Add new SentenceTransformer model.
Browse files- 1_Pooling/config.json +10 -0
- README.md +553 -0
- config.json +32 -0
- config_sentence_transformers.json +10 -0
- model.safetensors +3 -0
- modules.json +20 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- vocab.txt +0 -0
1_Pooling/config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 768,
|
3 |
+
"pooling_mode_cls_token": true,
|
4 |
+
"pooling_mode_mean_tokens": false,
|
5 |
+
"pooling_mode_max_tokens": false,
|
6 |
+
"pooling_mode_mean_sqrt_len_tokens": false,
|
7 |
+
"pooling_mode_weightedmean_tokens": false,
|
8 |
+
"pooling_mode_lasttoken": false,
|
9 |
+
"include_prompt": true
|
10 |
+
}
|
README.md
ADDED
@@ -0,0 +1,553 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: avsolatorio/GIST-Embedding-v0
|
3 |
+
datasets: []
|
4 |
+
language: []
|
5 |
+
library_name: sentence-transformers
|
6 |
+
pipeline_tag: sentence-similarity
|
7 |
+
tags:
|
8 |
+
- sentence-transformers
|
9 |
+
- sentence-similarity
|
10 |
+
- feature-extraction
|
11 |
+
- generated_from_trainer
|
12 |
+
- dataset_size:5864
|
13 |
+
- loss:ContrastiveTensionLoss
|
14 |
+
widget:
|
15 |
+
- source_sentence: pyrex blue cup rectangular plastic cover pc pack original genuine
|
16 |
+
pyrex made in the usa genuine pyrex replacement lid nonporous surface does not
|
17 |
+
absorb food odors flavors or stains refrigerator microwave and toprack dishwasher
|
18 |
+
safe will not fit anchor hocking products included pyrex pc blue cup rectangle
|
19 |
+
plastic lids lids only containers not included
|
20 |
+
sentences:
|
21 |
+
- 'kpywzer vintage leather sling bag bags for men women backpack shoulder messenger
|
22 |
+
crossbody outdoor travel hiking camping tactical chest pack daypack brown '
|
23 |
+
- dove beauty bar original moisturizing bar made with moisturizing cream gentle
|
24 |
+
for soft skin count oz each lock in moisture dove original beauty bar is the
|
25 |
+
classic white bar cleanser you trust to nourish and pamper skin and give you softer
|
26 |
+
smoother more radiantlooking skin effective cleanser gently wash away dirt and
|
27 |
+
germs for use every day on body face and hands this dove beauty bar creates luxurious
|
28 |
+
lather and wont dry your skin like ordinary bar soaps no dermatologist recommended
|
29 |
+
formulated with moisturizing cream dove moisturizing beauty bar and gentle skin
|
30 |
+
cleanser leaves skin instantly soft and smooth with lasting nourishment versatile
|
31 |
+
cleanser the unique formulation for effective skin care can be enjoyed by the
|
32 |
+
entire family as this allinone cleanser nourishes your face body and hands for
|
33 |
+
beautiful skin thoughtfully made this beauty bar is certified crueltyfree by peta
|
34 |
+
and sulfate free cleansers so you can feel good about switching from ordinary
|
35 |
+
bar soap to dove beauty bar care with your cleanser our mission is to help the
|
36 |
+
next generation of women develop a positive relationship with the way they look
|
37 |
+
helping them raise their selfesteem
|
38 |
+
- professional stainless steel pots and pans setply piece induction cookware setinduction
|
39 |
+
oven broiler safe f pots and pans silver stainless steel professional cookware
|
40 |
+
set geanbioso ply stainless steel pots and pans set combines the epitome in rapid
|
41 |
+
heating heat retention and cooking stability each piece features cast stainless
|
42 |
+
steel handles durable rivets measurement markings easytopour edges and allcooktop
|
43 |
+
compatibility superior qualitypots and pans are crafted from heavyduty ply clad
|
44 |
+
stainless steelthe outer layer is magneticconducting stainless steel the middle
|
45 |
+
is layer aluminum alloycore for even heat transfer throughout the panthe pot
|
46 |
+
is formed in one piece riveted links safe and solid healthy and environmentally
|
47 |
+
friendly physically nonstick and the service life of up to years or more suitable
|
48 |
+
for all cooktopsgeanbioso ply stainless steel cookware set is suitable for all
|
49 |
+
cooktops and is compatible with oven electric gas ceramic halogen and induction
|
50 |
+
cooktops it is convenient to put the pans in the dishwasheroven safe up to polished
|
51 |
+
technique easytoclean cookware setthis stainless steel pans and pots set interior
|
52 |
+
surface used mirror polished technique it make stainless steel cookware sets effectively
|
53 |
+
avoid deformation warping and rust easy to wash and quick cleanup this kitchen
|
54 |
+
set not only have long use life also make housework much more easier and decorate
|
55 |
+
your kitchen looks shining and high class this fabulous set consists of basics
|
56 |
+
and more the quart covered stockpot with lid takes care of everything from oatmeal
|
57 |
+
to bechamel sauce also included are and inch open skillets that turn out perfect
|
58 |
+
grilled cheese hamburgers and crepesand an quart covered stockpot for stews and
|
59 |
+
soups dishwashersafe this set has no coatings to flake off or plastic to melt
|
60 |
+
and will surely be family businessmotivated by our year familyhistory in kitchen
|
61 |
+
supplywe setout to multigenerational familyowned manufacturers in the usand western
|
62 |
+
europe to buildsuperior culinary toolsour aim is to enhance the experience of
|
63 |
+
your culinary creation and let them become your best kitchen companion
|
64 |
+
- source_sentence: logitech g lightspeed wireless gaming headset with suspension headband
|
65 |
+
lightsync rgb blue voce mic technology and prog audio drivers black total freedom
|
66 |
+
with up to meter wireless range and lightspeed wireless audio transmission keep
|
67 |
+
playing for up to hours of battery life play in stereo on playstationr note if
|
68 |
+
the size of the earbud tips does not match the size of your ear canals or the
|
69 |
+
headset is not worn properly in your ears you may not obtain the correct sound
|
70 |
+
qualities or call performance change the earbud tips to ones that fit more snugly
|
71 |
+
in your earspecific uses for product gamingpersonalstreaming personalize your
|
72 |
+
headset lighting across the full spectrum m colors play in colors with frontfacing
|
73 |
+
dualzone lightsync rgb lighting and choose from preset animations or create your
|
74 |
+
own with g hub software colorful reversible suspension headbands are designed
|
75 |
+
for comfort during long play sessions advanced mic filters that make your voice
|
76 |
+
sound richer cleaner and more professional customize with g hub and find your
|
77 |
+
sound hear every audio cue with breathtaking clarity and get immerse in your game
|
78 |
+
prog drivers are designed to significantly reduce distortion and reproduce precise
|
79 |
+
consistent rich sound quality soft duallayer memory foam that conforms to your
|
80 |
+
head and reduces stress points for longlasting comfort console compatible playstation playstation nintendo
|
81 |
+
switch in dock stereo sound only via usb wireless dongle frequency response hz khz
|
82 |
+
sentences:
|
83 |
+
- 'levis kids pajamas '
|
84 |
+
- bright dream placemats washable easy to clean pvc placemat for kitchen table heatresistand
|
85 |
+
woven vinyl hard table mats x inches set of blue placemats pvc and polyesterx
|
86 |
+
inch xcm dont put tomato juice on the placemats its hard to clean uptemperature
|
87 |
+
should not exceed washable and easy to cleanhand wash in warm soapy water and
|
88 |
+
wipe dryif there is stains stuch in the placematuse a brush and soapy water to
|
89 |
+
clean it no machine wash ecofriendly kitchen accessorieswashablenonfadingnonstainwipe
|
90 |
+
clean protect your table from scratches and stains liquid can go through placemats
|
91 |
+
clean it when finishedperfect additon to your dinner tablebeautiful stylish placemats
|
92 |
+
to addmore fun to your kitchen table
|
93 |
+
- outdoor portable volleyball net system adjustable height poles with soft volleyball
|
94 |
+
ball pump hammer boundary line and carry bag for backyard beach lawn for this
|
95 |
+
volleyball net set easy conversion for the height design for men height for
|
96 |
+
coplay height and for women height standard volleyball net sturdy nylon
|
97 |
+
net with strengthen polyester ropes knit together this net could durable inch
|
98 |
+
piece steel poles with black powdercoating for the total height is official instant
|
99 |
+
set up designed for easy use the makes each assembly step very simple set
|
100 |
+
up this set just in minutes volleyball set for backyardlawnbeach this set includes
|
101 |
+
standard volleyball net steel poles official size and weight volleyball balls
|
102 |
+
and inflation pump with needle boundary line and a carry bag patent pending
|
103 |
+
- source_sentence: king queen apron set wedding engagement gifts for couples funny
|
104 |
+
kitchen gifts for couples husband wife boyfriend girlfriend him her bridal shower
|
105 |
+
gifts unique valentines day gifts ideas perfect gift for couples searching for
|
106 |
+
a couples gift that is guaranteed to put glowing smiles on the faces of that special
|
107 |
+
pair look no further whats better than give the couple a great matching apron
|
108 |
+
of king queen to help them spending the happy cooking time together beautiful
|
109 |
+
gift for couples parents friends fantastic gift idea for fathers day mothers day
|
110 |
+
birthday valentines day anniversaries weddings or christmas superior quality practical couples
|
111 |
+
aprons are made of denselywoven polyester soft breathable fabric to be used and
|
112 |
+
enjoyed for years to come designed with adjustable neck waist straps comfortably
|
113 |
+
fit all body shapes sizes these aprons dont just look cute they add extra fun
|
114 |
+
to your daily routine quality time with your partner just got way better premium
|
115 |
+
quality design and printing carefully crafted for those who appreciate distinctive
|
116 |
+
elegance and quality our peel proof graphics are machine washable our aprons are
|
117 |
+
built to last and waterproof and deformable these matching aprons make a perfect
|
118 |
+
idea for valentines day gifts christmas gifts thanksgiving gifts birthday gifts
|
119 |
+
couple gifts engagement wedding anniversary gifts or housewarming gifts gifts
|
120 |
+
for couples who have everything king and queen apron gift set is made of denselywoven
|
121 |
+
polyester fabrics do waterproof and stainproof it can be worn while doing housework
|
122 |
+
gardening painting and baking our king and queen matching aprons come packaged
|
123 |
+
in a beautiful box ready to be gifted want to be the hit of the party add to cart
|
124 |
+
hasslefree guarantee never worry about not having a suitable choice for engagement
|
125 |
+
wedding anniversary gifts valentines day gifts christmas gifts housewarming gifts king queen
|
126 |
+
aprons gift set is perfect couples gifts your girlfriend boyfriend wife husband
|
127 |
+
partner parents best friend and family members will have a great laugh we take
|
128 |
+
pride in our king queen aprons with pockets and back these up with a lifetime
|
129 |
+
guarantee
|
130 |
+
sentences:
|
131 |
+
- 'maven thread workout headbands for women wide headbands for women sports running
|
132 |
+
headband for exercise gym hairband athletic workouts and yoga thick non slip
|
133 |
+
sweatbands for women pack fashionable functional these headbands for women make
|
134 |
+
the perfect accessory for a killer workout outfit or for adorable casual wear
|
135 |
+
whether youre doing yoga playing sports running hitting the gym or simply lounging
|
136 |
+
at home our headband will keep your hair out of the way and keep you looking fresh
|
137 |
+
nomess sweatband a girls gotta sweat and when she does our thick headband accessories
|
138 |
+
are ready for it this stretchy band features nonslip grip and moisturewicking
|
139 |
+
material so no matter the sport youre playing or the exercise youre doing you
|
140 |
+
can give it your all this hairband will wrap snugly around your head but wont
|
141 |
+
be too tight cute designs our headbands come in a variety of cute modern designs
|
142 |
+
that both girls and women love whether youre looking for an accessory to match
|
143 |
+
your favorite sweats or a headband to spruce up your ponytail were sure to have
|
144 |
+
a look youll love this basics set features darkgray headband lightgray headband navy
|
145 |
+
headband and black headband style for any wear whether youre a nurse trying to
|
146 |
+
keep her hair pulled back at work a runner pounding the pavement a biker hitting
|
147 |
+
the trails or just someone looking to add a boho or athletic touch to your outfit
|
148 |
+
these wraps are for you the cloth will keep thin straight curly or even thick
|
149 |
+
hair back if youre going to get sweaty toss an extra headband in your purse comfort quality
|
150 |
+
combined at maven thread we take pride in creating highquality products that are
|
151 |
+
both stylish and durable our headbands are made of comfortable fabric with of
|
152 |
+
blend of polyester rayon and spandex this fabric gives our bands fourway stretch
|
153 |
+
for onesizefitsall sizing we also offer sweatbands in widths and '
|
154 |
+
- 'disney minnie mouse girls short sleeve tshirt and shorts set for toddlers and
|
155 |
+
big kids '
|
156 |
+
- 'gymboree boys and toddler linen chino shorts '
|
157 |
+
- source_sentence: 'ntbay flannel fuzzy toddler blanket fluffy warm and lightweight
|
158 |
+
reversible stripes design baby plush blanket x inches pink flannel package include x
|
159 |
+
toddler blanket x inches product features our cozy baby blanket is made of flannel
|
160 |
+
fabric which is skin friendly and soft the lightweight toddler blanket is not
|
161 |
+
so thick but it can keep your baby warm and does not feel the pressure of the
|
162 |
+
blanket weight product function the size of the baby blanket is suitable and lightweight
|
163 |
+
which means that you can easily fold it up and pack it in bags while traveling
|
164 |
+
our baby blanket can be a multipurpose for baby stroller covers car seat covers
|
165 |
+
and all seasons applicable easy care machine wash cold gentle cycle only nonchlorine
|
166 |
+
bleach when needed tumble dry low cool iron if needed satisfactory sales service
|
167 |
+
we are so confident in the quality of our product that we offer days return and
|
168 |
+
replacement service we also provide it with a life time free customer service
|
169 |
+
if you find that our products have quality problems just contact us and we will
|
170 |
+
solve the problem for you immediately '
|
171 |
+
sentences:
|
172 |
+
- neutrogena original fragrancefree facial cleansing bar with glycerin pure transparent
|
173 |
+
gentle face wash bar soap free of harsh detergents dyes hardeners oz ounce neutrogena
|
174 |
+
facial cleansing bar in original fragrancefree formula for gentle daily facial
|
175 |
+
cleansing from a dermatologistrecommended skin care brand this pure cleansing
|
176 |
+
bar is designed for all skin types and lathers up to remove excess oil and gently
|
177 |
+
cleanse skin featuring the original neutrogena formula the face soap bar is glycerinrich
|
178 |
+
to attract moisture and contains no harsh detergents dyes or hardeners that can
|
179 |
+
irritate the skin our face cleansing bar is exceptionally cleanrinsing without
|
180 |
+
leaving behind any poreclogging residue for clear healthierlooking skin the pure
|
181 |
+
and gentle formula of this facial soap bar is fragrancefree hypoallergenic and
|
182 |
+
suitable for daily use
|
183 |
+
- 'french toast girls big vneck jumper blue gold plaid '
|
184 |
+
- philips norelco shaver rechargeable cordless electric shaver with popup trimmer
|
185 |
+
x with comfortcut blades you get a clean shave thats comfortable on your skin
|
186 |
+
rounded caps shield selfsharpening blades to gently cut hair just above skin
|
187 |
+
level and help the shaver glide smoothly over your skin d flex heads move independently
|
188 |
+
in directions to automatically adjust to the curves of your face neck and jaw
|
189 |
+
line popup trimmer for mustache and sideburns finish your look with the builtin
|
190 |
+
trimmer its ideal for maintaining your mustache and trimming your sideburns at
|
191 |
+
the touch of a button you can pop the heads open for an easy and thorough clean
|
192 |
+
under the tap up to minutes of cordless runtime thats about shaves or plug
|
193 |
+
it in for instant continuous power
|
194 |
+
- source_sentence: magic the gathering modern horizons bundle gift edition deluxe
|
195 |
+
bundle with collector booster play boosters fullart lands exclusive accessories
|
196 |
+
give the gift of magicthe perfect present for any magic fan this gift bundle is
|
197 |
+
full of exclusive accessories and the coolest cards from modern horizons including
|
198 |
+
a collector booster packed with rare cards shiny foils and altart altframe cards
|
199 |
+
moderns never been more marvelousintroducing a heaping helping of exciting cards
|
200 |
+
for modern one of magics most celebrated formats plus the return of competitive
|
201 |
+
favorites theres something for every fan to love in modern horizons a collector
|
202 |
+
booster full of treasuresboth powerful and flashy the included collector booster
|
203 |
+
is packed with only the coolest cards and is the only place fans may find foiletched
|
204 |
+
cards textured foil cards or serialized cards printed with a unique number boosters
|
205 |
+
for playing building decksplay boosters are the best packs for playing magic
|
206 |
+
with friends and are fun to open with a possibility of multiple rares and at least shining
|
207 |
+
foil card in every pack fullart lands special alternateart cardevery mh bundle
|
208 |
+
gift edition also comes with traditional foil promo card featuring bundleexclusive
|
209 |
+
alternate art and of the included land cards feature stunning fullart foil nonfoil
|
210 |
+
exclusive accessorieseach gift bundle also comes with exclusive accessories including
|
211 |
+
a special die to track your life total as you play and a sturdy box to store everything
|
212 |
+
in bundle gift edition contents collector booster play boosters traditional
|
213 |
+
foil altart card land cards foil nonfoil spindown life counter card storage
|
214 |
+
box and reference cards
|
215 |
+
sentences:
|
216 |
+
- dove men care in bar cleanser for body face and shaving extra fresh body and
|
217 |
+
facial cleanser more moisturizing than bar soap to clean and hydrate skin ounce
|
218 |
+
pack of hydrate your skin unlike other regular bar soap that can dry out skin
|
219 |
+
dove mencare extra fresh body and face bar deeply cleans and hydrates skin leaving
|
220 |
+
skin feeling smooth and comfortable from the dermatologist recommended mens brand
|
221 |
+
this face and body bar is formulated with more moisturizer than ordinary soap
|
222 |
+
bar and washes off easily to leave skin feeling healthy in for bar cleanser
|
223 |
+
for body face and shaving dove mencare extra fresh body and face bar formulation
|
224 |
+
is so hydrating and gentle on skin that you can also use it to wash your face
|
225 |
+
or to shave refreshing clean feel clean and invigorated with this hydrating body
|
226 |
+
cleanser and face bar and enjoy its crisp refreshing scent of mandarin citrus
|
227 |
+
patchouli and rosemary designed for men mens skin care is different men sweat
|
228 |
+
more have thicker skin and lose hydration faster dove mencare is specifically
|
229 |
+
developed for mens skin to protect it against skin dryness pledge for paternity
|
230 |
+
from the dermatologist recommended mens brand were committed to making paid paternity
|
231 |
+
leave the new standard
|
232 |
+
- backdrop stand xft photo video studio adjustable backdrop stand for parties wedding
|
233 |
+
photography advertising display note balloons colorful decorations are not included
|
234 |
+
meaningful family gathering cheerful and memorable birthday party romantic and
|
235 |
+
warm wedding professional photography attractive advertising display and other
|
236 |
+
uses just get ft backdrop stands adjustable stable backdrop stand loading capacity
|
237 |
+
up to lbkg good flexibility with width ftft height ft ft heavy duty spring clamp
|
238 |
+
and backdrop elastic string clip to holds curtains canvas muslin projector screen
|
239 |
+
or seamless paper prevent background slippage photography weight sandbag to stabilize
|
240 |
+
the backdrop support system note this bag comes empty its capacity is about lbub
|
241 |
+
the kit includes pcs crossbar parts pcs tripod bracket pcs spring clamp pcs
|
242 |
+
backdrop elastic string clip pcs sand bag pc carry bag
|
243 |
+
- 'burts bees baby baby girls mittens noscratch mitts organic cotton set of '
|
244 |
+
---
|
245 |
+
|
246 |
+
# SentenceTransformer based on avsolatorio/GIST-Embedding-v0
|
247 |
+
|
248 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [avsolatorio/GIST-Embedding-v0](https://huggingface.co/avsolatorio/GIST-Embedding-v0). 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.
|
249 |
+
|
250 |
+
## Model Details
|
251 |
+
|
252 |
+
### Model Description
|
253 |
+
- **Model Type:** Sentence Transformer
|
254 |
+
- **Base model:** [avsolatorio/GIST-Embedding-v0](https://huggingface.co/avsolatorio/GIST-Embedding-v0) <!-- at revision bf6b2e55e92f510a570ad4d7d2da2ec8cd22590c -->
|
255 |
+
- **Maximum Sequence Length:** 512 tokens
|
256 |
+
- **Output Dimensionality:** 768 tokens
|
257 |
+
- **Similarity Function:** Cosine Similarity
|
258 |
+
<!-- - **Training Dataset:** Unknown -->
|
259 |
+
<!-- - **Language:** Unknown -->
|
260 |
+
<!-- - **License:** Unknown -->
|
261 |
+
|
262 |
+
### Model Sources
|
263 |
+
|
264 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
265 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
266 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
267 |
+
|
268 |
+
### Full Model Architecture
|
269 |
+
|
270 |
+
```
|
271 |
+
SentenceTransformer(
|
272 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel
|
273 |
+
(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})
|
274 |
+
(2): Normalize()
|
275 |
+
)
|
276 |
+
```
|
277 |
+
|
278 |
+
## Usage
|
279 |
+
|
280 |
+
### Direct Usage (Sentence Transformers)
|
281 |
+
|
282 |
+
First install the Sentence Transformers library:
|
283 |
+
|
284 |
+
```bash
|
285 |
+
pip install -U sentence-transformers
|
286 |
+
```
|
287 |
+
|
288 |
+
Then you can load this model and run inference.
|
289 |
+
```python
|
290 |
+
from sentence_transformers import SentenceTransformer
|
291 |
+
|
292 |
+
# Download from the 🤗 Hub
|
293 |
+
model = SentenceTransformer("wjunwei/ecommerce_text_embedding")
|
294 |
+
# Run inference
|
295 |
+
sentences = [
|
296 |
+
'magic the gathering modern horizons bundle gift edition deluxe bundle with collector booster play boosters fullart lands exclusive accessories give the gift of magicthe perfect present for any magic fan this gift bundle is full of exclusive accessories and the coolest cards from modern horizons including a collector booster packed with rare cards shiny foils and altart altframe cards moderns never been more marvelousintroducing a heaping helping of exciting cards for modern one of magics most celebrated formats plus the return of competitive favorites theres something for every fan to love in modern horizons a collector booster full of treasuresboth powerful and flashy the included collector booster is packed with only the coolest cards and is the only place fans may find foiletched cards textured foil cards or serialized cards printed with a unique number boosters for playing building decksplay boosters are the best packs for playing magic with friends and are fun to open with a possibility of multiple rares and at least shining foil card in every pack fullart lands special alternateart cardevery mh bundle gift edition also comes with traditional foil promo card featuring bundleexclusive alternate art and of the included land cards feature stunning fullart foil nonfoil exclusive accessorieseach gift bundle also comes with exclusive accessories including a special die to track your life total as you play and a sturdy box to store everything in bundle gift edition contents collector booster play boosters traditional foil altart card land cards foil nonfoil spindown life counter card storage box and reference cards',
|
297 |
+
'backdrop stand xft photo video studio adjustable backdrop stand for parties wedding photography advertising display note balloons colorful decorations are not included meaningful family gathering cheerful and memorable birthday party romantic and warm wedding professional photography attractive advertising display and other uses just get ft backdrop stands adjustable stable backdrop stand loading capacity up to lbkg good flexibility with width ftft height ft ft heavy duty spring clamp and backdrop elastic string clip to holds curtains canvas muslin projector screen or seamless paper prevent background slippage photography weight sandbag to stabilize the backdrop support system note this bag comes empty its capacity is about lbub the kit includes pcs crossbar parts pcs tripod bracket pcs spring clamp pcs backdrop elastic string clip pcs sand bag pc carry bag',
|
298 |
+
'burts bees baby baby girls mittens noscratch mitts organic cotton set of ',
|
299 |
+
]
|
300 |
+
embeddings = model.encode(sentences)
|
301 |
+
print(embeddings.shape)
|
302 |
+
# [3, 768]
|
303 |
+
|
304 |
+
# Get the similarity scores for the embeddings
|
305 |
+
similarities = model.similarity(embeddings, embeddings)
|
306 |
+
print(similarities.shape)
|
307 |
+
# [3, 3]
|
308 |
+
```
|
309 |
+
|
310 |
+
<!--
|
311 |
+
### Direct Usage (Transformers)
|
312 |
+
|
313 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
314 |
+
|
315 |
+
</details>
|
316 |
+
-->
|
317 |
+
|
318 |
+
<!--
|
319 |
+
### Downstream Usage (Sentence Transformers)
|
320 |
+
|
321 |
+
You can finetune this model on your own dataset.
|
322 |
+
|
323 |
+
<details><summary>Click to expand</summary>
|
324 |
+
|
325 |
+
</details>
|
326 |
+
-->
|
327 |
+
|
328 |
+
<!--
|
329 |
+
### Out-of-Scope Use
|
330 |
+
|
331 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
332 |
+
-->
|
333 |
+
|
334 |
+
<!--
|
335 |
+
## Bias, Risks and Limitations
|
336 |
+
|
337 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
338 |
+
-->
|
339 |
+
|
340 |
+
<!--
|
341 |
+
### Recommendations
|
342 |
+
|
343 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
344 |
+
-->
|
345 |
+
|
346 |
+
## Training Details
|
347 |
+
|
348 |
+
### Training Dataset
|
349 |
+
|
350 |
+
#### Unnamed Dataset
|
351 |
+
|
352 |
+
|
353 |
+
* Size: 5,864 training samples
|
354 |
+
* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
|
355 |
+
* Approximate statistics based on the first 1000 samples:
|
356 |
+
| | sentence_0 | sentence_1 | label |
|
357 |
+
|:--------|:-----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------|
|
358 |
+
| type | string | string | int |
|
359 |
+
| details | <ul><li>min: 5 tokens</li><li>mean: 144.3 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 143.08 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>0: ~87.50%</li><li>1: ~12.50%</li></ul> |
|
360 |
+
* Samples:
|
361 |
+
| sentence_0 | sentence_1 | label |
|
362 |
+
|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------|
|
363 |
+
| <code>philips norelco shaver rechargeable electric shaver with popup trimmer s comfortcut blades get a clean shave thats comfortable on your skin rounded blade caps shield selfsharpening blades to gently cut hair just above skin level and help the shaver glide smoothly over your skin experience a convenient clean shave with heads that flex and float in directions the head adjusts to the curves of your face ensuring smooth contact with your skin without a lot of pressure d flex heads follow your faces contours for a clean shave popup trimmer for mustache and sideburns finish your look with the builtin trimmer ideal for maintaining your mustache and trimming your sideburns onetouch open for easy cleaning experience a convenient clean shave with heads that flex and float in directions the head adjusts to the curves of your face ensuring smooth contact with your skin without a lot of pressure minutes of cordless shaving from an hour charge thats about shaves or plug it in for instant continuous power</code> | <code>philips norelco shaver rechargeable electric shaver with popup trimmer s comfortcut blades get a clean shave thats comfortable on your skin rounded blade caps shield selfsharpening blades to gently cut hair just above skin level and help the shaver glide smoothly over your skin experience a convenient clean shave with heads that flex and float in directions the head adjusts to the curves of your face ensuring smooth contact with your skin without a lot of pressure d flex heads follow your faces contours for a clean shave popup trimmer for mustache and sideburns finish your look with the builtin trimmer ideal for maintaining your mustache and trimming your sideburns onetouch open for easy cleaning experience a convenient clean shave with heads that flex and float in directions the head adjusts to the curves of your face ensuring smooth contact with your skin without a lot of pressure minutes of cordless shaving from an hour charge thats about shaves or plug it in for instant continuous power</code> | <code>1</code> |
|
364 |
+
| <code>speedo girls swimsuit one piece thin straps </code> | <code>lace tulle flower girl long dress for wedding oneck princess dresses long sleeve pageant party gown </code> | <code>0</code> |
|
365 |
+
| <code>pyrex blue cup rectangular plastic cover pc pack original genuine pyrex made in the usa genuine pyrex replacement lid nonporous surface does not absorb food odors flavors or stains refrigerator microwave and toprack dishwasher safe will not fit anchor hocking products included pyrex pc blue cup rectangle plastic lids lids only containers not included</code> | <code>kpywzer vintage leather sling bag bags for men women backpack shoulder messenger crossbody outdoor travel hiking camping tactical chest pack daypack brown </code> | <code>0</code> |
|
366 |
+
* Loss: [<code>ContrastiveTensionLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastivetensionloss)
|
367 |
+
|
368 |
+
### Training Hyperparameters
|
369 |
+
#### Non-Default Hyperparameters
|
370 |
+
|
371 |
+
- `num_train_epochs`: 5
|
372 |
+
- `multi_dataset_batch_sampler`: round_robin
|
373 |
+
|
374 |
+
#### All Hyperparameters
|
375 |
+
<details><summary>Click to expand</summary>
|
376 |
+
|
377 |
+
- `overwrite_output_dir`: False
|
378 |
+
- `do_predict`: False
|
379 |
+
- `eval_strategy`: no
|
380 |
+
- `prediction_loss_only`: True
|
381 |
+
- `per_device_train_batch_size`: 8
|
382 |
+
- `per_device_eval_batch_size`: 8
|
383 |
+
- `per_gpu_train_batch_size`: None
|
384 |
+
- `per_gpu_eval_batch_size`: None
|
385 |
+
- `gradient_accumulation_steps`: 1
|
386 |
+
- `eval_accumulation_steps`: None
|
387 |
+
- `learning_rate`: 5e-05
|
388 |
+
- `weight_decay`: 0.0
|
389 |
+
- `adam_beta1`: 0.9
|
390 |
+
- `adam_beta2`: 0.999
|
391 |
+
- `adam_epsilon`: 1e-08
|
392 |
+
- `max_grad_norm`: 1
|
393 |
+
- `num_train_epochs`: 5
|
394 |
+
- `max_steps`: -1
|
395 |
+
- `lr_scheduler_type`: linear
|
396 |
+
- `lr_scheduler_kwargs`: {}
|
397 |
+
- `warmup_ratio`: 0.0
|
398 |
+
- `warmup_steps`: 0
|
399 |
+
- `log_level`: passive
|
400 |
+
- `log_level_replica`: warning
|
401 |
+
- `log_on_each_node`: True
|
402 |
+
- `logging_nan_inf_filter`: True
|
403 |
+
- `save_safetensors`: True
|
404 |
+
- `save_on_each_node`: False
|
405 |
+
- `save_only_model`: False
|
406 |
+
- `restore_callback_states_from_checkpoint`: False
|
407 |
+
- `no_cuda`: False
|
408 |
+
- `use_cpu`: False
|
409 |
+
- `use_mps_device`: False
|
410 |
+
- `seed`: 42
|
411 |
+
- `data_seed`: None
|
412 |
+
- `jit_mode_eval`: False
|
413 |
+
- `use_ipex`: False
|
414 |
+
- `bf16`: False
|
415 |
+
- `fp16`: False
|
416 |
+
- `fp16_opt_level`: O1
|
417 |
+
- `half_precision_backend`: auto
|
418 |
+
- `bf16_full_eval`: False
|
419 |
+
- `fp16_full_eval`: False
|
420 |
+
- `tf32`: None
|
421 |
+
- `local_rank`: 0
|
422 |
+
- `ddp_backend`: None
|
423 |
+
- `tpu_num_cores`: None
|
424 |
+
- `tpu_metrics_debug`: False
|
425 |
+
- `debug`: []
|
426 |
+
- `dataloader_drop_last`: False
|
427 |
+
- `dataloader_num_workers`: 0
|
428 |
+
- `dataloader_prefetch_factor`: None
|
429 |
+
- `past_index`: -1
|
430 |
+
- `disable_tqdm`: False
|
431 |
+
- `remove_unused_columns`: True
|
432 |
+
- `label_names`: None
|
433 |
+
- `load_best_model_at_end`: False
|
434 |
+
- `ignore_data_skip`: False
|
435 |
+
- `fsdp`: []
|
436 |
+
- `fsdp_min_num_params`: 0
|
437 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
438 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
439 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
440 |
+
- `deepspeed`: None
|
441 |
+
- `label_smoothing_factor`: 0.0
|
442 |
+
- `optim`: adamw_torch
|
443 |
+
- `optim_args`: None
|
444 |
+
- `adafactor`: False
|
445 |
+
- `group_by_length`: False
|
446 |
+
- `length_column_name`: length
|
447 |
+
- `ddp_find_unused_parameters`: None
|
448 |
+
- `ddp_bucket_cap_mb`: None
|
449 |
+
- `ddp_broadcast_buffers`: False
|
450 |
+
- `dataloader_pin_memory`: True
|
451 |
+
- `dataloader_persistent_workers`: False
|
452 |
+
- `skip_memory_metrics`: True
|
453 |
+
- `use_legacy_prediction_loop`: False
|
454 |
+
- `push_to_hub`: False
|
455 |
+
- `resume_from_checkpoint`: None
|
456 |
+
- `hub_model_id`: None
|
457 |
+
- `hub_strategy`: every_save
|
458 |
+
- `hub_private_repo`: False
|
459 |
+
- `hub_always_push`: False
|
460 |
+
- `gradient_checkpointing`: False
|
461 |
+
- `gradient_checkpointing_kwargs`: None
|
462 |
+
- `include_inputs_for_metrics`: False
|
463 |
+
- `eval_do_concat_batches`: True
|
464 |
+
- `fp16_backend`: auto
|
465 |
+
- `push_to_hub_model_id`: None
|
466 |
+
- `push_to_hub_organization`: None
|
467 |
+
- `mp_parameters`:
|
468 |
+
- `auto_find_batch_size`: False
|
469 |
+
- `full_determinism`: False
|
470 |
+
- `torchdynamo`: None
|
471 |
+
- `ray_scope`: last
|
472 |
+
- `ddp_timeout`: 1800
|
473 |
+
- `torch_compile`: False
|
474 |
+
- `torch_compile_backend`: None
|
475 |
+
- `torch_compile_mode`: None
|
476 |
+
- `dispatch_batches`: None
|
477 |
+
- `split_batches`: None
|
478 |
+
- `include_tokens_per_second`: False
|
479 |
+
- `include_num_input_tokens_seen`: False
|
480 |
+
- `neftune_noise_alpha`: None
|
481 |
+
- `optim_target_modules`: None
|
482 |
+
- `batch_eval_metrics`: False
|
483 |
+
- `batch_sampler`: batch_sampler
|
484 |
+
- `multi_dataset_batch_sampler`: round_robin
|
485 |
+
|
486 |
+
</details>
|
487 |
+
|
488 |
+
### Training Logs
|
489 |
+
| Epoch | Step | Training Loss |
|
490 |
+
|:------:|:----:|:-------------:|
|
491 |
+
| 0.6821 | 500 | 7.4403 |
|
492 |
+
| 1.3643 | 1000 | 4.8536 |
|
493 |
+
| 2.0464 | 1500 | 3.8646 |
|
494 |
+
| 2.7285 | 2000 | 3.8877 |
|
495 |
+
| 3.4106 | 2500 | 3.8789 |
|
496 |
+
| 4.0928 | 3000 | 3.8052 |
|
497 |
+
| 4.7749 | 3500 | 3.8385 |
|
498 |
+
|
499 |
+
|
500 |
+
### Framework Versions
|
501 |
+
- Python: 3.10.12
|
502 |
+
- Sentence Transformers: 3.0.1
|
503 |
+
- Transformers: 4.41.2
|
504 |
+
- PyTorch: 2.3.0+cu121
|
505 |
+
- Accelerate: 0.31.0
|
506 |
+
- Datasets: 2.20.0
|
507 |
+
- Tokenizers: 0.19.1
|
508 |
+
|
509 |
+
## Citation
|
510 |
+
|
511 |
+
### BibTeX
|
512 |
+
|
513 |
+
#### Sentence Transformers
|
514 |
+
```bibtex
|
515 |
+
@inproceedings{reimers-2019-sentence-bert,
|
516 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
517 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
518 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
519 |
+
month = "11",
|
520 |
+
year = "2019",
|
521 |
+
publisher = "Association for Computational Linguistics",
|
522 |
+
url = "https://arxiv.org/abs/1908.10084",
|
523 |
+
}
|
524 |
+
```
|
525 |
+
|
526 |
+
#### ContrastiveTensionLoss
|
527 |
+
```bibtex
|
528 |
+
@inproceedings{carlsson2021semantic,
|
529 |
+
title={Semantic Re-tuning with Contrastive Tension},
|
530 |
+
author={Fredrik Carlsson and Amaru Cuba Gyllensten and Evangelia Gogoulou and Erik Ylip{"a}{"a} Hellqvist and Magnus Sahlgren},
|
531 |
+
booktitle={International Conference on Learning Representations},
|
532 |
+
year={2021},
|
533 |
+
url={https://openreview.net/forum?id=Ov_sMNau-PF}
|
534 |
+
}
|
535 |
+
```
|
536 |
+
|
537 |
+
<!--
|
538 |
+
## Glossary
|
539 |
+
|
540 |
+
*Clearly define terms in order to be accessible across audiences.*
|
541 |
+
-->
|
542 |
+
|
543 |
+
<!--
|
544 |
+
## Model Card Authors
|
545 |
+
|
546 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
547 |
+
-->
|
548 |
+
|
549 |
+
<!--
|
550 |
+
## Model Card Contact
|
551 |
+
|
552 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
553 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "avsolatorio/GIST-Embedding-v0",
|
3 |
+
"architectures": [
|
4 |
+
"BertModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 3072,
|
17 |
+
"label2id": {
|
18 |
+
"LABEL_0": 0
|
19 |
+
},
|
20 |
+
"layer_norm_eps": 1e-12,
|
21 |
+
"max_position_embeddings": 512,
|
22 |
+
"model_type": "bert",
|
23 |
+
"num_attention_heads": 12,
|
24 |
+
"num_hidden_layers": 12,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"position_embedding_type": "absolute",
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.41.2",
|
29 |
+
"type_vocab_size": 2,
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 30522
|
32 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "3.0.1",
|
4 |
+
"transformers": "4.41.2",
|
5 |
+
"pytorch": "2.3.0+cu121"
|
6 |
+
},
|
7 |
+
"prompts": {},
|
8 |
+
"default_prompt_name": null,
|
9 |
+
"similarity_fn_name": null
|
10 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a8e1769362336ab67d958528542b4e985e2302c57e2758d94576226de94cd5d
|
3 |
+
size 437951328
|
modules.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[
|
2 |
+
{
|
3 |
+
"idx": 0,
|
4 |
+
"name": "0",
|
5 |
+
"path": "",
|
6 |
+
"type": "sentence_transformers.models.Transformer"
|
7 |
+
},
|
8 |
+
{
|
9 |
+
"idx": 1,
|
10 |
+
"name": "1",
|
11 |
+
"path": "1_Pooling",
|
12 |
+
"type": "sentence_transformers.models.Pooling"
|
13 |
+
},
|
14 |
+
{
|
15 |
+
"idx": 2,
|
16 |
+
"name": "2",
|
17 |
+
"path": "2_Normalize",
|
18 |
+
"type": "sentence_transformers.models.Normalize"
|
19 |
+
}
|
20 |
+
]
|
sentence_bert_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"max_seq_length": 512,
|
3 |
+
"do_lower_case": true
|
4 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "BertTokenizer",
|
56 |
+
"unk_token": "[UNK]"
|
57 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|