rawhide, which is made in America, is a satisfy- ing
376
+ chew, but it’s problematic with some dogs who chew obsessively because they gulp
377
+ it as they go and can choke or get indigestion. Destructible bones also cost money
378
+ to replace — just saying.
379
+
380
+
381
+ Personally, my clients have had the most luck with pressed rawhide, animal-part
382
+ sticks (hooves and bully sticks), and vegetable-matter pulp bones. Test out a
383
+ few kinds yourself to find a bone that satisfies your puppy’s craving and that
384
+ can pass the “systems” test (their digestive system, that is); then buy it in
385
+ bulk.'
386
+ - 'Don’t use cotton swabs or poke into your puppy’s ear canal. You can cause irreparable
387
+ damage by doing so.
388
+
389
+
390
+ » Prevent water from entering the ear. If you’re bathing your pup, put a cotton
391
+ ball in the opening ahead of time and wipe the ears out with a dry cotton ball
392
+ when you’re finished.
393
+
394
+
395
+ Ear infections are quite common. Signs of infection include a red or swollen ear,
396
+ discharge, head shaking, ear itching, or bad odor. If you notice any of these
397
+ symp- toms, get your puppy to their doctor immediately. Left untreated, infections
398
+ can cause fever, depression, irritability, and loss of balance. Your veterinarian
399
+ may prescribe an ointment that you administer at home. Here’s how to use it:
400
+
401
+
402
+ 1. Wait until your dog’s a little sleepy. 2. Bring them to the refrigerator and
403
+ swipe some peanut butter or broth at their eye level.
404
+
405
+
406
+ 3. As they’re licking the refrigerator, gently squeeze into their ear canal the
407
+ amount of ointment specified by your veterinarian.
408
+
409
+
410
+ You don’t have to know much about the nose, though it is helpful for tipping you
411
+ off to the fact that your puppy’s not feeling well. A warm nose can be caused
412
+ by elevated temperature. (See the nearby sidebar, “Taking your puppy’s tempera-
413
+ ture.”) However, weather conditions also can lead to dryness or fluctuation in
414
+ body temperature. If you suspect that your puppy has a fever, touch their other
415
+ body areas without fur (belly, paws, or the inside of their ears) or take their
416
+ tem- perature. Did I mention that you have to do it rectally? What fun!'
417
+ - 'More than 320 breeds are now registered worldwide. These days, being a purebred
418
+ dog is like belonging to an exclusive club: Only dogs with similar looks and inter-
419
+ ests get in. Although most breeds are no longer asked to do the work they were
420
+ developed for, fanciers continually devote themselves to breeding and selling
421
+ puppies that reflect their traditions.
422
+
423
+
424
+ Choosing a specific breed enables you to predict the size, weight, and interest
425
+ of your puppy. Selecting a one-of-a-kind mixed-breed puppy, and predicting or
426
+ discovering the various breeds that combine to create them, allows you to make
427
+ accurate descriptions about their interests and energy level as an adult dog.
428
+
429
+
430
+ When researching a breed, mixed-breed, or designer-mixed-breed, try to meet at
431
+ least three adult dogs of the same breed or mix-breeds. All puppies are cute and
432
+ adorable, but they grow up in the blink of an eye, so make sure you like the look
433
+ and personality of the dog your puppy will become.
434
+
435
+
436
+ Whether you’re considering a purebred, mixed-breed, or designer-mixed-breed, take
437
+ a good, hard look at your lifestyle now and project out five to ten years. How
438
+ might a certain breed’s or mixed breed’s interests and energy level play out in
439
+ your home?'
440
+ pipeline_tag: sentence-similarity
441
+ library_name: sentence-transformers
442
+ metrics:
443
+ - cosine_accuracy@1
444
+ - cosine_accuracy@3
445
+ - cosine_accuracy@5
446
+ - cosine_accuracy@10
447
+ - cosine_precision@1
448
+ - cosine_precision@3
449
+ - cosine_precision@5
450
+ - cosine_precision@10
451
+ - cosine_recall@1
452
+ - cosine_recall@3
453
+ - cosine_recall@5
454
+ - cosine_recall@10
455
+ - cosine_ndcg@10
456
+ - cosine_mrr@10
457
+ - cosine_map@100
458
+ model-index:
459
+ - name: SentenceTransformer based on Snowflake/snowflake-arctic-embed-l
460
+ results:
461
+ - task:
462
+ type: information-retrieval
463
+ name: Information Retrieval
464
+ dataset:
465
+ name: Unknown
466
+ type: unknown
467
+ metrics:
468
+ - type: cosine_accuracy@1
469
+ value: 0.6666666666666666
470
+ name: Cosine Accuracy@1
471
+ - type: cosine_accuracy@3
472
+ value: 0.8533333333333334
473
+ name: Cosine Accuracy@3
474
+ - type: cosine_accuracy@5
475
+ value: 0.9266666666666666
476
+ name: Cosine Accuracy@5
477
+ - type: cosine_accuracy@10
478
+ value: 0.96
479
+ name: Cosine Accuracy@10
480
+ - type: cosine_precision@1
481
+ value: 0.6666666666666666
482
+ name: Cosine Precision@1
483
+ - type: cosine_precision@3
484
+ value: 0.2844444444444444
485
+ name: Cosine Precision@3
486
+ - type: cosine_precision@5
487
+ value: 0.1853333333333333
488
+ name: Cosine Precision@5
489
+ - type: cosine_precision@10
490
+ value: 0.09599999999999996
491
+ name: Cosine Precision@10
492
+ - type: cosine_recall@1
493
+ value: 0.6666666666666666
494
+ name: Cosine Recall@1
495
+ - type: cosine_recall@3
496
+ value: 0.8533333333333334
497
+ name: Cosine Recall@3
498
+ - type: cosine_recall@5
499
+ value: 0.9266666666666666
500
+ name: Cosine Recall@5
501
+ - type: cosine_recall@10
502
+ value: 0.96
503
+ name: Cosine Recall@10
504
+ - type: cosine_ndcg@10
505
+ value: 0.8201527661146794
506
+ name: Cosine Ndcg@10
507
+ - type: cosine_mrr@10
508
+ value: 0.7745740740740741
509
+ name: Cosine Mrr@10
510
+ - type: cosine_map@100
511
+ value: 0.7766199861997735
512
+ name: Cosine Map@100
513
+ ---
514
+
515
+ # SentenceTransformer based on Snowflake/snowflake-arctic-embed-l
516
+
517
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Snowflake/snowflake-arctic-embed-l](https://huggingface.co/Snowflake/snowflake-arctic-embed-l). It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
518
+
519
+ ## Model Details
520
+
521
+ ### Model Description
522
+ - **Model Type:** Sentence Transformer
523
+ - **Base model:** [Snowflake/snowflake-arctic-embed-l](https://huggingface.co/Snowflake/snowflake-arctic-embed-l) <!-- at revision d8fb21ca8d905d2832ee8b96c894d3298964346b -->
524
+ - **Maximum Sequence Length:** 512 tokens
525
+ - **Output Dimensionality:** 1024 dimensions
526
+ - **Similarity Function:** Cosine Similarity
527
+ <!-- - **Training Dataset:** Unknown -->
528
+ <!-- - **Language:** Unknown -->
529
+ <!-- - **License:** Unknown -->
530
+
531
+ ### Model Sources
532
+
533
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
534
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
535
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
536
+
537
+ ### Full Model Architecture
538
+
539
+ ```
540
+ SentenceTransformer(
541
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
542
+ (1): Pooling({'word_embedding_dimension': 1024, '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})
543
+ (2): Normalize()
544
+ )
545
+ ```
546
+
547
+ ## Usage
548
+
549
+ ### Direct Usage (Sentence Transformers)
550
+
551
+ First install the Sentence Transformers library:
552
+
553
+ ```bash
554
+ pip install -U sentence-transformers
555
+ ```
556
+
557
+ Then you can load this model and run inference.
558
+ ```python
559
+ from sentence_transformers import SentenceTransformer
560
+
561
+ # Download from the 🤗 Hub
562
+ model = SentenceTransformer("JTh34/puppy-embed-colab-d23f57a4")
563
+ # Run inference
564
+ sentences = [
565
+ 'What should I do if I notice signs of an ear infection in my puppy?',
566
+ 'Don’t use cotton swabs or poke into your puppy’s ear canal. You can cause irreparable damage by doing so.\n\n» Prevent water from entering the ear. If you’re bathing your pup, put a cotton ball in the opening ahead of time and wipe the ears out with a dry cotton ball when you’re finished.\n\nEar infections are quite common. Signs of infection include a red or swollen ear, discharge, head shaking, ear itching, or bad odor. If you notice any of these symp- toms, get your puppy to their doctor immediately. Left untreated, infections can cause fever, depression, irritability, and loss of balance. Your veterinarian may prescribe an ointment that you administer at home. Here’s how to use it:\n\n1. Wait until your dog’s a little sleepy. 2. Bring them to the refrigerator and swipe some peanut butter or broth at their eye level.\n\n3. As they’re licking the refrigerator, gently squeeze into their ear canal the amount of ointment specified by your veterinarian.\n\nYou don’t have to know much about the nose, though it is helpful for tipping you off to the fact that your puppy’s not feeling well. A warm nose can be caused by elevated temperature. (See the nearby sidebar, “Taking your puppy’s tempera- ture.”) However, weather conditions also can lead to dryness or fluctuation in body temperature. If you suspect that your puppy has a fever, touch their other body areas without fur (belly, paws, or the inside of their ears) or take their tem- perature. Did I mention that you have to do it rectally? What fun!',
567
+ 'More than 320 breeds are now registered worldwide. These days, being a purebred dog is like belonging to an exclusive club: Only dogs with similar looks and inter- ests get in. Although most breeds are no longer asked to do the work they were developed for, fanciers continually devote themselves to breeding and selling puppies that reflect their traditions.\n\nChoosing a specific breed enables you to predict the size, weight, and interest of your puppy. Selecting a one-of-a-kind mixed-breed puppy, and predicting or discovering the various breeds that combine to create them, allows you to make accurate descriptions about their interests and energy level as an adult dog.\n\nWhen researching a breed, mixed-breed, or designer-mixed-breed, try to meet at least three adult dogs of the same breed or mix-breeds. All puppies are cute and adorable, but they grow up in the blink of an eye, so make sure you like the look and personality of the dog your puppy will become.\n\nWhether you’re considering a purebred, mixed-breed, or designer-mixed-breed, take a good, hard look at your lifestyle now and project out five to ten years. How might a certain breed’s or mixed breed’s interests and energy level play out in your home?',
568
+ ]
569
+ embeddings = model.encode(sentences)
570
+ print(embeddings.shape)
571
+ # [3, 1024]
572
+
573
+ # Get the similarity scores for the embeddings
574
+ similarities = model.similarity(embeddings, embeddings)
575
+ print(similarities.shape)
576
+ # [3, 3]
577
+ ```
578
+
579
+ <!--
580
+ ### Direct Usage (Transformers)
581
+
582
+ <details><summary>Click to see the direct usage in Transformers</summary>
583
+
584
+ </details>
585
+ -->
586
+
587
+ <!--
588
+ ### Downstream Usage (Sentence Transformers)
589
+
590
+ You can finetune this model on your own dataset.
591
+
592
+ <details><summary>Click to expand</summary>
593
+
594
+ </details>
595
+ -->
596
+
597
+ <!--
598
+ ### Out-of-Scope Use
599
+
600
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
601
+ -->
602
+
603
+ ## Evaluation
604
+
605
+ ### Metrics
606
+
607
+ #### Information Retrieval
608
+
609
+ * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
610
+
611
+ | Metric | Value |
612
+ |:--------------------|:-----------|
613
+ | cosine_accuracy@1 | 0.6667 |
614
+ | cosine_accuracy@3 | 0.8533 |
615
+ | cosine_accuracy@5 | 0.9267 |
616
+ | cosine_accuracy@10 | 0.96 |
617
+ | cosine_precision@1 | 0.6667 |
618
+ | cosine_precision@3 | 0.2844 |
619
+ | cosine_precision@5 | 0.1853 |
620
+ | cosine_precision@10 | 0.096 |
621
+ | cosine_recall@1 | 0.6667 |
622
+ | cosine_recall@3 | 0.8533 |
623
+ | cosine_recall@5 | 0.9267 |
624
+ | cosine_recall@10 | 0.96 |
625
+ | **cosine_ndcg@10** | **0.8202** |
626
+ | cosine_mrr@10 | 0.7746 |
627
+ | cosine_map@100 | 0.7766 |
628
+
629
+ <!--
630
+ ## Bias, Risks and Limitations
631
+
632
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
633
+ -->
634
+
635
+ <!--
636
+ ### Recommendations
637
+
638
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
639
+ -->
640
+
641
+ ## Training Details
642
+
643
+ ### Training Dataset
644
+
645
+ #### Unnamed Dataset
646
+
647
+ * Size: 700 training samples
648
+ * Columns: <code>sentence_0</code> and <code>sentence_1</code>
649
+ * Approximate statistics based on the first 700 samples:
650
+ | | sentence_0 | sentence_1 |
651
+ |:--------|:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
652
+ | type | string | string |
653
+ | details | <ul><li>min: 15 tokens</li><li>mean: 23.47 tokens</li><li>max: 40 tokens</li></ul> | <ul><li>min: 44 tokens</li><li>mean: 331.62 tokens</li><li>max: 512 tokens</li></ul> |
654
+ * Samples:
655
+ | sentence_0 | sentence_1 |
656
+ |:--------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
657
+ | <code>What techniques can I apply to train my puppy to stay calm and still when I approach, similar to how llamas are trained?</code> | <code>are each a process, defined by results. Negative reinforcers can be used effectively to train behavior, and even though aversive stimuli are involved, the process can be relatively benign. Here (with thanks to llama expert Jim Logan) is a nice use of the negative reinforcer with a semidomestic animal, the llama, kept in the United States as pets and elsewhere as pack animals and for their wool.<br><br>Llamas are timid and shy, like horses. Unless handled a lot when young,<br><br>they can be hard to approach. So, while operant conditioning with a food reinforcer works splendidly with llamas, if a llama is too skittish to come close enough to a person to take the food, here's what modern llama trainers do. They use a clicker as a signal to tell the llama that what it is doing has earned a reinforcer, but the primary or real reinforcer is the removal of a negative reinforcer, an aversive.<br><br>In effect, you say to the llama, "Will you stand still if I approach within<br><br>thirty feet? Yes? Good. I'll click m...</code> |
658
+ | <code>What are the best ways to socialize my hound puppy with household pets to avoid any chasing instincts?</code> | <code>When these puppies are exercised, directed, and included, no group is more happy-go-lucky and accepting of life’s random chaos. But when they don’t get enough playtime or training, they can be hyperactive and destructive.<br><br>Even though the loyal and cheerful dogs in the Sporting group have well-earned reputations as patient family pets, they need both mental and physical stimulation. They can’t cope with long hours of isolation; coupled with a lack of exercise, this isolation fuels anxiety. An unhappy Sporting dog is destructive, hyperactive, and impulsive. This isn’t a good mix — especially for your couch and end table.<br><br>The dogs in the Hound group are a happy lot with a 1-track mind; their fascination with hunting propels them through life and allows them plenty of opportunity for employment. Though you may have no interest in hunting a fox, chasing deer, or treeing a raccoon, your hound puppy probably will.<br><br>Originally teamed in pairs or packs, each hound was prized for their instinc...</code> |
659
+ | <code>What are the top five dog breeds recommended for first-time owners, and what makes them suitable for beginners?</code> | <code>Now don’t get me wrong, I’m not trying to put you off. I love dogs, and I think everyone can benefit from having one in their life. If you’re still unsure which breed is right for you, let me suggest a few that I think make brilliant first dogs.<br><br>Every trainer and dog lover will tell you something different about what breeds are best for you. At the end of the day, it’s your choice. But these are my top five dogs for a first-time owner. I’ve chosen them based on a decade’s experience of working with breeds of all sorts and seeing firsthand some of the common problems among dogs. These five are all typically easygoing, good-natured, smart, and willing to learn. The Rottweiler man in me can observe occasional “over-friendliness” in these breeds, but that’s not a bad thing for beginners, and basically makes them perfect for the novice trainer. If your heart is set on an American bully, but you’ve never had a dog before, think about having one of these dogs first—you can always grow your family l...</code> |
660
+ * Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
661
+ ```json
662
+ {
663
+ "loss": "MultipleNegativesRankingLoss",
664
+ "matryoshka_dims": [
665
+ 1024,
666
+ 512,
667
+ 256,
668
+ 128,
669
+ 64
670
+ ],
671
+ "matryoshka_weights": [
672
+ 1,
673
+ 1,
674
+ 1,
675
+ 1,
676
+ 1
677
+ ],
678
+ "n_dims_per_step": -1
679
+ }
680
+ ```
681
+
682
+ ### Training Hyperparameters
683
+ #### Non-Default Hyperparameters
684
+
685
+ - `eval_strategy`: steps
686
+ - `per_device_train_batch_size`: 16
687
+ - `per_device_eval_batch_size`: 16
688
+ - `num_train_epochs`: 5
689
+ - `multi_dataset_batch_sampler`: round_robin
690
+
691
+ #### All Hyperparameters
692
+ <details><summary>Click to expand</summary>
693
+
694
+ - `overwrite_output_dir`: False
695
+ - `do_predict`: False
696
+ - `eval_strategy`: steps
697
+ - `prediction_loss_only`: True
698
+ - `per_device_train_batch_size`: 16
699
+ - `per_device_eval_batch_size`: 16
700
+ - `per_gpu_train_batch_size`: None
701
+ - `per_gpu_eval_batch_size`: None
702
+ - `gradient_accumulation_steps`: 1
703
+ - `eval_accumulation_steps`: None
704
+ - `torch_empty_cache_steps`: None
705
+ - `learning_rate`: 5e-05
706
+ - `weight_decay`: 0.0
707
+ - `adam_beta1`: 0.9
708
+ - `adam_beta2`: 0.999
709
+ - `adam_epsilon`: 1e-08
710
+ - `max_grad_norm`: 1
711
+ - `num_train_epochs`: 5
712
+ - `max_steps`: -1
713
+ - `lr_scheduler_type`: linear
714
+ - `lr_scheduler_kwargs`: {}
715
+ - `warmup_ratio`: 0.0
716
+ - `warmup_steps`: 0
717
+ - `log_level`: passive
718
+ - `log_level_replica`: warning
719
+ - `log_on_each_node`: True
720
+ - `logging_nan_inf_filter`: True
721
+ - `save_safetensors`: True
722
+ - `save_on_each_node`: False
723
+ - `save_only_model`: False
724
+ - `restore_callback_states_from_checkpoint`: False
725
+ - `no_cuda`: False
726
+ - `use_cpu`: False
727
+ - `use_mps_device`: False
728
+ - `seed`: 42
729
+ - `data_seed`: None
730
+ - `jit_mode_eval`: False
731
+ - `use_ipex`: False
732
+ - `bf16`: False
733
+ - `fp16`: False
734
+ - `fp16_opt_level`: O1
735
+ - `half_precision_backend`: auto
736
+ - `bf16_full_eval`: False
737
+ - `fp16_full_eval`: False
738
+ - `tf32`: None
739
+ - `local_rank`: 0
740
+ - `ddp_backend`: None
741
+ - `tpu_num_cores`: None
742
+ - `tpu_metrics_debug`: False
743
+ - `debug`: []
744
+ - `dataloader_drop_last`: False
745
+ - `dataloader_num_workers`: 0
746
+ - `dataloader_prefetch_factor`: None
747
+ - `past_index`: -1
748
+ - `disable_tqdm`: False
749
+ - `remove_unused_columns`: True
750
+ - `label_names`: None
751
+ - `load_best_model_at_end`: False
752
+ - `ignore_data_skip`: False
753
+ - `fsdp`: []
754
+ - `fsdp_min_num_params`: 0
755
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
756
+ - `fsdp_transformer_layer_cls_to_wrap`: None
757
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
758
+ - `deepspeed`: None
759
+ - `label_smoothing_factor`: 0.0
760
+ - `optim`: adamw_torch
761
+ - `optim_args`: None
762
+ - `adafactor`: False
763
+ - `group_by_length`: False
764
+ - `length_column_name`: length
765
+ - `ddp_find_unused_parameters`: None
766
+ - `ddp_bucket_cap_mb`: None
767
+ - `ddp_broadcast_buffers`: False
768
+ - `dataloader_pin_memory`: True
769
+ - `dataloader_persistent_workers`: False
770
+ - `skip_memory_metrics`: True
771
+ - `use_legacy_prediction_loop`: False
772
+ - `push_to_hub`: False
773
+ - `resume_from_checkpoint`: None
774
+ - `hub_model_id`: None
775
+ - `hub_strategy`: every_save
776
+ - `hub_private_repo`: None
777
+ - `hub_always_push`: False
778
+ - `gradient_checkpointing`: False
779
+ - `gradient_checkpointing_kwargs`: None
780
+ - `include_inputs_for_metrics`: False
781
+ - `include_for_metrics`: []
782
+ - `eval_do_concat_batches`: True
783
+ - `fp16_backend`: auto
784
+ - `push_to_hub_model_id`: None
785
+ - `push_to_hub_organization`: None
786
+ - `mp_parameters`:
787
+ - `auto_find_batch_size`: False
788
+ - `full_determinism`: False
789
+ - `torchdynamo`: None
790
+ - `ray_scope`: last
791
+ - `ddp_timeout`: 1800
792
+ - `torch_compile`: False
793
+ - `torch_compile_backend`: None
794
+ - `torch_compile_mode`: None
795
+ - `include_tokens_per_second`: False
796
+ - `include_num_input_tokens_seen`: False
797
+ - `neftune_noise_alpha`: None
798
+ - `optim_target_modules`: None
799
+ - `batch_eval_metrics`: False
800
+ - `eval_on_start`: False
801
+ - `use_liger_kernel`: False
802
+ - `eval_use_gather_object`: False
803
+ - `average_tokens_across_devices`: False
804
+ - `prompts`: None
805
+ - `batch_sampler`: batch_sampler
806
+ - `multi_dataset_batch_sampler`: round_robin
807
+
808
+ </details>
809
+
810
+ ### Training Logs
811
+ | Epoch | Step | cosine_ndcg@10 |
812
+ |:------:|:----:|:--------------:|
813
+ | 0.5682 | 25 | 0.7986 |
814
+ | 1.0 | 44 | 0.8182 |
815
+ | 1.1364 | 50 | 0.8224 |
816
+ | 1.7045 | 75 | 0.8181 |
817
+ | 2.0 | 88 | 0.8224 |
818
+ | 2.2727 | 100 | 0.8205 |
819
+ | 2.8409 | 125 | 0.8221 |
820
+ | 3.0 | 132 | 0.8235 |
821
+ | 3.4091 | 150 | 0.8205 |
822
+ | 3.9773 | 175 | 0.8178 |
823
+ | 4.0 | 176 | 0.8184 |
824
+ | 4.5455 | 200 | 0.8204 |
825
+ | 5.0 | 220 | 0.8202 |
826
+
827
+
828
+ ### Framework Versions
829
+ - Python: 3.11.12
830
+ - Sentence Transformers: 4.1.0
831
+ - Transformers: 4.52.2
832
+ - PyTorch: 2.6.0+cu124
833
+ - Accelerate: 1.7.0
834
+ - Datasets: 2.14.4
835
+ - Tokenizers: 0.21.1
836
+
837
+ ## Citation
838
+
839
+ ### BibTeX
840
+
841
+ #### Sentence Transformers
842
+ ```bibtex
843
+ @inproceedings{reimers-2019-sentence-bert,
844
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
845
+ author = "Reimers, Nils and Gurevych, Iryna",
846
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
847
+ month = "11",
848
+ year = "2019",
849
+ publisher = "Association for Computational Linguistics",
850
+ url = "https://arxiv.org/abs/1908.10084",
851
+ }
852
+ ```
853
+
854
+ #### MatryoshkaLoss
855
+ ```bibtex
856
+ @misc{kusupati2024matryoshka,
857
+ title={Matryoshka Representation Learning},
858
+ author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
859
+ year={2024},
860
+ eprint={2205.13147},
861
+ archivePrefix={arXiv},
862
+ primaryClass={cs.LG}
863
+ }
864
+ ```
865
+
866
+ #### MultipleNegativesRankingLoss
867
+ ```bibtex
868
+ @misc{henderson2017efficient,
869
+ title={Efficient Natural Language Response Suggestion for Smart Reply},
870
+ author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
871
+ year={2017},
872
+ eprint={1705.00652},
873
+ archivePrefix={arXiv},
874
+ primaryClass={cs.CL}
875
+ }
876
+ ```
877
+
878
+ <!--
879
+ ## Glossary
880
+
881
+ *Clearly define terms in order to be accessible across audiences.*
882
+ -->
883
+
884
+ <!--
885
+ ## Model Card Authors
886
+
887
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
888
+ -->
889
+
890
+ <!--
891
+ ## Model Card Contact
892
+
893
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
894
+ -->
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertModel"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 1024,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4096,
12
+ "layer_norm_eps": 1e-12,
13
+ "max_position_embeddings": 512,
14
+ "model_type": "bert",
15
+ "num_attention_heads": 16,
16
+ "num_hidden_layers": 24,
17
+ "pad_token_id": 0,
18
+ "position_embedding_type": "absolute",
19
+ "torch_dtype": "float32",
20
+ "transformers_version": "4.52.2",
21
+ "type_vocab_size": 2,
22
+ "use_cache": true,
23
+ "vocab_size": 30522
24
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "4.1.0",
4
+ "transformers": "4.52.2",
5
+ "pytorch": "2.6.0+cu124"
6
+ },
7
+ "prompts": {
8
+ "query": "Represent this sentence for searching relevant passages: "
9
+ },
10
+ "default_prompt_name": null,
11
+ "similarity_fn_name": "cosine"
12
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5509e8bc3c6bd6e08e092783dd0c4b28629f68327cec88110a57c41ccf24593
3
+ size 1336413848
modules.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ },
14
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_Normalize",
18
+ "type": "sentence_transformers.models.Normalize"
19
+ }
20
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 512,
3
+ "do_lower_case": 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 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "max_length": 512,
50
+ "model_max_length": 512,
51
+ "pad_to_multiple_of": null,
52
+ "pad_token": "[PAD]",
53
+ "pad_token_type_id": 0,
54
+ "padding_side": "right",
55
+ "sep_token": "[SEP]",
56
+ "stride": 0,
57
+ "strip_accents": null,
58
+ "tokenize_chinese_chars": true,
59
+ "tokenizer_class": "BertTokenizer",
60
+ "truncation_side": "right",
61
+ "truncation_strategy": "longest_first",
62
+ "unk_token": "[UNK]"
63
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff