knguyennguyen
commited on
Add new SentenceTransformer model.
Browse files- 1_Pooling/config.json +10 -0
- README.md +506 -0
- config.json +24 -0
- config_sentence_transformers.json +10 -0
- model.safetensors +3 -0
- modules.json +14 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +72 -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": 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 +1,506 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- sentence-transformers
|
4 |
+
- sentence-similarity
|
5 |
+
- feature-extraction
|
6 |
+
- generated_from_trainer
|
7 |
+
- dataset_size:11397
|
8 |
+
- loss:MultipleNegativesRankingLoss
|
9 |
+
base_model: sentence-transformers/all-mpnet-base-v2
|
10 |
+
widget:
|
11 |
+
- source_sentence: a leather jacket for casual occasions and weekend trips for men
|
12 |
+
sentences:
|
13 |
+
- "Title: Blazer Jackets for Women Business Casual Suit Coat Zipper Crop Cardigan\
|
14 |
+
\ Work Outfits Office Long Sleeve Boyfriend Blazers Descripion: [\"Blazer Jackets\
|
15 |
+
\ for Women Business Casual Suit Coat Zipper Crop Cardigan Work Outfits Office\
|
16 |
+
\ Long Sleeve Boyfriend Blazers/Women's Casual Blazers Open Front Long Sleeve\
|
17 |
+
\ Button Work Office Blazer Jacket\"\n '【 Feature:】'\n \"✨ Women blazer casual,\
|
18 |
+
\ open front cardigan jacket comes with long sleeve and label collar. ✨ Occasion:\
|
19 |
+
\ Women's lapel pocket blazer suit perfect for casual, daily life, work office,\
|
20 |
+
\ going out, night out, travel, vacation, holiday, spring, fall, winter, etc.\
|
21 |
+
\ ✨ Women's Casual Lightweight Open Front Cardigan is extremely comfortable! It\
|
22 |
+
\ can be dressed up for business or work, or dressed down for a casual look! Good\
|
23 |
+
\ quality and versatile!\"\n '【 Size Chart】'\n \"Size:S US:6 EU:36 Bust:98cm/38.58''\
|
24 |
+
\ Sleeve:60cm/23.62'' Front Length:60cm/23.62'' Size:M US:8 EU:38 Bust:102cm/40.16''\
|
25 |
+
\ Sleeve:61cm/24.02'' Front Length:61cm/24.02'' Size:L US:10 EU:40 Bust:106cm/41.73''\
|
26 |
+
\ Sleeve:62cm/24.41'' Front Length:62cm/24.41'' Size:XL US:12 EU:42 Bust:110cm/43.31''\
|
27 |
+
\ Sleeve:63cm/24.80'' Front Length:63cm/24.80''\"\n '❤️ Please Refer to Our Size\
|
28 |
+
\ Chart for Choosing Your Most Suitable Open Front Lapel Blazer Suit/Long Sleeves\
|
29 |
+
\ Buttons Work Suit/Flap Pockets Suit Outerwear Coat, Work Blazer Suit for Women/Basic\
|
30 |
+
\ Lapel Collar Blazer Jacket for Women.'\n \"❤️BDFCY'S SERVICE:\"\n '\U0001F495\
|
31 |
+
About Shipping: ✨ Standard Shipping: 8-15 Biz Days to Arrive ✨ Expedited Shipping:\
|
32 |
+
\ 3-5 Biz Days to Arrive \U0001F495Guarantee: * We endeavors 100% customer satisfaction\
|
33 |
+
\ service and experience. * If you receive damaged or wrong items,please contact\
|
34 |
+
\ us, we will provide you a satisfactory solution asap, please rest assured to\
|
35 |
+
\ purchase.* If you are satisfied with our product or service,hope you can leave\
|
36 |
+
\ your positive message,thanks for your encouragement.']"
|
37 |
+
- 'Title: LZJDS Mens Wool Coats Casual Regular Fit Trenchcoats Double Collar Thick
|
38 |
+
Winter Peacoats Mid-Length Jacket Overcoat Descripion: ["★Mens trench coat autumn
|
39 |
+
winter long jacket overcoat business woolen coat with double collar (removable)
|
40 |
+
to resist the cold and keep warm. The fashion trend of woolen coat is becoming
|
41 |
+
more and more fierce. The design of this coat provides a new standardMaterial:
|
42 |
+
wool blend + polyester (30% wool 70% polyester fiber)Color: black, gray, camelSize:
|
43 |
+
M-170, L-175, XL-180, XXL-185, XXXL-190, XXXXL-195Style: business gentlemanFeatures:
|
44 |
+
thick, single-breasted, double-layer collar, side slit pockets★Packing list: 1*Men''s
|
45 |
+
thick windbreaker coat★Notes:1. Please carefully refer to our size suggestion
|
46 |
+
pictures (not the Amazon size chart). The jacket is a slim fit, slightly smaller
|
47 |
+
than expected2. We are trying to take a photo to show the color of the item, but
|
48 |
+
it may be different depending on the settings of the monitor3. Due to long-distance
|
49 |
+
transportation. The coat may be a little crumpled when delivered, we are glad
|
50 |
+
that you can iron it before wearing it, it will look much better."]'
|
51 |
+
- 'Title: Men Brown Air Force A-2 Leather Flight Bomber Jacket - ww2 flight jacket
|
52 |
+
- Men Navy G-1 Jacket - Brown Bomber leather Jacket Descripion: ["The G1 Men leather
|
53 |
+
jacket is a premium quality, vintage jacket designed to provide a rugged and stylish
|
54 |
+
look for men. The G1Leather jacket is made of high-quality distressed leather
|
55 |
+
that gives it a unique, worn-in appearance. The Distressed Brown leather jacket
|
56 |
+
features a stylish collar with a button closure and a front zipper closure. The
|
57 |
+
G1 Men jacket also comes with two spacious pockets on the front for storing your
|
58 |
+
essentials. The Leather jacket Men'' cuffs and hemline are made of rib-knit fabric,
|
59 |
+
which provides a comfortable fit and protects against cold winds. The Brown Bomber
|
60 |
+
jacket is a timeless classic that never goes out of style. It is perfect for casual
|
61 |
+
occasions, such as a night out with friends or a weekend trip. This jacket will
|
62 |
+
keep you looking stylish while also providing the warmth and comfort you need."]'
|
63 |
+
- source_sentence: a shirt jacket for warmth and comfort in rugged conditions for
|
64 |
+
men
|
65 |
+
sentences:
|
66 |
+
- 'Title: Carhartt Men''s Big & Tall Relaxed Fit Heavyweight Flannel Sherpa-Lined
|
67 |
+
Shirt Jacket, Brown, 3X-Large Descripion: ["This men''s Carhartt shirt jac blends
|
68 |
+
the comfort of a hoodie with the ruggedness of a jacket. Made from heavyweight
|
69 |
+
flannel with a plush sherpa lining and a relaxed fit. Features two outer pockets
|
70 |
+
plus an inner pocket on the chest. 8-ounce, 100% cotton ringspun flannel. Sherpa
|
71 |
+
fleece lining for warmth. Carhartt strong triple-stitched main seams. Relaxed
|
72 |
+
fit. Spread collar. Two-snap adjustable cuffs with extended plackets. Antique-finish
|
73 |
+
nickel snaps. Two chest pockets with flaps and snap closures #Interior chest pocket.
|
74 |
+
Replaces 104452. Imported"]'
|
75 |
+
- 'Title: Tommy Hilfiger Men''s Lightweight Active Water Resistant Hooded Rain Jacket
|
76 |
+
Descripion: [''Lightweight updated hooded rain slicker with red white and navy
|
77 |
+
center front contrast zipper tape.'']'
|
78 |
+
- 'Title: UGFashions Icy Hot Jacket Kurt Russell Death Proof Stuntman Mike Racing
|
79 |
+
Costume Silver Satin Jacket Descripion: ["Icy Hot Silver Race Driver Costume Silver
|
80 |
+
Satin Jacket Icy Hot Death Proof Stuntsman Mike Kurt Russell Silver Jacket This
|
81 |
+
Stuntman Mike Racing Jacket turned Kurt Russell into a Hollywood celebrity. It
|
82 |
+
is the Stuntman Mike jacket that Kurt Russell wore in his movie Death Proof. He
|
83 |
+
looked smart and stylish wearing this Death Proof Satin Jacket. Now you can buy
|
84 |
+
this silver jacket. Icy Hot Racing Costume Jacket has following features Item
|
85 |
+
Specifications: Manufactured from Satin material Front Zipper closure | icy hot
|
86 |
+
jacket Inside Viscose Lining | death proof jacket Shirt style collar | kurt russell
|
87 |
+
jacket Button Cuffs | stuntman mike satin jacket Patches at back and on Sleeves
|
88 |
+
| racing costume jacket Waist Side Pockets We have multiple resources for entire
|
89 |
+
operations including manufacturing, packaging and shipping to minimize the risk
|
90 |
+
for the item being late or defective. We accept returns/ exchanges are possible
|
91 |
+
within 30 day time period after delivery. Size chart is provided at the end in
|
92 |
+
images section so you can select the perfect size for your body and even if it
|
93 |
+
doesn''t fit, we are available 24/7 to guide you for further steps. QC is done
|
94 |
+
2-3 times to make sure that whatever item is being sent to the buyer gets delivered
|
95 |
+
in accurate and perfect condition"]'
|
96 |
+
- source_sentence: men's windbreaker with a lightweight design, weather-resistant
|
97 |
+
fabric, and adjustable features for comfort and convenience.
|
98 |
+
sentences:
|
99 |
+
- 'Title: Zafy Leather Geniune Leather Women Jacket Small Red Descripion: [''High-Quality
|
100 |
+
men Leather Jacket - The " Zafy Leather" is known for its leather quality. The
|
101 |
+
jackets are crafted by professional artisans so that it must be slim fit, stylish
|
102 |
+
and comfortable to wear. The color may differ slightly due to photography lights
|
103 |
+
or different screen resolution setting. The solid color you get from us will not
|
104 |
+
fade easily and built to last for years. Best Gift for her: Its soft touch makes
|
105 |
+
it the best choice as a gift on the occasion of Birthday Day, Christmas Gift and
|
106 |
+
Anniversary. Maintainance Tips: Clean leather jacket with little liquid cleaner
|
107 |
+
using soft cotton cloth. Do not wash with water or direct sunlight exposure may
|
108 |
+
damage color.'']'
|
109 |
+
- 'Title: Cosplay.fm Women''s Cosplay Costume Red Jacket with Hat Descripion: [''cosplay
|
110 |
+
outfit consists of a red jacket, pants, socks, belt, and gloves. Made with nice
|
111 |
+
materials, PU leather, cotton and polyester.Bulma costume will definitely make
|
112 |
+
you the most eye-catching in cosplay shows, parties, comic cons, stage performances,
|
113 |
+
etc.'']'
|
114 |
+
- 'Title: Columbia Men''s M Fkt Ii Windbreaker Jacket Descripion: ["Ultra light
|
115 |
+
and weather-repelling, this protective and packable windbreaker is a must for
|
116 |
+
running in wet, blustery weather. \u2028\u2028 You will be comfortably shielded
|
117 |
+
in this stain and water resistant windbreaker. It''s the perfect lightweight layer
|
118 |
+
and first line of defense to combat chilly winds and light drizzle. Its full length
|
119 |
+
zippered front allows you to dial in the protection on the fly, while a zip-closed
|
120 |
+
security pocket keeps essentials close by. Sleeves with elastic at the cuffs and
|
121 |
+
thumbholes keep hands and arms comfortable, while elastic at the hem and reflective
|
122 |
+
detail adds a touch of safety. This coat can pack down into its own pocket for
|
123 |
+
easy travel. Columbia offers this jacket in multiple colors and sizes. Active
|
124 |
+
Fit. To ensure the size you choose is right, utilize our sizing chart and the
|
125 |
+
following measurement instructions: For the sleeves, start at the center back
|
126 |
+
of your neck and measure across the shoulder and down to the sleeve. If you come
|
127 |
+
up with a partial number, round up to the next even number. For the chest, measure
|
128 |
+
at the fullest part of the chest, under the armpits and over the shoulder blades,
|
129 |
+
keeping the tape measure firm and level."]'
|
130 |
+
- source_sentence: women's waterproof jacket with a detachable hood, adjustable cuffs,
|
131 |
+
and multiple storage pockets.
|
132 |
+
sentences:
|
133 |
+
- 'Title: Camii Mia-Rain-Jackets-for-Women-Waterproof Hooded Jacket Drawstring Lightweight
|
134 |
+
Hiking Mountain Camping Descripion: ["Camii Mia is very known for its simplicity
|
135 |
+
and elegance in extremely well made and durable products. We have the desire that
|
136 |
+
makes the fashion art more efficient and easy going. That''s how we change the
|
137 |
+
world. We strive to make perfect blend of design, material and color. Hope you
|
138 |
+
will like our work. Camii Mia women''s 3 in 1 Rain jacket featuring detachable
|
139 |
+
hood with elastic drawstring, adjustable cuffs with velcro, 2 zippered slanted
|
140 |
+
hand pockests and 5 internal hand pocket. Windproof, durable and breathable fabric
|
141 |
+
and removable warm polar fleece linning could guarantees the best heat retention.
|
142 |
+
Keep your body from wind, rain and cold weather. Suitable for outdoor occasions
|
143 |
+
such as hiking, camping, climbing, traveling, skiing, snowboarding and other outdoor
|
144 |
+
sports. Size Measurement: Small -- Chest 43.3''''(110cm), Shoulder 16.5'''' ,
|
145 |
+
Sleeve 23.8'''', Length 25.6'''' Medium -- Chest 46.5''''(118cm), Shoulder 17.7'''',
|
146 |
+
Sleeve 25'''', Length 27.2'''' Large -- Chest 48.8''''(124cm), Shoulder 19.9'''',
|
147 |
+
Sleeve 25.8'''', Length 29.1'''' X-Large -- Chest 52''''(132cm), Shoulder 21.1'''',
|
148 |
+
Sleeve 27'''', Length 30.7'''' XX-Large -- Chest 53.5''''(136cm), Shoulder 21.7'''',
|
149 |
+
Sleeve 27'', Length 30.7'''' If you''re not sure about your size, please tell
|
150 |
+
us your weight, bust and height in lbs and inches. Let''s help you to make choice.
|
151 |
+
Thanks!"]'
|
152 |
+
- 'Title: Mountain Warehouse Womens Waterproof Ski Jacket - Slim Fit for Winter
|
153 |
+
Descripion: [''Get ready to face the elements in the Slalom Extreme Ski Jacket.
|
154 |
+
Fully waterproof with taped seams, the jacket is breathable and features RECCO
|
155 |
+
technology, a detachable snowskirt, inner stretch ski cuffs and underarm zips.
|
156 |
+
Ref: 031369'']'
|
157 |
+
- 'Title: The Classo Bomberium Black Bomber Men Leather Jacket Descripion: [''We
|
158 |
+
have introduce our products with high quality leather and Craftsmanship. We have
|
159 |
+
aim to provide excellent quality leather product to our valued customer in affordable
|
160 |
+
price with elegant Style. When you wear our outerwear feel comfortable. We make
|
161 |
+
our own leather and do stitching. It is soft Lambskin leather which has been created
|
162 |
+
by Famous tendery that product remarkable skin. We also make this item in faux
|
163 |
+
leather which is called Artificial Leather. We are offering both leather for leather
|
164 |
+
lovers and faux leather jacket who do not want to wear Animal Skin. Note" The
|
165 |
+
color and shade may vary from the picture you are seeing in the laptop due to
|
166 |
+
LED color and scheme.'']'
|
167 |
+
- source_sentence: men's winter jacket with a water-resistant exterior, thermal insulation,
|
168 |
+
and multiple pockets for storage.
|
169 |
+
sentences:
|
170 |
+
- 'Title: Bon Bebe Baby-boys Newborn Champ 3 Piece Velour Jacket And Pant Set Descripion:
|
171 |
+
[''Velour, button-front, hooded jacket with embroidered applique. 100 percent
|
172 |
+
cotton printed bodysuit with lap shoulder neck opening and 3-snap closure at inseam
|
173 |
+
for easy on-off dressing. Velour pant with elastic waistband.'']'
|
174 |
+
- 'Title: Yansguard Men''s Cycling Jerseys Tops Biking Shirts Short Sleeve Bike
|
175 |
+
Clothing Full Zipper Bicycle Jacket Gray, M (jersey008),J-G-M Descripion: [''100%
|
176 |
+
Polyester.Ultra-soft and UV protection.Full zipper in front, easy to wear and
|
177 |
+
take offHigh quality Moisture Wicking Fabric, quick-dry feature makes you feel
|
178 |
+
more comfortableWith 5 Pockets for safe storage, one of which has a zipper and
|
179 |
+
is waterproof!.There are reflective signs on the back of cycling jersey to enhance
|
180 |
+
the safety of cycling at night'']'
|
181 |
+
- 'Title: Columbia Men''s Grand Wall Jacket Descripion: [''Perfect for Fall and
|
182 |
+
Winter, the Columbia Men’s Grand Wall Jacket combines a classic outdoor look with
|
183 |
+
advanced technology to keep you warm and dry. Crafted from water resistant fabric,
|
184 |
+
packed with our down-like Thermarator insulation, and lined with our signature
|
185 |
+
Omni-HEAT reflective dots – this is your new go-to cold weather coat. Complete
|
186 |
+
with zippered hand pockets, a chest pocket for important essentials, and binding
|
187 |
+
at the cuffs — perfect to help block the cold, and lock your comfy body heat in.
|
188 |
+
This men’s winter jacket is offered in multiple sizes and colors. Extended sizing
|
189 |
+
available. Regular Fit. To ensure the size you choose is right, utilize our sizing
|
190 |
+
chart and the following measurement instructions: For the sleeves, start at the
|
191 |
+
center back of your neck and measure across the shoulder and down to the sleeve.
|
192 |
+
If you come up with a partial number, round up to the next even number. For the
|
193 |
+
chest, measure at the fullest part of the chest, under the armpits and over the
|
194 |
+
shoulder blades, keeping the tape measure firm and level.'']'
|
195 |
+
pipeline_tag: sentence-similarity
|
196 |
+
library_name: sentence-transformers
|
197 |
+
---
|
198 |
+
|
199 |
+
# SentenceTransformer based on sentence-transformers/all-mpnet-base-v2
|
200 |
+
|
201 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2). 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.
|
202 |
+
|
203 |
+
## Model Details
|
204 |
+
|
205 |
+
### Model Description
|
206 |
+
- **Model Type:** Sentence Transformer
|
207 |
+
- **Base model:** [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) <!-- at revision 9a3225965996d404b775526de6dbfe85d3368642 -->
|
208 |
+
- **Maximum Sequence Length:** 256 tokens
|
209 |
+
- **Output Dimensionality:** 768 tokens
|
210 |
+
- **Similarity Function:** Cosine Similarity
|
211 |
+
<!-- - **Training Dataset:** Unknown -->
|
212 |
+
<!-- - **Language:** Unknown -->
|
213 |
+
<!-- - **License:** Unknown -->
|
214 |
+
|
215 |
+
### Model Sources
|
216 |
+
|
217 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
218 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
219 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
220 |
+
|
221 |
+
### Full Model Architecture
|
222 |
+
|
223 |
+
```
|
224 |
+
SentenceTransformer(
|
225 |
+
(0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: MPNetModel
|
226 |
+
(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})
|
227 |
+
)
|
228 |
+
```
|
229 |
+
|
230 |
+
## Usage
|
231 |
+
|
232 |
+
### Direct Usage (Sentence Transformers)
|
233 |
+
|
234 |
+
First install the Sentence Transformers library:
|
235 |
+
|
236 |
+
```bash
|
237 |
+
pip install -U sentence-transformers
|
238 |
+
```
|
239 |
+
|
240 |
+
Then you can load this model and run inference.
|
241 |
+
```python
|
242 |
+
from sentence_transformers import SentenceTransformer
|
243 |
+
|
244 |
+
# Download from the 🤗 Hub
|
245 |
+
model = SentenceTransformer("knguyennguyen/mpnet_jacket4k_adjusted")
|
246 |
+
# Run inference
|
247 |
+
sentences = [
|
248 |
+
"men's winter jacket with a water-resistant exterior, thermal insulation, and multiple pockets for storage.",
|
249 |
+
"Title: Columbia Men's Grand Wall Jacket Descripion: ['Perfect for Fall and Winter, the Columbia Men’s Grand Wall Jacket combines a classic outdoor look with advanced technology to keep you warm and dry. Crafted from water resistant fabric, packed with our down-like Thermarator insulation, and lined with our signature Omni-HEAT reflective dots – this is your new go-to cold weather coat. Complete with zippered hand pockets, a chest pocket for important essentials, and binding at the cuffs — perfect to help block the cold, and lock your comfy body heat in. This men’s winter jacket is offered in multiple sizes and colors. Extended sizing available. Regular Fit. To ensure the size you choose is right, utilize our sizing chart and the following measurement instructions: For the sleeves, start at the center back of your neck and measure across the shoulder and down to the sleeve. If you come up with a partial number, round up to the next even number. For the chest, measure at the fullest part of the chest, under the armpits and over the shoulder blades, keeping the tape measure firm and level.']",
|
250 |
+
"Title: Yansguard Men's Cycling Jerseys Tops Biking Shirts Short Sleeve Bike Clothing Full Zipper Bicycle Jacket Gray, M (jersey008),J-G-M Descripion: ['100% Polyester.Ultra-soft and UV protection.Full zipper in front, easy to wear and take offHigh quality Moisture Wicking Fabric, quick-dry feature makes you feel more comfortableWith 5 Pockets for safe storage, one of which has a zipper and is waterproof!.There are reflective signs on the back of cycling jersey to enhance the safety of cycling at night']",
|
251 |
+
]
|
252 |
+
embeddings = model.encode(sentences)
|
253 |
+
print(embeddings.shape)
|
254 |
+
# [3, 768]
|
255 |
+
|
256 |
+
# Get the similarity scores for the embeddings
|
257 |
+
similarities = model.similarity(embeddings, embeddings)
|
258 |
+
print(similarities.shape)
|
259 |
+
# [3, 3]
|
260 |
+
```
|
261 |
+
|
262 |
+
<!--
|
263 |
+
### Direct Usage (Transformers)
|
264 |
+
|
265 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
266 |
+
|
267 |
+
</details>
|
268 |
+
-->
|
269 |
+
|
270 |
+
<!--
|
271 |
+
### Downstream Usage (Sentence Transformers)
|
272 |
+
|
273 |
+
You can finetune this model on your own dataset.
|
274 |
+
|
275 |
+
<details><summary>Click to expand</summary>
|
276 |
+
|
277 |
+
</details>
|
278 |
+
-->
|
279 |
+
|
280 |
+
<!--
|
281 |
+
### Out-of-Scope Use
|
282 |
+
|
283 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
284 |
+
-->
|
285 |
+
|
286 |
+
<!--
|
287 |
+
## Bias, Risks and Limitations
|
288 |
+
|
289 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
290 |
+
-->
|
291 |
+
|
292 |
+
<!--
|
293 |
+
### Recommendations
|
294 |
+
|
295 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
296 |
+
-->
|
297 |
+
|
298 |
+
## Training Details
|
299 |
+
|
300 |
+
### Training Dataset
|
301 |
+
|
302 |
+
#### Unnamed Dataset
|
303 |
+
|
304 |
+
|
305 |
+
* Size: 11,397 training samples
|
306 |
+
* Columns: <code>sentence_0</code> and <code>sentence_1</code>
|
307 |
+
* Approximate statistics based on the first 1000 samples:
|
308 |
+
| | sentence_0 | sentence_1 |
|
309 |
+
|:--------|:---------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
|
310 |
+
| type | string | string |
|
311 |
+
| details | <ul><li>min: 8 tokens</li><li>mean: 24.5 tokens</li><li>max: 59 tokens</li></ul> | <ul><li>min: 31 tokens</li><li>mean: 155.6 tokens</li><li>max: 256 tokens</li></ul> |
|
312 |
+
* Samples:
|
313 |
+
| sentence_0 | sentence_1 |
|
314 |
+
|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
315 |
+
| <code>a heated vest for staying warm in winter</code> | <code>Title: Yi-Create Heated Vest with Battery Pack Included,Unisex Heated Jacket for Men & Women,7.4v 7000mAh Quick Heated Closing Descripion: ['Yi-create Heated Vest with Battery Pack Included,Unisex Heated Jacket for Men & Women,7.4v 7000mAh Quick Heated Clothing with 3 Heating Levels,Lightweight USB Electric Heated Vest with 8 Heating Zone']</code> |
|
316 |
+
| <code>a mid-layer jacket for cold-weather sports and casual wear for men. men's mid-layer jacket with a combination of moisture-wicking panels and a warm, textured fabric.</code> | <code>Title: Spyder Active Sports Men's Bandit Half Zip Mid-Layer Jacket Descripion: ['An excellent first layer for its combo of wicking side panels and warm sweater knit bonded to fleece everywhere else, the half zip bandit is made for cold-weather sports, but is stylish enough for just sauntering around town.']</code> |
|
317 |
+
| <code>a down jacket for camping and hiking adventures</code> | <code>Title: Helly-Hansen Mens Verglas Icefall Down Jacket Descripion: ["An essential piece in anyone's pack; a lightweight down insulator, ready for your next adventure."]</code> |
|
318 |
+
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
|
319 |
+
```json
|
320 |
+
{
|
321 |
+
"scale": 20.0,
|
322 |
+
"similarity_fct": "cos_sim"
|
323 |
+
}
|
324 |
+
```
|
325 |
+
|
326 |
+
### Training Hyperparameters
|
327 |
+
#### Non-Default Hyperparameters
|
328 |
+
|
329 |
+
- `per_device_train_batch_size`: 128
|
330 |
+
- `per_device_eval_batch_size`: 128
|
331 |
+
- `num_train_epochs`: 5
|
332 |
+
- `multi_dataset_batch_sampler`: round_robin
|
333 |
+
|
334 |
+
#### All Hyperparameters
|
335 |
+
<details><summary>Click to expand</summary>
|
336 |
+
|
337 |
+
- `overwrite_output_dir`: False
|
338 |
+
- `do_predict`: False
|
339 |
+
- `eval_strategy`: no
|
340 |
+
- `prediction_loss_only`: True
|
341 |
+
- `per_device_train_batch_size`: 128
|
342 |
+
- `per_device_eval_batch_size`: 128
|
343 |
+
- `per_gpu_train_batch_size`: None
|
344 |
+
- `per_gpu_eval_batch_size`: None
|
345 |
+
- `gradient_accumulation_steps`: 1
|
346 |
+
- `eval_accumulation_steps`: None
|
347 |
+
- `torch_empty_cache_steps`: None
|
348 |
+
- `learning_rate`: 5e-05
|
349 |
+
- `weight_decay`: 0.0
|
350 |
+
- `adam_beta1`: 0.9
|
351 |
+
- `adam_beta2`: 0.999
|
352 |
+
- `adam_epsilon`: 1e-08
|
353 |
+
- `max_grad_norm`: 1
|
354 |
+
- `num_train_epochs`: 5
|
355 |
+
- `max_steps`: -1
|
356 |
+
- `lr_scheduler_type`: linear
|
357 |
+
- `lr_scheduler_kwargs`: {}
|
358 |
+
- `warmup_ratio`: 0.0
|
359 |
+
- `warmup_steps`: 0
|
360 |
+
- `log_level`: passive
|
361 |
+
- `log_level_replica`: warning
|
362 |
+
- `log_on_each_node`: True
|
363 |
+
- `logging_nan_inf_filter`: True
|
364 |
+
- `save_safetensors`: True
|
365 |
+
- `save_on_each_node`: False
|
366 |
+
- `save_only_model`: False
|
367 |
+
- `restore_callback_states_from_checkpoint`: False
|
368 |
+
- `no_cuda`: False
|
369 |
+
- `use_cpu`: False
|
370 |
+
- `use_mps_device`: False
|
371 |
+
- `seed`: 42
|
372 |
+
- `data_seed`: None
|
373 |
+
- `jit_mode_eval`: False
|
374 |
+
- `use_ipex`: False
|
375 |
+
- `bf16`: False
|
376 |
+
- `fp16`: False
|
377 |
+
- `fp16_opt_level`: O1
|
378 |
+
- `half_precision_backend`: auto
|
379 |
+
- `bf16_full_eval`: False
|
380 |
+
- `fp16_full_eval`: False
|
381 |
+
- `tf32`: None
|
382 |
+
- `local_rank`: 0
|
383 |
+
- `ddp_backend`: None
|
384 |
+
- `tpu_num_cores`: None
|
385 |
+
- `tpu_metrics_debug`: False
|
386 |
+
- `debug`: []
|
387 |
+
- `dataloader_drop_last`: False
|
388 |
+
- `dataloader_num_workers`: 0
|
389 |
+
- `dataloader_prefetch_factor`: None
|
390 |
+
- `past_index`: -1
|
391 |
+
- `disable_tqdm`: False
|
392 |
+
- `remove_unused_columns`: True
|
393 |
+
- `label_names`: None
|
394 |
+
- `load_best_model_at_end`: False
|
395 |
+
- `ignore_data_skip`: False
|
396 |
+
- `fsdp`: []
|
397 |
+
- `fsdp_min_num_params`: 0
|
398 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
399 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
400 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
401 |
+
- `deepspeed`: None
|
402 |
+
- `label_smoothing_factor`: 0.0
|
403 |
+
- `optim`: adamw_torch
|
404 |
+
- `optim_args`: None
|
405 |
+
- `adafactor`: False
|
406 |
+
- `group_by_length`: False
|
407 |
+
- `length_column_name`: length
|
408 |
+
- `ddp_find_unused_parameters`: None
|
409 |
+
- `ddp_bucket_cap_mb`: None
|
410 |
+
- `ddp_broadcast_buffers`: False
|
411 |
+
- `dataloader_pin_memory`: True
|
412 |
+
- `dataloader_persistent_workers`: False
|
413 |
+
- `skip_memory_metrics`: True
|
414 |
+
- `use_legacy_prediction_loop`: False
|
415 |
+
- `push_to_hub`: False
|
416 |
+
- `resume_from_checkpoint`: None
|
417 |
+
- `hub_model_id`: None
|
418 |
+
- `hub_strategy`: every_save
|
419 |
+
- `hub_private_repo`: False
|
420 |
+
- `hub_always_push`: False
|
421 |
+
- `gradient_checkpointing`: False
|
422 |
+
- `gradient_checkpointing_kwargs`: None
|
423 |
+
- `include_inputs_for_metrics`: False
|
424 |
+
- `eval_do_concat_batches`: True
|
425 |
+
- `fp16_backend`: auto
|
426 |
+
- `push_to_hub_model_id`: None
|
427 |
+
- `push_to_hub_organization`: None
|
428 |
+
- `mp_parameters`:
|
429 |
+
- `auto_find_batch_size`: False
|
430 |
+
- `full_determinism`: False
|
431 |
+
- `torchdynamo`: None
|
432 |
+
- `ray_scope`: last
|
433 |
+
- `ddp_timeout`: 1800
|
434 |
+
- `torch_compile`: False
|
435 |
+
- `torch_compile_backend`: None
|
436 |
+
- `torch_compile_mode`: None
|
437 |
+
- `dispatch_batches`: None
|
438 |
+
- `split_batches`: None
|
439 |
+
- `include_tokens_per_second`: False
|
440 |
+
- `include_num_input_tokens_seen`: False
|
441 |
+
- `neftune_noise_alpha`: None
|
442 |
+
- `optim_target_modules`: None
|
443 |
+
- `batch_eval_metrics`: False
|
444 |
+
- `eval_on_start`: False
|
445 |
+
- `use_liger_kernel`: False
|
446 |
+
- `eval_use_gather_object`: False
|
447 |
+
- `batch_sampler`: batch_sampler
|
448 |
+
- `multi_dataset_batch_sampler`: round_robin
|
449 |
+
|
450 |
+
</details>
|
451 |
+
|
452 |
+
### Framework Versions
|
453 |
+
- Python: 3.11.11
|
454 |
+
- Sentence Transformers: 3.1.1
|
455 |
+
- Transformers: 4.45.2
|
456 |
+
- PyTorch: 2.5.1+cu121
|
457 |
+
- Accelerate: 1.2.1
|
458 |
+
- Datasets: 3.2.0
|
459 |
+
- Tokenizers: 0.20.3
|
460 |
+
|
461 |
+
## Citation
|
462 |
+
|
463 |
+
### BibTeX
|
464 |
+
|
465 |
+
#### Sentence Transformers
|
466 |
+
```bibtex
|
467 |
+
@inproceedings{reimers-2019-sentence-bert,
|
468 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
469 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
470 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
471 |
+
month = "11",
|
472 |
+
year = "2019",
|
473 |
+
publisher = "Association for Computational Linguistics",
|
474 |
+
url = "https://arxiv.org/abs/1908.10084",
|
475 |
+
}
|
476 |
+
```
|
477 |
+
|
478 |
+
#### MultipleNegativesRankingLoss
|
479 |
+
```bibtex
|
480 |
+
@misc{henderson2017efficient,
|
481 |
+
title={Efficient Natural Language Response Suggestion for Smart Reply},
|
482 |
+
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},
|
483 |
+
year={2017},
|
484 |
+
eprint={1705.00652},
|
485 |
+
archivePrefix={arXiv},
|
486 |
+
primaryClass={cs.CL}
|
487 |
+
}
|
488 |
+
```
|
489 |
+
|
490 |
+
<!--
|
491 |
+
## Glossary
|
492 |
+
|
493 |
+
*Clearly define terms in order to be accessible across audiences.*
|
494 |
+
-->
|
495 |
+
|
496 |
+
<!--
|
497 |
+
## Model Card Authors
|
498 |
+
|
499 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
500 |
+
-->
|
501 |
+
|
502 |
+
<!--
|
503 |
+
## Model Card Contact
|
504 |
+
|
505 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
506 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "sentence-transformers/all-mpnet-base-v2",
|
3 |
+
"architectures": [
|
4 |
+
"MPNetModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-05,
|
15 |
+
"max_position_embeddings": 514,
|
16 |
+
"model_type": "mpnet",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 1,
|
20 |
+
"relative_attention_num_buckets": 32,
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.45.2",
|
23 |
+
"vocab_size": 30527
|
24 |
+
}
|
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": null
|
10 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf5cc5e3ccf5a0dafbe99c141f1472310d740bbc3672b89bd3284b2becabbfc2
|
3 |
+
size 437967672
|
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": 256,
|
3 |
+
"do_lower_case": false
|
4 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "[UNK]",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"104": {
|
36 |
+
"content": "[UNK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"30526": {
|
44 |
+
"content": "<mask>",
|
45 |
+
"lstrip": true,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
}
|
51 |
+
},
|
52 |
+
"bos_token": "<s>",
|
53 |
+
"clean_up_tokenization_spaces": false,
|
54 |
+
"cls_token": "<s>",
|
55 |
+
"do_lower_case": true,
|
56 |
+
"eos_token": "</s>",
|
57 |
+
"mask_token": "<mask>",
|
58 |
+
"max_length": 128,
|
59 |
+
"model_max_length": 256,
|
60 |
+
"pad_to_multiple_of": null,
|
61 |
+
"pad_token": "<pad>",
|
62 |
+
"pad_token_type_id": 0,
|
63 |
+
"padding_side": "right",
|
64 |
+
"sep_token": "</s>",
|
65 |
+
"stride": 0,
|
66 |
+
"strip_accents": null,
|
67 |
+
"tokenize_chinese_chars": true,
|
68 |
+
"tokenizer_class": "MPNetTokenizer",
|
69 |
+
"truncation_side": "right",
|
70 |
+
"truncation_strategy": "longest_first",
|
71 |
+
"unk_token": "[UNK]"
|
72 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|