knguyennguyen commited on
Commit
3b198cd
·
verified ·
1 Parent(s): 010f814

Add new SentenceTransformer model.

Browse files
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