Add new SentenceTransformer model.
Browse files- 1_Pooling/config.json +10 -0
- README.md +508 -0
- config.json +27 -0
- config_sentence_transformers.json +10 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- modules.json +14 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- vocab.json +0 -0
1_Pooling/config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 768,
|
3 |
+
"pooling_mode_cls_token": false,
|
4 |
+
"pooling_mode_mean_tokens": true,
|
5 |
+
"pooling_mode_max_tokens": false,
|
6 |
+
"pooling_mode_mean_sqrt_len_tokens": false,
|
7 |
+
"pooling_mode_weightedmean_tokens": false,
|
8 |
+
"pooling_mode_lasttoken": false,
|
9 |
+
"include_prompt": true
|
10 |
+
}
|
README.md
ADDED
@@ -0,0 +1,508 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- sentence-transformers
|
4 |
+
- sentence-similarity
|
5 |
+
- feature-extraction
|
6 |
+
- generated_from_trainer
|
7 |
+
- dataset_size:4693
|
8 |
+
- loss:MultipleNegativesRankingLoss
|
9 |
+
base_model: FacebookAI/roberta-base
|
10 |
+
widget:
|
11 |
+
- source_sentence: I'm looking for a pair of sleek and comfortable footwear designed
|
12 |
+
for running. They should offer a lightweight feel and have a striking appearance.
|
13 |
+
sentences:
|
14 |
+
- 'Title: Wood Sunglasses for Men and Women Vintage Polarized Lenses Uv Protection
|
15 |
+
Bamboo Wooden Sun Glasses Descripion: [''SUNMER WOOD (Brand) Your love for the
|
16 |
+
outdoors and warm summer days shouldn’t come at the cost of your eyes. While the
|
17 |
+
sun creates the perfect setting for exploring nature, its harmful UVA and UVB
|
18 |
+
rays can cause immense damage to your eyes and skin, causing not just visual deterioration
|
19 |
+
but wrinkles too. At Sunmer Wood, we are a team of designers specializing in making
|
20 |
+
premium sunglasses that give your eyes protection and your outfit a stylish upgrade.
|
21 |
+
We use organic wood and heavy-duty materials to ensure unmatched durability and
|
22 |
+
world-class comfort.'']'
|
23 |
+
- 'Title: Nike Men''s Epic React Flyknit Running Shoes Descripion: [''The Nike Epic
|
24 |
+
React Flyknit provides a smooth, lightweight performance and a bold look.'']'
|
25 |
+
- 'Title: Metal D Rings Heavy Duty 1 Inch D Shape Rings for Sewing, Keychains, Straps
|
26 |
+
Ties, Belts, Crafts and Dog Leash (50 Pack) Descripion: [''50pcs 1inch Metal D
|
27 |
+
Rings Buckles for Straps Ties Belts Bags, Silver ☛Specification : √Material:
|
28 |
+
alloy √Color: Silver √Inner width: 25mm √Inner high: 16mm √Thickness: 3mm ☛LOAD
|
29 |
+
BEARING : Made from strong metal, these D ring fasteners have good load bearing
|
30 |
+
characteristics and can resist sudden impact. ☛GOOD GIFTS : The package includes
|
31 |
+
50 pieces Silver d rings. You can use them to make beautiful bags to send your
|
32 |
+
friends or your family. ☛APPLICATION: Suitable for DIY Fashion Belts. Suitable
|
33 |
+
for Pets Collars. Suitable for Strap. ☛Package included: 50 x D Rings(1 inch) ☛Note:
|
34 |
+
1.Please allow 1-3mm minor deviation due to manual measurement. 2.Due to the difference
|
35 |
+
between different monitors, the picture may not reflect the actual color of the
|
36 |
+
item.'']'
|
37 |
+
- source_sentence: I'm looking for a versatile outdoor garment that can handle various
|
38 |
+
weather conditions while providing ample storage options. It should be comfortable
|
39 |
+
to wear for activities like fishing or photography and have a hood that can be
|
40 |
+
removed.
|
41 |
+
sentences:
|
42 |
+
- "Title: Yimidear Unisex Outdoor Casual Quick-Drying Extra Pockets Fishing Vest\
|
43 |
+
\ Travel Photography Vest with Detachable Hood Descripion: ['Features:'\n 'The\
|
44 |
+
\ characteristics of the multi-functional leisure vest features large capacity,\
|
45 |
+
\ highly breathable, can protect you from wind and rain. And this multi-purpose\
|
46 |
+
\ vest with high strength and good extensibility, will make you feel comfortable.Condition:\
|
47 |
+
\ 100% Brand New.Material: Nylon & Polyester MeshGender: Men&Women'\n 'Size:'\n\
|
48 |
+
\ 'M: Bust: 110cm/43.3\", Shoulder Width: 42cm/16.54\", Clothes Length: 62cm/24.4\"\
|
49 |
+
.L: Bust: 114cm/44.88\", Shoulder Width: 43cm/16.93\", Clothes Length: 66cm/25.98\"\
|
50 |
+
.XL: Bust: 116cm/45.67\", Shoulder Width: 44cm/17.32\", Clothes Length: 68cm/26.77\"\
|
51 |
+
.XXL: Bust: 122cm/48\", Shoulder Width: 46cm/18.1\", Clothes Length: 70cm/27.56\"\
|
52 |
+
.'\n 'Note:'\n '1-2cm error of measuring is a reasonable range due to different\
|
53 |
+
\ measurement methods.Please kingly understand that.Due to different camera lens\
|
54 |
+
\ and light environments, the real item color which you receive may be a little\
|
55 |
+
\ vary from the listing picture. Thanks for your understanding.'\n 'Package include'\
|
56 |
+
\ '1 x Vest']"
|
57 |
+
- 'Title: 1-3 Pack Famous TIK Tok Butt Lift High Waist Yoga Workout Pants Pattern
|
58 |
+
Scrunch Tummy Control Sliming Leggings for Women Descripion: [''72% Polyester,
|
59 |
+
28% Spandex Tiktok Internet celebrity recommendation. Turn your gear inside out
|
60 |
+
when washing; wash separately. Air dry or tumble dry low Crafted from a brushed,
|
61 |
+
buttery soft and stretch fabric for delivering you the naked sensation and the
|
62 |
+
unrestricted movement Experience the comfort of yoga pants with a seamless waistband
|
63 |
+
that does not dig in Side pockets allow you to store your personal items when
|
64 |
+
you’re on the go Flatlock construction minimize chafe. Approx. 25” inseam; 7/8
|
65 |
+
length'']'
|
66 |
+
- 'Title: I Love You 3000 Keychain Iron Man for Women Men Valentine Day Gifts for
|
67 |
+
Lover Couple Christmas Birthday Anniversary Keychain Gifts for Boyfriend Husband
|
68 |
+
Love You Gifts for Fiance for Him Her Descripion: [''★"I love you 3,000", a line
|
69 |
+
originally said by Tony Stark\''s daughter Morgan in Avengers: Endgame, is definitely
|
70 |
+
going down in history as one of the most impactful quotes in the Marvel Cinematic
|
71 |
+
Universe (MCU).★Although he may be gone, his influence lives in every one of us.
|
72 |
+
Buy these keychains to show as a proof to others that Tony Stark has a Heart and
|
73 |
+
your love for him is 3000.★Exquisite and Useful: Delicate Keychain pendant look
|
74 |
+
chic, great on your purses backpack handbags, and also fit for as DIY accessories
|
75 |
+
to connect charms, links and other ornaments★After-Sales Service: 90-Day money
|
76 |
+
back guarantee or replacement; We are engaged in providing the best shopping experience
|
77 |
+
for you.★Notice: The little connecting ring is soldered to hold the plates securely.'']'
|
78 |
+
- source_sentence: I'm looking for a collectible set that celebrates a specific game
|
79 |
+
location, featuring a unique character. It should include a decorative pin and
|
80 |
+
be a fun addition to a gaming collection.
|
81 |
+
sentences:
|
82 |
+
- 'Title: Pokemon Champions Path Pin Collection Hammerlocke Gym Featuring Duraludon
|
83 |
+
Descripion: [''Pokemon Champions Path Pin Collection Hammerlocke Gym Featuring
|
84 |
+
Duraludon'']'
|
85 |
+
- 'Title: Kiddus Fashionable Girls Watch for Kids. Children’s Analogue Wristwatch
|
86 |
+
with Educational Exercises. Japanese Quartz Movement. Cute, Stylish, Elegant &
|
87 |
+
Fabulous Descripion: ["STYLISH & EDUCATIONAL WATCH FOR KIDS: Designed for children
|
88 |
+
who are learning to read the time AND who want to be fabulously fashionable. Cute
|
89 |
+
designs, vibrant colours and glitter all over make them super attractive. Your
|
90 |
+
child will love his fancy watch! RECOMMENDED AGE: For Children from 5 years old.
|
91 |
+
Not suitable for children under 3 years of age due to small parts which may cause
|
92 |
+
a chocking hazard. RELIABLE & ADJUSTABLE: Provided with a HIGH-QUALITY Japanese
|
93 |
+
Mechanism and LONG LASTING Japanese battery, our kids watch line features also
|
94 |
+
a SHOCK RESISTANT CASE, nickel-free stainless steel backside, and 8 adjustment
|
95 |
+
holes on the strap to fit wrists large and small. Our watches for kids are water
|
96 |
+
resistant, so they can withstand splashes while washing hands or playing in the
|
97 |
+
rain but should be removed before bathing or swimming. PERFECT GIFT - GIVE THE
|
98 |
+
GIFT OF TIME: Available in a variety of styles and colours, our childrens'' watches
|
99 |
+
come packaged in a GIFT BOX so you can watch your child’s face light up as the
|
100 |
+
box is opened. Also included is a worksheet with specific Time Teacher exercises
|
101 |
+
to learn to read the time with your child. PURCHASE WITHOUT WORRY: As our products
|
102 |
+
are rigorously tested and made with love, we firmly believe in the high quality
|
103 |
+
of our product. So we offer a 30 day unconditional MONEY BACK GUARANTEE and a
|
104 |
+
12-month warranty. Even if you give it to someone else, it''s still covered! If
|
105 |
+
you have problems or issues with the watch, contact us and we will help you."]'
|
106 |
+
- 'Title: Kayhoma Extra Soft Artificial Wool Leg Warmer Descripion: [''Kayhoma Extra
|
107 |
+
Soft Artificial Wool Leg Warmer Thicker - Increased the density of knitted fabric
|
108 |
+
by 30% than last design, which become thicker and warmer. Softer - From natural
|
109 |
+
cotton upgrade to artificial wool. It is almost as soft as wool. and not easy
|
110 |
+
out of shape after worn and washed. Good elasticity makes it possible to completely
|
111 |
+
cover the calf and not be too tight, protecting your circulation. Stay Up Well
|
112 |
+
- After multiple tests and experiments, the leg warmer will stay up all day, feel
|
113 |
+
free to walk or move as you like, not having to keep tugging at them to keep them
|
114 |
+
up.'']'
|
115 |
+
- source_sentence: I'm looking for a reusable face covering that offers protection
|
116 |
+
against dust. It should have ear loops for a secure fit and come with a filter
|
117 |
+
option.
|
118 |
+
sentences:
|
119 |
+
- "Title: Balaclava Face Mask - New Range 3 Pack Now with 20 PM 2.5 Filters - Comfortable\
|
120 |
+
\ Cooling Neck Gaiter with Filter and Ear Loops, Bandana Face Mask Black Grey,\
|
121 |
+
\ Silk face mask, Sports Mask with Filters. Descripion: ['Free Shipping $25+ orders,\
|
122 |
+
\ save a few dollars, shipping 5-8 days'\n 'Free Shipping $25+ orders, save a\
|
123 |
+
\ few dollars, shipping 5-8 days'\n 'Super comfortable spandex material for easy\
|
124 |
+
\ fit'\n 'Super comfortable spandex material for easy fit'\n 'Stylish and fashionable,\
|
125 |
+
\ can be worn for sports or social'\n 'Stylish and fashionable, can be worn for\
|
126 |
+
\ sports or social'\n 'Breathable face mask with filter to capture dust & pollen'\n\
|
127 |
+
\ 'Breathable face mask with filter to capture dust & pollen'\n 'One size fits\
|
128 |
+
\ most people' 'One size fits most people'\n 'The neck gaiters are a quality made\
|
129 |
+
\ product'\n 'The neck gaiters are a quality made product'\n 'Wear with or without\
|
130 |
+
\ the filter depending on your requirements'\n 'Wear with or without the filter\
|
131 |
+
\ depending on your requirements'\n 'Each pack includes 3 Masks (1x Jet Black,\
|
132 |
+
\ 1x Black Violet, 1x Deep Grey) + extra 20x PM 2.5 filters'\n 'Each pack includes\
|
133 |
+
\ 3 Masks (1x Jet Black, 1x Black Violet, 1x Deep Grey) + extra 20x PM 2.5 filters'\n\
|
134 |
+
\ 'We use these ourselves on the motorcycles and current stage 4 restrictions\
|
135 |
+
\ in Australia as an outdoor face mask.'\n 'Very comfortable face mask, stretchy\
|
136 |
+
\ with spandex fabric that fits most men, women and teenagers.'\n 'Perfect to\
|
137 |
+
\ wear for sports and outdoors while walking, cycling, hiking, skiing, fishing,\
|
138 |
+
\ motorcycle or horse riding, also good as a UV protection face mask to protect\
|
139 |
+
\ you from direct sunlight and sunburn, would assist people with hay fever.'\n\
|
140 |
+
\ 'Not only covers the face but also covers the neck for maximum protection, being\
|
141 |
+
\ soft and light weight, the fabric moves over the skin which has a cooling effect.'\n\
|
142 |
+
\ 'Reusable simply wash the balaclava and replace the PM 2.5 filters as needed.'\n\
|
143 |
+
\ 'More filters can be purchased in large pack to make it affordable to replace\
|
144 |
+
\ regularly as recommended.'\n 'Perfect for a thoughtful gift that family and\
|
145 |
+
\ friends will definitely use and enjoy for years to come.'\n 'What are your favorite\
|
146 |
+
\ colours and styles, let us know, we are expanding our range to meet our clients\
|
147 |
+
\ requirements. Shipping directly from the USA home land to your home in 1-5 days,\
|
148 |
+
\ we are hope you enjoy this product and can wear while doing most activities\
|
149 |
+
\ and social environments.']"
|
150 |
+
- 'Title: Men''s genuine fullgrain tanned leather jeans belt with buckle Descripion:
|
151 |
+
["GENUINE MEN’S LEATHER BELT: The ''s Leather Belt is made with 100% genuine leather
|
152 |
+
and has a single-loop antique-finish buckle"]'
|
153 |
+
- 'Title: Ruikim Mouth Bandana For Dust Protection Face Bandana Washable Earloop
|
154 |
+
-Pm2.5 Filter Chip Descripion: [''100% Satisfy Service: 12 Month Quality Guarantee,
|
155 |
+
Buy With Confidence'']'
|
156 |
+
- source_sentence: I'm looking for a charming ring that embodies innocence and purity,
|
157 |
+
suitable for daily wear. It should have a minimalistic design and be stackable
|
158 |
+
with other rings. Durability is key, and I prefer it to be available in a unique
|
159 |
+
metallic finish.
|
160 |
+
sentences:
|
161 |
+
- "Title: CozzySayido Daisy Flower Ring Bands for Woman Innocent Daisy Promise Dainty\
|
162 |
+
\ Delicate Design Minimalistic Stackable Available in Silver and Rose Gold Descripion:\
|
163 |
+
\ ['“Always have something beautiful in sight, even if it’s just a daisy in a\
|
164 |
+
\ jelly glass.”'\n '- H. Jackson, Brown Jr.'\n 'Simple, sweet, stackable everyday\
|
165 |
+
\ ring for the sweetest ones.' 'Perks'\n 'Silver or rose gold Stainless steel\
|
166 |
+
\ No corrosion No peeling No spotting or staining No green fingers Resistant to\
|
167 |
+
\ perfume, sweat, and salt water Styling versatility (stack rings, minimalistic\
|
168 |
+
\ one-piece, knuckle, toe, stopper) Medical-grade stainless steel Unbreakable\
|
169 |
+
\ Unbendable Dainty, sweet, and delicate design 30-day full refund'\n 'Sizing'\n\
|
170 |
+
\ 'Available in size 3-10 (For sizing specs and how to know your size, please\
|
171 |
+
\ consult out sizing guide in the photo panel above.)'\n 'CozzySayido'\n 'We brainstorm\
|
172 |
+
\ for our customer to get the best value product. Proudly present, a daisy flower\
|
173 |
+
\ ring. We chose stainless-steel material which is no allergies for sensitive\
|
174 |
+
\ skin, durable and tough in any conditions, no matter if you wash your hand with\
|
175 |
+
\ alcohol sanitizer or washing tons of dishes or swimming in chlorine and salt\
|
176 |
+
\ water, it never gets spotting, staining or turn your finger green or any other\
|
177 |
+
\ color. Unbreakable and unbendable no matter, how you wear it.'\n 'Meaningful\
|
178 |
+
\ design, daisy flower is the symbol of innocence, purity, true love and new beginning\
|
179 |
+
\ to make every of your day the start of something new.'\n 'Designs as well as\
|
180 |
+
\ on-trend fashion jewelry for women with minimalist, dainty, sweet, and delicate\
|
181 |
+
\ style.']"
|
182 |
+
- 'Title: Chelsea FC Official Soccer Gift Mens Graphic T-Shirt Navy XXL Descripion:
|
183 |
+
[''Official CFC mens T-shirt Large club crest & text print to front Garment Size
|
184 |
+
(Chest): Sm. 40"; Med. 41"; Lge. 42"; XL 44"; XXL 48"; 3XL 52" 100% cotton, top
|
185 |
+
quality T-shirt Many more gift ideas for him @ FootballShopOnline'']'
|
186 |
+
- "Title: TMVFPYR Youth Pretty Cotton Moisture Wicking Extra Heavy Cushion Crew\
|
187 |
+
\ Socks… Descripion: ['PRODUCT SPECIFICATION'\n '- Size: 7.9in- Weight: 0.26ib/120g-\
|
188 |
+
\ Material: Polyester- Style: Individual, FashionPackage includes:1 Socks'\n 'PRODUCT\
|
189 |
+
\ FEATURES' 'DURABLE AND LONG LASTING'\n 'Superior quality fabrics makes them\
|
190 |
+
\ long lasting and durable. They won’t rip, tear or shred and they’ll maintain\
|
191 |
+
\ their outstanding look and feel through machine washing.'\n 'IDEAL FOR OUTDOOR\
|
192 |
+
\ SPORTS'\n 'Trekking, walking, running, camping, mountaineering, climbing, skiing,\
|
193 |
+
\ snowboarding, backpacking, traveling, various athletic pursuits or daily wear'\n\
|
194 |
+
\ 'COZY AND COMFORTABLE'\n 'Breathable materials give your feet the comfort they\
|
195 |
+
\ deserve. Keep your feet warm, cool and dry all day long. Luxury materials won’t\
|
196 |
+
\ absorb sweat and feel great on your feet.']"
|
197 |
+
pipeline_tag: sentence-similarity
|
198 |
+
library_name: sentence-transformers
|
199 |
+
---
|
200 |
+
|
201 |
+
# SentenceTransformer based on FacebookAI/roberta-base
|
202 |
+
|
203 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base). 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.
|
204 |
+
|
205 |
+
## Model Details
|
206 |
+
|
207 |
+
### Model Description
|
208 |
+
- **Model Type:** Sentence Transformer
|
209 |
+
- **Base model:** [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) <!-- at revision e2da8e2f811d1448a5b465c236feacd80ffbac7b -->
|
210 |
+
- **Maximum Sequence Length:** 128 tokens
|
211 |
+
- **Output Dimensionality:** 768 tokens
|
212 |
+
- **Similarity Function:** Cosine Similarity
|
213 |
+
<!-- - **Training Dataset:** Unknown -->
|
214 |
+
<!-- - **Language:** Unknown -->
|
215 |
+
<!-- - **License:** Unknown -->
|
216 |
+
|
217 |
+
### Model Sources
|
218 |
+
|
219 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
220 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
221 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
222 |
+
|
223 |
+
### Full Model Architecture
|
224 |
+
|
225 |
+
```
|
226 |
+
SentenceTransformer(
|
227 |
+
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: RobertaModel
|
228 |
+
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
|
229 |
+
)
|
230 |
+
```
|
231 |
+
|
232 |
+
## Usage
|
233 |
+
|
234 |
+
### Direct Usage (Sentence Transformers)
|
235 |
+
|
236 |
+
First install the Sentence Transformers library:
|
237 |
+
|
238 |
+
```bash
|
239 |
+
pip install -U sentence-transformers
|
240 |
+
```
|
241 |
+
|
242 |
+
Then you can load this model and run inference.
|
243 |
+
```python
|
244 |
+
from sentence_transformers import SentenceTransformer
|
245 |
+
|
246 |
+
# Download from the 🤗 Hub
|
247 |
+
model = SentenceTransformer("knguyennguyen/fashion_5k")
|
248 |
+
# Run inference
|
249 |
+
sentences = [
|
250 |
+
"I'm looking for a charming ring that embodies innocence and purity, suitable for daily wear. It should have a minimalistic design and be stackable with other rings. Durability is key, and I prefer it to be available in a unique metallic finish.",
|
251 |
+
"Title: CozzySayido Daisy Flower Ring Bands for Woman Innocent Daisy Promise Dainty Delicate Design Minimalistic Stackable Available in Silver and Rose Gold Descripion: ['“Always have something beautiful in sight, even if it’s just a daisy in a jelly glass.”'\n '- H. Jackson, Brown Jr.'\n 'Simple, sweet, stackable everyday ring for the sweetest ones.' 'Perks'\n 'Silver or rose gold Stainless steel No corrosion No peeling No spotting or staining No green fingers Resistant to perfume, sweat, and salt water Styling versatility (stack rings, minimalistic one-piece, knuckle, toe, stopper) Medical-grade stainless steel Unbreakable Unbendable Dainty, sweet, and delicate design 30-day full refund'\n 'Sizing'\n 'Available in size 3-10 (For sizing specs and how to know your size, please consult out sizing guide in the photo panel above.)'\n 'CozzySayido'\n 'We brainstorm for our customer to get the best value product. Proudly present, a daisy flower ring. We chose stainless-steel material which is no allergies for sensitive skin, durable and tough in any conditions, no matter if you wash your hand with alcohol sanitizer or washing tons of dishes or swimming in chlorine and salt water, it never gets spotting, staining or turn your finger green or any other color. Unbreakable and unbendable no matter, how you wear it.'\n 'Meaningful design, daisy flower is the symbol of innocence, purity, true love and new beginning to make every of your day the start of something new.'\n 'Designs as well as on-trend fashion jewelry for women with minimalist, dainty, sweet, and delicate style.']",
|
252 |
+
'Title: Chelsea FC Official Soccer Gift Mens Graphic T-Shirt Navy XXL Descripion: [\'Official CFC mens T-shirt Large club crest & text print to front Garment Size (Chest): Sm. 40"; Med. 41"; Lge. 42"; XL 44"; XXL 48"; 3XL 52" 100% cotton, top quality T-shirt Many more gift ideas for him @ FootballShopOnline\']',
|
253 |
+
]
|
254 |
+
embeddings = model.encode(sentences)
|
255 |
+
print(embeddings.shape)
|
256 |
+
# [3, 768]
|
257 |
+
|
258 |
+
# Get the similarity scores for the embeddings
|
259 |
+
similarities = model.similarity(embeddings, embeddings)
|
260 |
+
print(similarities.shape)
|
261 |
+
# [3, 3]
|
262 |
+
```
|
263 |
+
|
264 |
+
<!--
|
265 |
+
### Direct Usage (Transformers)
|
266 |
+
|
267 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
268 |
+
|
269 |
+
</details>
|
270 |
+
-->
|
271 |
+
|
272 |
+
<!--
|
273 |
+
### Downstream Usage (Sentence Transformers)
|
274 |
+
|
275 |
+
You can finetune this model on your own dataset.
|
276 |
+
|
277 |
+
<details><summary>Click to expand</summary>
|
278 |
+
|
279 |
+
</details>
|
280 |
+
-->
|
281 |
+
|
282 |
+
<!--
|
283 |
+
### Out-of-Scope Use
|
284 |
+
|
285 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
286 |
+
-->
|
287 |
+
|
288 |
+
<!--
|
289 |
+
## Bias, Risks and Limitations
|
290 |
+
|
291 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
292 |
+
-->
|
293 |
+
|
294 |
+
<!--
|
295 |
+
### Recommendations
|
296 |
+
|
297 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
298 |
+
-->
|
299 |
+
|
300 |
+
## Training Details
|
301 |
+
|
302 |
+
### Training Dataset
|
303 |
+
|
304 |
+
#### Unnamed Dataset
|
305 |
+
|
306 |
+
|
307 |
+
* Size: 4,693 training samples
|
308 |
+
* Columns: <code>sentence_0</code> and <code>sentence_1</code>
|
309 |
+
* Approximate statistics based on the first 1000 samples:
|
310 |
+
| | sentence_0 | sentence_1 |
|
311 |
+
|:--------|:----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
|
312 |
+
| type | string | string |
|
313 |
+
| details | <ul><li>min: 26 tokens</li><li>mean: 44.9 tokens</li><li>max: 87 tokens</li></ul> | <ul><li>min: 21 tokens</li><li>mean: 106.64 tokens</li><li>max: 128 tokens</li></ul> |
|
314 |
+
* Samples:
|
315 |
+
| sentence_0 | sentence_1 |
|
316 |
+
|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
317 |
+
| <code>I'm looking for a spooky mask that can enhance my costume for a Halloween event. It should have a unique design, feature some lighting effects, and come with hair, suitable for adults.</code> | <code>Title: Scary Clown Mask for Penny It Cosplay Costume Halloween Led Light Up Joker Mask with Hair Latex Horror Adult Mask Party Props Descripion: ['This clown costume mask for adults is available in a standard size that fits most adults and teens and is perfect for Halloween, themed parties, haunted houses, and more. Does not include shoes or costume. Care for this 100% latex mask with attached synthetic polyester hair']</code> |
|
318 |
+
| <code>I'm looking for a festive accessory set to celebrate a special birthday. It should include a stylish decorative piece that can be adjusted for comfort and a fun headpiece that adds a touch of sparkle, perfect for both intimate gatherings and lively celebrations.</code> | <code>Title: Birthday Queen Sash & Rhinestone Headband Set - Silver Glitter Birthday Sash Birthday Gifts for Women Birthday Party Supplies Descripion: ['"Birthday Queen" sash & rhinestone headband set ↑ No need to keep looking...it\'s the ultimate birthday party gifts set! ✓ Silver glitter sash + black lettering looks great on Instagram. Make the birthday queen feel special and stand out from the crowd. ✓ It\'s party tested and approved...will last day into night! Not only perfect for the cozy birthday parties with family but also for the crazy night at Vegas. ✓ No size trouble + Comfortable wearing: Sash can be adjust by clip on to fit from all type body figure. Headband can sit comfortably on the head and the letters are large enough to be clearly identifiable We had so much fun designing this birthday gifts set, we hope they add just as much fun to your parties too. Get the sash and headband at the same time and be prepare for the birthday celebration!']</code> |
|
319 |
+
| <code>I'm looking for a cozy and stylish outerwear option for the colder months, ideally with a hood and a playful design. It should be warm and plush, perfect for layering, and have a comfortable fit.</code> | <code>Title: OutTop Sherpa Jacket Women Fall Winter Plush Warm Hooded Stripe Color Block Thicken Warm Fleece Coats Parka Outwear Descripion: ['Package Include:1 PC Coats'<br> '==========================================================================='<br> 'SIZE TABLE' ': International standard : 1 inch = 2.54 cm☺'<br> "Size:S____US:4____Bust:100cm/39.37''____Sleeve:56.5cm/22.24''____Length:88cm/34.65''"<br> "Size:M____US:6____Bust:105cm/41.34''____Sleeve:57cm/22.44''____Length:89cm/35.04''"<br> "Size:L____US:8____Bust:110cm/43.31''____Sleeve:57.5cm/22.64''____Length:90cm/35.43''"<br> "Size:XL____US:10____Bust:115cm/45.28''____Sleeve:58cm/22.83''____Length:91cm/35.83''"<br> "Size:XXL____US:12____Bust:120cm/47.24''____Sleeve:58.5cm/23.03''____Length:92cm/36.22''"<br> "Size:XXXL____US:14____Bust:125cm/49.21''____Sleeve:59cm/23.23''____Length:93cm/36.61''"<br> "Size:XXXXL____US:16____Bust:130cm/51.18''____Sleeve:59.5cm/23.43''____Length:94cm/37.01''"<br> "Size:XXXXXL____US:18____Bust:135cm/53.15''____Sleeve:60cm/23.62''____Length:95cm/37.40''"<br> '==========================================================================='<br> 'Any questions, please feel free to contact us.☺☺' 'Delivery:'<br> 'Standard express would take 7-20 days to deliver. Expedited express need 5-7 days.☺☺']</code> |
|
320 |
+
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
|
321 |
+
```json
|
322 |
+
{
|
323 |
+
"scale": 20.0,
|
324 |
+
"similarity_fct": "cos_sim"
|
325 |
+
}
|
326 |
+
```
|
327 |
+
|
328 |
+
### Training Hyperparameters
|
329 |
+
#### Non-Default Hyperparameters
|
330 |
+
|
331 |
+
- `per_device_train_batch_size`: 128
|
332 |
+
- `per_device_eval_batch_size`: 128
|
333 |
+
- `num_train_epochs`: 5
|
334 |
+
- `multi_dataset_batch_sampler`: round_robin
|
335 |
+
|
336 |
+
#### All Hyperparameters
|
337 |
+
<details><summary>Click to expand</summary>
|
338 |
+
|
339 |
+
- `overwrite_output_dir`: False
|
340 |
+
- `do_predict`: False
|
341 |
+
- `eval_strategy`: no
|
342 |
+
- `prediction_loss_only`: True
|
343 |
+
- `per_device_train_batch_size`: 128
|
344 |
+
- `per_device_eval_batch_size`: 128
|
345 |
+
- `per_gpu_train_batch_size`: None
|
346 |
+
- `per_gpu_eval_batch_size`: None
|
347 |
+
- `gradient_accumulation_steps`: 1
|
348 |
+
- `eval_accumulation_steps`: None
|
349 |
+
- `torch_empty_cache_steps`: None
|
350 |
+
- `learning_rate`: 5e-05
|
351 |
+
- `weight_decay`: 0.0
|
352 |
+
- `adam_beta1`: 0.9
|
353 |
+
- `adam_beta2`: 0.999
|
354 |
+
- `adam_epsilon`: 1e-08
|
355 |
+
- `max_grad_norm`: 1
|
356 |
+
- `num_train_epochs`: 5
|
357 |
+
- `max_steps`: -1
|
358 |
+
- `lr_scheduler_type`: linear
|
359 |
+
- `lr_scheduler_kwargs`: {}
|
360 |
+
- `warmup_ratio`: 0.0
|
361 |
+
- `warmup_steps`: 0
|
362 |
+
- `log_level`: passive
|
363 |
+
- `log_level_replica`: warning
|
364 |
+
- `log_on_each_node`: True
|
365 |
+
- `logging_nan_inf_filter`: True
|
366 |
+
- `save_safetensors`: True
|
367 |
+
- `save_on_each_node`: False
|
368 |
+
- `save_only_model`: False
|
369 |
+
- `restore_callback_states_from_checkpoint`: False
|
370 |
+
- `no_cuda`: False
|
371 |
+
- `use_cpu`: False
|
372 |
+
- `use_mps_device`: False
|
373 |
+
- `seed`: 42
|
374 |
+
- `data_seed`: None
|
375 |
+
- `jit_mode_eval`: False
|
376 |
+
- `use_ipex`: False
|
377 |
+
- `bf16`: False
|
378 |
+
- `fp16`: False
|
379 |
+
- `fp16_opt_level`: O1
|
380 |
+
- `half_precision_backend`: auto
|
381 |
+
- `bf16_full_eval`: False
|
382 |
+
- `fp16_full_eval`: False
|
383 |
+
- `tf32`: None
|
384 |
+
- `local_rank`: 0
|
385 |
+
- `ddp_backend`: None
|
386 |
+
- `tpu_num_cores`: None
|
387 |
+
- `tpu_metrics_debug`: False
|
388 |
+
- `debug`: []
|
389 |
+
- `dataloader_drop_last`: False
|
390 |
+
- `dataloader_num_workers`: 0
|
391 |
+
- `dataloader_prefetch_factor`: None
|
392 |
+
- `past_index`: -1
|
393 |
+
- `disable_tqdm`: False
|
394 |
+
- `remove_unused_columns`: True
|
395 |
+
- `label_names`: None
|
396 |
+
- `load_best_model_at_end`: False
|
397 |
+
- `ignore_data_skip`: False
|
398 |
+
- `fsdp`: []
|
399 |
+
- `fsdp_min_num_params`: 0
|
400 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
401 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
402 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
403 |
+
- `deepspeed`: None
|
404 |
+
- `label_smoothing_factor`: 0.0
|
405 |
+
- `optim`: adamw_torch
|
406 |
+
- `optim_args`: None
|
407 |
+
- `adafactor`: False
|
408 |
+
- `group_by_length`: False
|
409 |
+
- `length_column_name`: length
|
410 |
+
- `ddp_find_unused_parameters`: None
|
411 |
+
- `ddp_bucket_cap_mb`: None
|
412 |
+
- `ddp_broadcast_buffers`: False
|
413 |
+
- `dataloader_pin_memory`: True
|
414 |
+
- `dataloader_persistent_workers`: False
|
415 |
+
- `skip_memory_metrics`: True
|
416 |
+
- `use_legacy_prediction_loop`: False
|
417 |
+
- `push_to_hub`: False
|
418 |
+
- `resume_from_checkpoint`: None
|
419 |
+
- `hub_model_id`: None
|
420 |
+
- `hub_strategy`: every_save
|
421 |
+
- `hub_private_repo`: False
|
422 |
+
- `hub_always_push`: False
|
423 |
+
- `gradient_checkpointing`: False
|
424 |
+
- `gradient_checkpointing_kwargs`: None
|
425 |
+
- `include_inputs_for_metrics`: False
|
426 |
+
- `eval_do_concat_batches`: True
|
427 |
+
- `fp16_backend`: auto
|
428 |
+
- `push_to_hub_model_id`: None
|
429 |
+
- `push_to_hub_organization`: None
|
430 |
+
- `mp_parameters`:
|
431 |
+
- `auto_find_batch_size`: False
|
432 |
+
- `full_determinism`: False
|
433 |
+
- `torchdynamo`: None
|
434 |
+
- `ray_scope`: last
|
435 |
+
- `ddp_timeout`: 1800
|
436 |
+
- `torch_compile`: False
|
437 |
+
- `torch_compile_backend`: None
|
438 |
+
- `torch_compile_mode`: None
|
439 |
+
- `dispatch_batches`: None
|
440 |
+
- `split_batches`: None
|
441 |
+
- `include_tokens_per_second`: False
|
442 |
+
- `include_num_input_tokens_seen`: False
|
443 |
+
- `neftune_noise_alpha`: None
|
444 |
+
- `optim_target_modules`: None
|
445 |
+
- `batch_eval_metrics`: False
|
446 |
+
- `eval_on_start`: False
|
447 |
+
- `use_liger_kernel`: False
|
448 |
+
- `eval_use_gather_object`: False
|
449 |
+
- `batch_sampler`: batch_sampler
|
450 |
+
- `multi_dataset_batch_sampler`: round_robin
|
451 |
+
|
452 |
+
</details>
|
453 |
+
|
454 |
+
### Framework Versions
|
455 |
+
- Python: 3.11.11
|
456 |
+
- Sentence Transformers: 3.1.1
|
457 |
+
- Transformers: 4.45.2
|
458 |
+
- PyTorch: 2.5.1+cu121
|
459 |
+
- Accelerate: 1.2.1
|
460 |
+
- Datasets: 3.2.0
|
461 |
+
- Tokenizers: 0.20.3
|
462 |
+
|
463 |
+
## Citation
|
464 |
+
|
465 |
+
### BibTeX
|
466 |
+
|
467 |
+
#### Sentence Transformers
|
468 |
+
```bibtex
|
469 |
+
@inproceedings{reimers-2019-sentence-bert,
|
470 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
471 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
472 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
473 |
+
month = "11",
|
474 |
+
year = "2019",
|
475 |
+
publisher = "Association for Computational Linguistics",
|
476 |
+
url = "https://arxiv.org/abs/1908.10084",
|
477 |
+
}
|
478 |
+
```
|
479 |
+
|
480 |
+
#### MultipleNegativesRankingLoss
|
481 |
+
```bibtex
|
482 |
+
@misc{henderson2017efficient,
|
483 |
+
title={Efficient Natural Language Response Suggestion for Smart Reply},
|
484 |
+
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},
|
485 |
+
year={2017},
|
486 |
+
eprint={1705.00652},
|
487 |
+
archivePrefix={arXiv},
|
488 |
+
primaryClass={cs.CL}
|
489 |
+
}
|
490 |
+
```
|
491 |
+
|
492 |
+
<!--
|
493 |
+
## Glossary
|
494 |
+
|
495 |
+
*Clearly define terms in order to be accessible across audiences.*
|
496 |
+
-->
|
497 |
+
|
498 |
+
<!--
|
499 |
+
## Model Card Authors
|
500 |
+
|
501 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
502 |
+
-->
|
503 |
+
|
504 |
+
<!--
|
505 |
+
## Model Card Contact
|
506 |
+
|
507 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
508 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "roberta",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.45.2",
|
24 |
+
"type_vocab_size": 1,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 50265
|
27 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "3.1.1",
|
4 |
+
"transformers": "4.45.2",
|
5 |
+
"pytorch": "2.5.1+cu121"
|
6 |
+
},
|
7 |
+
"prompts": {},
|
8 |
+
"default_prompt_name": null,
|
9 |
+
"similarity_fn_name": "cosine"
|
10 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7ab3e65e7878528ad21caa89369f453fecb97ba8c66f43dff54f924a26b5722
|
3 |
+
size 498604904
|
modules.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[
|
2 |
+
{
|
3 |
+
"idx": 0,
|
4 |
+
"name": "0",
|
5 |
+
"path": "",
|
6 |
+
"type": "sentence_transformers.models.Transformer"
|
7 |
+
},
|
8 |
+
{
|
9 |
+
"idx": 1,
|
10 |
+
"name": "1",
|
11 |
+
"path": "1_Pooling",
|
12 |
+
"type": "sentence_transformers.models.Pooling"
|
13 |
+
}
|
14 |
+
]
|
sentence_bert_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"max_seq_length": 128,
|
3 |
+
"do_lower_case": false
|
4 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
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 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"50264": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": false,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"model_max_length": 128,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"sep_token": "</s>",
|
54 |
+
"tokenizer_class": "RobertaTokenizer",
|
55 |
+
"trim_offsets": true,
|
56 |
+
"unk_token": "<unk>"
|
57 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|