guyhadad01 commited on
Commit
b41f660
·
verified ·
1 Parent(s): 1e71243

Training in progress, step 43, checkpoint

Browse files
.gitattributes CHANGED
@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ last-checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text
last-checkpoint/1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 1024,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": false,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": true,
9
+ "include_prompt": true
10
+ }
last-checkpoint/README.md ADDED
@@ -0,0 +1,564 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - sentence-transformers
4
+ - sentence-similarity
5
+ - feature-extraction
6
+ - dense
7
+ - generated_from_trainer
8
+ - dataset_size:21955
9
+ - loss:CachedMultipleNegativesRankingLoss
10
+ base_model: Qwen/Qwen3-Embedding-0.6B
11
+ widget:
12
+ - source_sentence: 'Title: Gold extatic Musk EDT 90ml'
13
+ sentences:
14
+ - 'Description: [''When you’re looking for soothing relief, reach for Aloe MSM Gel.
15
+ MSM stands for Methyl Sulfonyl Methane, an organic sulfur found in almost all
16
+ living organisms. In fact, sulfur is the third most abundant substance in our
17
+ body. The other main ingredient in Aloe MSM Gel is pure, stabilized Aloe Vera.
18
+ Aloe MSM Gel combines these two powerful ingredients with herbal extracts and
19
+ other select ingredients for soothing relief anytime. Try Aloe MSM Gel today!
20
+ DIRECTIONS: Apply liberally and massage into skin areas where needed. Should eye
21
+ contact occur, flush with water for several minutes. Repeat application as needed.'']
22
+
23
+ Clear, non-staining formula
24
+
25
+ For soothing relief anytime
26
+
27
+ Contains pure, stabilized Aloe Vera'
28
+ - 'Description: [''Edt spray 3 oz design house: balmain'']
29
+
30
+ Extatic Balmain Gold Musk By Balmain Edt Spray 3 Oz'
31
+ - 'Description: [''Euphoria is a heavenly and intoxicating perfume for the woman
32
+ who enjoys attention. Its original blend of sparkly and sweet ingredients is simply
33
+ irresistible. Persimmon and pomegranate open the scent with an uncommon kick.
34
+ The two fruits combine for a rich aroma of musky, sweet wine deepened by green
35
+ accords. Black orchid and lotus blossom provide clean, watery flower notes just
36
+ exotic enough to suggest the marvels of a faraway land. Violet, cream, amber,
37
+ and wood notes support the perfume with a milky, savory aroma. Made for the uncommon
38
+ woman, this perfume longs to be noticed.'']'
39
+ - source_sentence: 'Title: Nail Clippers for Thick Nails - Heavy Duty Stainless Steel
40
+ Fingernail Toenail Clipper for Tough Nails,Wide Jaw Extra Large Nail Cutter for
41
+ Thick Toenails for Seniors Men & Women,Curved Blades'
42
+ sentences:
43
+ - 'Description: [''Launched by the design house of Chanel in 2002, CHANEL CHANCE
44
+ by Chanel is classified as a flowery fragrance. This feminine scent posesses a
45
+ blend of: a refined blend of jasmine and citrus. It is recommended for daytime
46
+ wear.'']'
47
+ - 'Description: [''Medicated Treatment Conditioner'', ''🥇 Intense multi-functional
48
+ formula.🥈 Designed to penetrate the hair shaft to stop drying and add moisture.
49
+ 🥉 Also helps in the aid of minor scalp irritations and fungus.'']
50
+
51
+ ✅ 👩🏾 👩🏽‍🦰👩🏼 Works on all hair types
52
+
53
+ ✅ Formulated with Aloe
54
+
55
+ ✅ Works best when used with Kiti Kiti Medicated Treatment Shampoo
56
+
57
+ ✅ Help remove dry, flaking skin from scalp'
58
+ - 'Description: [''Are you still spending thousands of dollars a year for your thick
59
+ nail problems? Are you still complaining about traditional nail clippers for men
60
+ that are easily damaged?'', ''We recommend you to try the new professional nail
61
+ clippers of the DEJLIG brand.'', ''Toenail clippers for thick nails adopt a unique
62
+ lever design, and the blade of nail clippers for thick toenails can be opened
63
+ up to 16mm. Fingernail clippers for men can trim nails of any thickness and easily
64
+ cut our thick nails. Clipper pro nail cutters are very durable and sharp, saying
65
+ goodbye to the annoying thick nail problem.'', ''DEJLIG is an American brand dedicated
66
+ to producing high-quality large nail clippers for thick toenails.'', "Our heavy
67
+ duty nail clippers for thick nails have an elegant ergonomic design and have the
68
+ most durable and sharpest blades. Professional nail clippers for seniors made
69
+ of surgical grade stainless steel have outstanding performance and are today''s
70
+ masterpieces. She is one of the best nail clippers set for men on the market today. It''s
71
+ time to say goodbye to cheap and low-quality toenail clippers for thick toenails.",
72
+ ''Try our wide jaw toenail clippers now! When you trim your nails, they will provide
73
+ you with the smoothest and most enjoyable experience.'', ''【Gift Box Includes】'',
74
+ ''1 x Big Toenail Clippers 1 x Nail File1×Instructions'', ''【After-sales Service:
75
+ Lifetime Service】'', ''All heavy duty toenail clippers must pass strict quality
76
+ inspections before they can be sold. If you have any questions about our stainless
77
+ steel nail clippers, please go to the following path: "My Order"-"Contact Seller"
78
+ to contact us.'']
79
+
80
+ 【Professional Nail Clippers Set】- Toe nail clippers for thick toenails are designed
81
+ for various nail types and are suitable for professional occasions such as nail
82
+ salons, including men, women and seniors. This is also a great nail clipper kit
83
+ (including a nail clipper and a nail file), which can provide a relaxing and enjoyable
84
+ experience for heavy duty toenail clippers, nail cutters for seniors and travel
85
+ nail clippers. Large Toenail Clippers for Thick Toenails Are the Best Choice for
86
+ Gifts.
87
+
88
+ 【Sharp & Durable】- Toenail clippers for thick nails for seniors are made of high-quality
89
+ surgical grade stainless steel for rust and durability .The new sharp curved blade
90
+ adapts to the curvature of the nail and trims sharp pieces of corners precisely.
91
+ Nail clippers for thick toenails use a unique lever, which is very durable, ergonomic
92
+ and comfortable to use. Nail Clippers for Women Are Professional Cutting Tools
93
+ Manufactured According to The Highest Standards.
94
+
95
+ 【Ultra Wide Jaw Opening】- Professional toenail clippers use a unique lever design,
96
+ allowing the wide jaw blade to open up to 16mm, suitable for trimming nails of
97
+ any thickness. Ultra wide jaw opening and non-slip handle work perfectly together,
98
+ and nail clippers for men can reduce the pressure required to cut thick nails
99
+ or tough toenails. Fingernail clippers for women help us cut nails easily and
100
+ comfortably, so Large Nail Clippers for Thick Toenails Will Be Our Best Tool for
101
+ Trimming Nails.
102
+
103
+ 【Designed for Thick Nails】- Nail clippers for thick nails can easily trim nails
104
+ of various thicknesses, saving us strength and time. Sturdy and sharp curved blade
105
+ with double curved edges allows toenail clippers for thick toenails to trim nails
106
+ precisely without pain. Heavy duty nail clippers for thick nails effectively alleviate
107
+ tough nail problems caused by fungus, diabetes, and aging. Fingernail Clippers
108
+ for Men Are A Good Helper for Every Thick Nail Friend.
109
+
110
+ 【Lifetime Warranty】- We are very confident in the quality of our nail trimmer
111
+ for women and offer a leading lifetime replacement warranty to every customer
112
+ who buys thick toenail clippers. If you have any questions about our toenail clippers
113
+ for thick nails, please feel free to email us. Our US professional team will give
114
+ you the most satisfactory answer within 24 hours. Clipper Pro Nail Cutter Provide
115
+ Reliable Quality, So You Can Buy Stainless Steel Nail Clippers with More Confidence.'
116
+ - source_sentence: 'Title: Nail Art Brushes,Acrylic Nail Brush,Nail Art Brush,Acrylic
117
+ Brush Embossed Sable Nail Tools for Nail Salon Home Use,Nail Tools (#20)'
118
+ sentences:
119
+ - 'Description: [''Product Details: Weight: about 0.63-0.98 oz Material: alloy +
120
+ plastic + Kolinsky hair Color: Black Size: #8,10,12,14,16,18,20 Length: about
121
+ 17.2-18.5 cm Nail brushes soft, flexible bristles give the artist great control
122
+ over the product. Long-lasting and strong, it will not split or deform, the alloy
123
+ handle is easy to handle, has a very smooth surface, more durable than any type
124
+ of brush, both beautiful and practical. Nail acrylic brush is the perfect nail
125
+ art tool for professional salons and home DIY nail art, the more times you use
126
+ it, the smoother the result. Warm Tips: Please clean our nail brushes with a brush
127
+ before use. After the manicure, please clean the nail brush with Brush Liquid
128
+ Monomer. Wipe off as much water as possible with a paper towel and re-store. Proper
129
+ care and cleaning will extend the life of your nail brushes. Proper use and proper
130
+ care will ensure a longer life for your nail art brushes. Always keep air circulating
131
+ and in an upright position. The acrylic nail brushes need to breathe to prevent
132
+ bad stuff growth. Also, keep pinceles para acrilico out of direct sunlight. With
133
+ proper care, your acrylic brush will have a longer life.'']'
134
+ - 'Description: [''For carefree hair with time to spare start your day with Aussie
135
+ Total Miracle Collection 7N1 Shampoo. Packed with 7 benefits in 1 bottle it starts
136
+ by cleansing your tresses to reveal brilliant natural shine. The moisture-enriched
137
+ serum infusion protects your hair from dryness split ends and breakage. On top
138
+ of that this miraculous shampoo makes your hair more manageable by detangling
139
+ your strands. The result? Your hair is less prone to damage and breakage. Follow
140
+ with Aussie Total Miracle Collection 7N1 Conditioner and emerge from the shower
141
+ with a head full of silky smooth hair. Because around here we make Aussome hair
142
+ easy!'']'
143
+ - 'Description: [''EVA Hard Protective Travel Case Carrying Pouch Cover Bag for
144
+ John Frieda Salon Shape 1.5 Inch Hot Air Brush By Hermitshell'']
145
+
146
+ Hermitshell Hard Travel Storage Carrying Case Bag
147
+
148
+ Protect your favorite device from bumps dents and scratches
149
+
150
+ Made to fit John Frieda Salon Shape 1.5 Inch Hot Air Brush
151
+
152
+ Material:EVA ,Color: Black
153
+
154
+ For sale is case only (device and accessories are sold separately)'
155
+ - source_sentence: 'Title: Stand Electric Toothbrush Heads Case Holder for Braun Oral
156
+ B'
157
+ sentences:
158
+ - 'Description: [''3 bottles of ROSE WATER & IVY Shea & Vitamin E SHOWER GELS.'']'
159
+ - 'Description: [''Package Content: 1 x Toothbrush Stand (The toothbrush, brush
160
+ heads, and charger are not included in the package.)'']
161
+
162
+ A perfect solution to organize your toothbrush, brush heads and charger in one
163
+ stand.Hold up to 4 brush heads,2 Oral B electric toothbrush.and 1 charger, (Charging
164
+ port size is only suitable for original oral b charger),(The toothbrush, brush
165
+ heads, and charger are not included in the package)
166
+
167
+ It comes with a lid that can keep your brush heads safe and clean.the holder is
168
+ made of ABS,100% Environmental protection material,safe and durable
169
+
170
+ This fit right around the toothbrush charger perfectly. the cover keeps it extra
171
+ clean and Convenient storage
172
+
173
+ Size: 19.5 * 9.5 * 3.5cm, IRLIC Stand Electric Toothbrush Heads Case Holder for
174
+ Braun Oral B
175
+
176
+ Compatible with Braun Oral-B rechargeable toothbrush, Oral B Stages Power Kids-950,
177
+ Oral B Stages Power Kids, Oral B Vitality Sensitive Clean, Oral B Pro 600, Oral
178
+ B Pro 650, Oral B Pro 700 3d white, Oral B Pro 1000, Oral B Pro 2000, Oral B Pro
179
+ 3000, Oral B Pro 4000, Oral B Pro 5000, Oral B Pro 6000, Oral B Pro 7000, Oral
180
+ B Pro 8000, Oral B Genius 9000, Oral B Genius 10000n'
181
+ - 'Description: []
182
+
183
+ ❤️[Short Hairstyles]- Natural Grey Wigs for White Women, 12 inch Length Bob Wigs
184
+ for Women, Heat Resistant Fiber Synthetic Hair Replacement Wigs Colored Blond
185
+ Side Parting Bangs Trendy Haircuts Wig with Free Wig Cap x 1
186
+
187
+ ❤️[Hair Material]- Heat resistant hair tinsel that holds up to styling tools providing
188
+ a similar styling versatility as with human hair. The wig can also be customized
189
+ to suit your own individual look by cutting them or using a curling iron/hair
190
+ straightener. (Note: optimal temperature is 250-275 degrees, but going above 350
191
+ degrees is not recommended.)
192
+
193
+ ❤️[Occasions]- Fashionable and stylish short bob wig look natural, real like human
194
+ hair wig, very pretty, and feminine, soft touch. You can wear it for parties,
195
+ Halloween, cosplay, daily use, gift sending to friends and certain themed performances,
196
+ fashion and attractive, adding more charm and fun.
197
+
198
+ ❤️[Adjustable Size]- Cap size 20-22.5 inches,There are two adjustment straps inside
199
+ the wig, which can be intertwined to a fixed position to suit different head sizes.
200
+
201
+ ❤️[Worry-free After-sales]- We Are Committed To Providing Customers with Quality
202
+ Products and Attentive Services, Free Returns If You Don''t Like It or a Quality
203
+ Problem.'
204
+ - source_sentence: 'Title: Sinful Colors Finger Nail Polish Color Lacquer Set 16-Piece
205
+ Collection'
206
+ sentences:
207
+ - 'Description: []
208
+
209
+ Lot of 16 Random Sinful Colors Finger Nail Polish Color Lacquer All Different
210
+ Colors No Repeats
211
+
212
+ Images for reference only
213
+
214
+ Actual color/texture may vary from the image shown
215
+
216
+ Randomly pre-packed 16 nail polishes'
217
+ - 'Description: ["Adorox Red Horn Devil Woman''s Wig Demon Angel Halloween Costume
218
+ Prop Measures about: 27 Inches Length. Perfect for a Woman''s Devil Halloween
219
+ Costume. Sized for adults and teens. One Size fits most"]
220
+
221
+ Long fiery Red hair with Horns
222
+
223
+ Measures about: 27 Inches Length
224
+
225
+ 100% Polyester
226
+
227
+ Perfect for a Woman''s Devil Halloween Costume
228
+
229
+ Sized for adults and teens.'
230
+ - 'Description: [''Ovvio Oils All Natural Smooth Strength Plus Lip Balm For Chapped
231
+ Lips 0.5 oz (14.2 g)'']'
232
+ pipeline_tag: sentence-similarity
233
+ library_name: sentence-transformers
234
+ ---
235
+
236
+ # SentenceTransformer based on Qwen/Qwen3-Embedding-0.6B
237
+
238
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Qwen/Qwen3-Embedding-0.6B](https://huggingface.co/Qwen/Qwen3-Embedding-0.6B) on the amazon-reviews-2023 dataset. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
239
+
240
+ ## Model Details
241
+
242
+ ### Model Description
243
+ - **Model Type:** Sentence Transformer
244
+ - **Base model:** [Qwen/Qwen3-Embedding-0.6B](https://huggingface.co/Qwen/Qwen3-Embedding-0.6B) <!-- at revision c54f2e6e80b2d7b7de06f51cec4959f6b3e03418 -->
245
+ - **Maximum Sequence Length:** 512 tokens
246
+ - **Output Dimensionality:** 1024 dimensions
247
+ - **Similarity Function:** Cosine Similarity
248
+ - **Training Dataset:**
249
+ - amazon-reviews-2023
250
+ <!-- - **Language:** Unknown -->
251
+ <!-- - **License:** Unknown -->
252
+
253
+ ### Model Sources
254
+
255
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
256
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
257
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
258
+
259
+ ### Full Model Architecture
260
+
261
+ ```
262
+ SentenceTransformer(
263
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': 'Qwen3Model'})
264
+ (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': True, 'include_prompt': True})
265
+ (2): Normalize()
266
+ )
267
+ ```
268
+
269
+ ## Usage
270
+
271
+ ### Direct Usage (Sentence Transformers)
272
+
273
+ First install the Sentence Transformers library:
274
+
275
+ ```bash
276
+ pip install -U sentence-transformers
277
+ ```
278
+
279
+ Then you can load this model and run inference.
280
+ ```python
281
+ from sentence_transformers import SentenceTransformer
282
+
283
+ # Download from the 🤗 Hub
284
+ model = SentenceTransformer("guyhadad01/EncodeRec_600M_Beauty")
285
+ # Run inference
286
+ queries = [
287
+ "Title: Sinful Colors Finger Nail Polish Color Lacquer Set 16-Piece Collection",
288
+ ]
289
+ documents = [
290
+ 'Description: []\nLot of 16 Random Sinful Colors Finger Nail Polish Color Lacquer All Different Colors No Repeats\nImages for reference only\nActual color/texture may vary from the image shown\nRandomly pre-packed 16 nail polishes',
291
+ "Description: ['Ovvio Oils All Natural Smooth Strength Plus Lip Balm For Chapped Lips 0.5 oz (14.2 g)']",
292
+ 'Description: ["Adorox Red Horn Devil Woman\'s Wig Demon Angel Halloween Costume Prop Measures about: 27 Inches Length. Perfect for a Woman\'s Devil Halloween Costume. Sized for adults and teens. One Size fits most"]\nLong fiery Red hair with Horns\nMeasures about: 27 Inches Length\n100% Polyester\nPerfect for a Woman\'s Devil Halloween Costume\nSized for adults and teens.',
293
+ ]
294
+ query_embeddings = model.encode_query(queries)
295
+ document_embeddings = model.encode_document(documents)
296
+ print(query_embeddings.shape, document_embeddings.shape)
297
+ # [1, 1024] [3, 1024]
298
+
299
+ # Get the similarity scores for the embeddings
300
+ similarities = model.similarity(query_embeddings, document_embeddings)
301
+ print(similarities)
302
+ # tensor([[ 0.7898, -0.0228, -0.0027]])
303
+ ```
304
+
305
+ <!--
306
+ ### Direct Usage (Transformers)
307
+
308
+ <details><summary>Click to see the direct usage in Transformers</summary>
309
+
310
+ </details>
311
+ -->
312
+
313
+ <!--
314
+ ### Downstream Usage (Sentence Transformers)
315
+
316
+ You can finetune this model on your own dataset.
317
+
318
+ <details><summary>Click to expand</summary>
319
+
320
+ </details>
321
+ -->
322
+
323
+ <!--
324
+ ### Out-of-Scope Use
325
+
326
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
327
+ -->
328
+
329
+ <!--
330
+ ## Bias, Risks and Limitations
331
+
332
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
333
+ -->
334
+
335
+ <!--
336
+ ### Recommendations
337
+
338
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
339
+ -->
340
+
341
+ ## Training Details
342
+
343
+ ### Training Dataset
344
+
345
+ #### amazon-reviews-2023
346
+
347
+ * Dataset: amazon-reviews-2023
348
+ * Size: 21,955 training samples
349
+ * Columns: <code>title</code> and <code>description</code>
350
+ * Approximate statistics based on the first 1000 samples:
351
+ | | title | description |
352
+ |:--------|:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
353
+ | type | string | string |
354
+ | details | <ul><li>min: 6 tokens</li><li>mean: 29.97 tokens</li><li>max: 114 tokens</li></ul> | <ul><li>min: 15 tokens</li><li>mean: 197.11 tokens</li><li>max: 512 tokens</li></ul> |
355
+ * Samples:
356
+ | title | description |
357
+ |:--------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
358
+ | <code>Title: Precision Plunger Bars for Cartridge Grips – 93mm – Bag of 10 Plungers</code> | <code>Description: ['The Precision Plunger Bars are designed to work seamlessly with the\xa0Precision Disposable 1. 25" Contoured Soft Cartridge Grips\xa0and the\xa0Precision Disposable 1" Textured Soft Cartridge Grips\xa0to drive cartridge needles with vice style or standard tattoo machine setups. These plunger bars are manufactured from 304 Stainless Steel and feature a brass tip. The plungers are sold in a bag of ten in your choice of 88mm, 93mm, or 98mm length.']<br>Material: 304 Stainless Steel; Brass tip<br>Lengths Available: 88mm, 93mm, 98mm<br>Accepts cartridge needles with vice style tattoo machines<br>Works perfectly with Precision Disposable Soft Cartridge Grips<br>Price per one bag of 10 plungers</code> |
359
+ | <code>Title: Lurrose 100Pcs Full Cover Fake Toenails Artificial Transparent Nail Tips Nail Art for DIY</code> | <code>Description: ['Description', 'The false toenails are durable with perfect length. You have the option to wear them long or clip them short, easy to trim and file them to in any length and shape you like. Plus, ABS is kind of green enviromental material, and makes the nails durable, breathable, light even no pressure on your own toenails. Fit well to your natural toenails. Non toxic, no smell, no harm to your health.', 'Feature', '- Color: As Shown.- Material: ABS.- Size: 14.3 x 7.2 x 1cm.', 'Package Including', '100 x Pieces fake toenails']<br>The false toenails are durable with perfect length. You have the option to wear them long or clip them short, easy to trim and file them to in any length and shape you like.<br>ABS is kind of green enviromental material, and makes the nails durable, breathable, light even no pressure on your own nails.<br>Fit well to your natural toenails. Non toxic, no smell, no harm to your health.<br>Wonderful as gift for girlfriend, family and friends.<br>The easiest and mo...</code> |
360
+ | <code>Title: Gold extatic Musk EDT 90ml</code> | <code>Description: ['Edt spray 3 oz design house: balmain']<br>Extatic Balmain Gold Musk By Balmain Edt Spray 3 Oz</code> |
361
+ * Loss: [<code>CachedMultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedmultiplenegativesrankingloss) with these parameters:
362
+ ```json
363
+ {
364
+ "scale": 20.0,
365
+ "similarity_fct": "cos_sim",
366
+ "mini_batch_size": 8,
367
+ "gather_across_devices": false
368
+ }
369
+ ```
370
+
371
+ ### Training Hyperparameters
372
+ #### Non-Default Hyperparameters
373
+
374
+ - `per_device_train_batch_size`: 512
375
+ - `num_train_epochs`: 1
376
+ - `warmup_ratio`: 0.1
377
+ - `bf16`: True
378
+ - `push_to_hub`: True
379
+ - `hub_model_id`: guyhadad01/EncodeRec_600M_Beauty
380
+ - `hub_strategy`: checkpoint
381
+ - `prompts`: Instruct: Given a web search query, retrieve relevant passages that answer the query
382
+ Query:
383
+
384
+ #### All Hyperparameters
385
+ <details><summary>Click to expand</summary>
386
+
387
+ - `overwrite_output_dir`: False
388
+ - `do_predict`: False
389
+ - `eval_strategy`: no
390
+ - `prediction_loss_only`: True
391
+ - `per_device_train_batch_size`: 512
392
+ - `per_device_eval_batch_size`: 8
393
+ - `per_gpu_train_batch_size`: None
394
+ - `per_gpu_eval_batch_size`: None
395
+ - `gradient_accumulation_steps`: 1
396
+ - `eval_accumulation_steps`: None
397
+ - `torch_empty_cache_steps`: None
398
+ - `learning_rate`: 5e-05
399
+ - `weight_decay`: 0.0
400
+ - `adam_beta1`: 0.9
401
+ - `adam_beta2`: 0.999
402
+ - `adam_epsilon`: 1e-08
403
+ - `max_grad_norm`: 1.0
404
+ - `num_train_epochs`: 1
405
+ - `max_steps`: -1
406
+ - `lr_scheduler_type`: linear
407
+ - `lr_scheduler_kwargs`: {}
408
+ - `warmup_ratio`: 0.1
409
+ - `warmup_steps`: 0
410
+ - `log_level`: passive
411
+ - `log_level_replica`: warning
412
+ - `log_on_each_node`: True
413
+ - `logging_nan_inf_filter`: True
414
+ - `save_safetensors`: True
415
+ - `save_on_each_node`: False
416
+ - `save_only_model`: False
417
+ - `restore_callback_states_from_checkpoint`: False
418
+ - `no_cuda`: False
419
+ - `use_cpu`: False
420
+ - `use_mps_device`: False
421
+ - `seed`: 42
422
+ - `data_seed`: None
423
+ - `jit_mode_eval`: False
424
+ - `bf16`: True
425
+ - `fp16`: False
426
+ - `fp16_opt_level`: O1
427
+ - `half_precision_backend`: auto
428
+ - `bf16_full_eval`: False
429
+ - `fp16_full_eval`: False
430
+ - `tf32`: None
431
+ - `local_rank`: 0
432
+ - `ddp_backend`: None
433
+ - `tpu_num_cores`: None
434
+ - `tpu_metrics_debug`: False
435
+ - `debug`: []
436
+ - `dataloader_drop_last`: False
437
+ - `dataloader_num_workers`: 0
438
+ - `dataloader_prefetch_factor`: None
439
+ - `past_index`: -1
440
+ - `disable_tqdm`: False
441
+ - `remove_unused_columns`: True
442
+ - `label_names`: None
443
+ - `load_best_model_at_end`: False
444
+ - `ignore_data_skip`: False
445
+ - `fsdp`: []
446
+ - `fsdp_min_num_params`: 0
447
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
448
+ - `fsdp_transformer_layer_cls_to_wrap`: None
449
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
450
+ - `parallelism_config`: None
451
+ - `deepspeed`: None
452
+ - `label_smoothing_factor`: 0.0
453
+ - `optim`: adamw_torch
454
+ - `optim_args`: None
455
+ - `adafactor`: False
456
+ - `group_by_length`: False
457
+ - `length_column_name`: length
458
+ - `project`: huggingface
459
+ - `trackio_space_id`: trackio
460
+ - `ddp_find_unused_parameters`: None
461
+ - `ddp_bucket_cap_mb`: None
462
+ - `ddp_broadcast_buffers`: False
463
+ - `dataloader_pin_memory`: True
464
+ - `dataloader_persistent_workers`: False
465
+ - `skip_memory_metrics`: True
466
+ - `use_legacy_prediction_loop`: False
467
+ - `push_to_hub`: True
468
+ - `resume_from_checkpoint`: None
469
+ - `hub_model_id`: guyhadad01/EncodeRec_600M_Beauty
470
+ - `hub_strategy`: checkpoint
471
+ - `hub_private_repo`: None
472
+ - `hub_always_push`: False
473
+ - `hub_revision`: None
474
+ - `gradient_checkpointing`: False
475
+ - `gradient_checkpointing_kwargs`: None
476
+ - `include_inputs_for_metrics`: False
477
+ - `include_for_metrics`: []
478
+ - `eval_do_concat_batches`: True
479
+ - `fp16_backend`: auto
480
+ - `push_to_hub_model_id`: None
481
+ - `push_to_hub_organization`: None
482
+ - `mp_parameters`:
483
+ - `auto_find_batch_size`: False
484
+ - `full_determinism`: False
485
+ - `torchdynamo`: None
486
+ - `ray_scope`: last
487
+ - `ddp_timeout`: 1800
488
+ - `torch_compile`: False
489
+ - `torch_compile_backend`: None
490
+ - `torch_compile_mode`: None
491
+ - `include_tokens_per_second`: False
492
+ - `include_num_input_tokens_seen`: no
493
+ - `neftune_noise_alpha`: None
494
+ - `optim_target_modules`: None
495
+ - `batch_eval_metrics`: False
496
+ - `eval_on_start`: False
497
+ - `use_liger_kernel`: False
498
+ - `liger_kernel_config`: None
499
+ - `eval_use_gather_object`: False
500
+ - `average_tokens_across_devices`: True
501
+ - `prompts`: Instruct: Given a web search query, retrieve relevant passages that answer the query
502
+ Query:
503
+ - `batch_sampler`: batch_sampler
504
+ - `multi_dataset_batch_sampler`: proportional
505
+ - `router_mapping`: {}
506
+ - `learning_rate_mapping`: {}
507
+
508
+ </details>
509
+
510
+ ### Framework Versions
511
+ - Python: 3.12.11
512
+ - Sentence Transformers: 5.1.0
513
+ - Transformers: 4.57.0
514
+ - PyTorch: 2.7.1+cu126
515
+ - Accelerate: 1.10.0
516
+ - Datasets: 3.6.0
517
+ - Tokenizers: 0.22.1
518
+
519
+ ## Citation
520
+
521
+ ### BibTeX
522
+
523
+ #### Sentence Transformers
524
+ ```bibtex
525
+ @inproceedings{reimers-2019-sentence-bert,
526
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
527
+ author = "Reimers, Nils and Gurevych, Iryna",
528
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
529
+ month = "11",
530
+ year = "2019",
531
+ publisher = "Association for Computational Linguistics",
532
+ url = "https://arxiv.org/abs/1908.10084",
533
+ }
534
+ ```
535
+
536
+ #### CachedMultipleNegativesRankingLoss
537
+ ```bibtex
538
+ @misc{gao2021scaling,
539
+ title={Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup},
540
+ author={Luyu Gao and Yunyi Zhang and Jiawei Han and Jamie Callan},
541
+ year={2021},
542
+ eprint={2101.06983},
543
+ archivePrefix={arXiv},
544
+ primaryClass={cs.LG}
545
+ }
546
+ ```
547
+
548
+ <!--
549
+ ## Glossary
550
+
551
+ *Clearly define terms in order to be accessible across audiences.*
552
+ -->
553
+
554
+ <!--
555
+ ## Model Card Authors
556
+
557
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
558
+ -->
559
+
560
+ <!--
561
+ ## Model Card Contact
562
+
563
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
564
+ -->
last-checkpoint/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
last-checkpoint/chat_template.jinja ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
27
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
28
+ {%- elif message.role == "assistant" %}
29
+ {%- set content = message.content %}
30
+ {%- set reasoning_content = '' %}
31
+ {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
32
+ {%- set reasoning_content = message.reasoning_content %}
33
+ {%- else %}
34
+ {%- if '</think>' in message.content %}
35
+ {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
36
+ {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
37
+ {%- endif %}
38
+ {%- endif %}
39
+ {%- if loop.index0 > ns.last_query_index %}
40
+ {%- if loop.last or (not loop.last and reasoning_content) %}
41
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
42
+ {%- else %}
43
+ {{- '<|im_start|>' + message.role + '\n' + content }}
44
+ {%- endif %}
45
+ {%- else %}
46
+ {{- '<|im_start|>' + message.role + '\n' + content }}
47
+ {%- endif %}
48
+ {%- if message.tool_calls %}
49
+ {%- for tool_call in message.tool_calls %}
50
+ {%- if (loop.first and content) or (not loop.first) %}
51
+ {{- '\n' }}
52
+ {%- endif %}
53
+ {%- if tool_call.function %}
54
+ {%- set tool_call = tool_call.function %}
55
+ {%- endif %}
56
+ {{- '<tool_call>\n{"name": "' }}
57
+ {{- tool_call.name }}
58
+ {{- '", "arguments": ' }}
59
+ {%- if tool_call.arguments is string %}
60
+ {{- tool_call.arguments }}
61
+ {%- else %}
62
+ {{- tool_call.arguments | tojson }}
63
+ {%- endif %}
64
+ {{- '}\n</tool_call>' }}
65
+ {%- endfor %}
66
+ {%- endif %}
67
+ {{- '<|im_end|>\n' }}
68
+ {%- elif message.role == "tool" %}
69
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
70
+ {{- '<|im_start|>user' }}
71
+ {%- endif %}
72
+ {{- '\n<tool_response>\n' }}
73
+ {{- message.content }}
74
+ {{- '\n</tool_response>' }}
75
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
76
+ {{- '<|im_end|>\n' }}
77
+ {%- endif %}
78
+ {%- endif %}
79
+ {%- endfor %}
80
+ {%- if add_generation_prompt %}
81
+ {{- '<|im_start|>assistant\n' }}
82
+ {%- if enable_thinking is defined and enable_thinking is false %}
83
+ {{- '<think>\n\n</think>\n\n' }}
84
+ {%- endif %}
85
+ {%- endif %}
last-checkpoint/config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3Model"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "dtype": "float32",
9
+ "eos_token_id": 151643,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_types": [
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention"
44
+ ],
45
+ "max_position_embeddings": 32768,
46
+ "max_window_layers": 28,
47
+ "model_type": "qwen3",
48
+ "num_attention_heads": 16,
49
+ "num_hidden_layers": 28,
50
+ "num_key_value_heads": 8,
51
+ "rms_norm_eps": 1e-06,
52
+ "rope_scaling": null,
53
+ "rope_theta": 1000000,
54
+ "sliding_window": null,
55
+ "tie_word_embeddings": true,
56
+ "transformers_version": "4.57.0",
57
+ "use_cache": true,
58
+ "use_sliding_window": false,
59
+ "vocab_size": 151669
60
+ }
last-checkpoint/config_sentence_transformers.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "prompts": {
3
+ "query": "Instruct: Given a web search query, retrieve relevant passages that answer the query\nQuery:",
4
+ "document": ""
5
+ },
6
+ "default_prompt_name": null,
7
+ "similarity_fn_name": "cosine",
8
+ "model_type": "SentenceTransformer",
9
+ "__version__": {
10
+ "sentence_transformers": "5.1.0",
11
+ "transformers": "4.57.0",
12
+ "pytorch": "2.7.1+cu126"
13
+ }
14
+ }
last-checkpoint/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:634d9cd269fe0d583a546cd77180b2ac581442abc3157067fdc0383e98b38aee
3
+ size 2383139480
last-checkpoint/modules.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ },
14
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_Normalize",
18
+ "type": "sentence_transformers.models.Normalize"
19
+ }
20
+ ]
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df87da3cebba22cacef885c6056555a0042bb358208399b555c8c2f46954598a
3
+ size 4766477779
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:866c0d16e0ba412369309f8c0cbcb2a24695a6a2921557f033b691f2cb5b2dd8
3
+ size 14645
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc97c427c4a1a55e7821fe5b53aa4d6490c1ab3a4c5ef79e3eadb4afd22c88ce
3
+ size 1465
last-checkpoint/sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 512,
3
+ "do_lower_case": false
4
+ }
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
last-checkpoint/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c87c38db060bafb0122019c0c749ec1eb1ae510dae43c93f0042ec51099942e8
3
+ size 11423971
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 131072,
235
+ "pad_token": "<|endoftext|>",
236
+ "split_special_tokens": false,
237
+ "tokenizer_class": "Qwen2Tokenizer",
238
+ "unk_token": null
239
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 43,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [],
12
+ "logging_steps": 50,
13
+ "max_steps": 43,
14
+ "num_input_tokens_seen": 0,
15
+ "num_train_epochs": 1,
16
+ "save_steps": 200,
17
+ "stateful_callbacks": {
18
+ "TrainerControl": {
19
+ "args": {
20
+ "should_epoch_stop": false,
21
+ "should_evaluate": false,
22
+ "should_log": false,
23
+ "should_save": true,
24
+ "should_training_stop": true
25
+ },
26
+ "attributes": {}
27
+ }
28
+ },
29
+ "total_flos": 0.0,
30
+ "train_batch_size": 512,
31
+ "trial_name": null,
32
+ "trial_params": null
33
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b399764abfbe075f6d000718b12ff8e0f9afe70f5d9ff48947a3a3a2d8fa976
3
+ size 6289
last-checkpoint/vocab.json ADDED
The diff for this file is too large to render. See raw diff