svystun-taras commited on
Commit
75a7def
1 Parent(s): 32524d3

Add SetFit model

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
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
+ }
README.md ADDED
@@ -0,0 +1,323 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: setfit
3
+ tags:
4
+ - setfit
5
+ - sentence-transformers
6
+ - text-classification
7
+ - generated_from_setfit_trainer
8
+ datasets:
9
+ - CabraVC/vector_dataset_stratified_ttv_split_2023-12-05_21-07
10
+ metrics:
11
+ - accuracy
12
+ widget:
13
+ - text: "flow or estimates of sales proceeds valuation methodologies. The ability\
14
+ \ to accurately predict future cash flows, especially in developing and emerging\
15
+ \ markets, may impact the determination of fair value. \n\nIn the event the fair\
16
+ \ value of an investment declines below our cost basis, management is required\
17
+ \ to determine if the decline in fair value is other than temporary. If management\
18
+ \ determines the decline is other than temporary, an impairment charge is recorded.\
19
+ \ Management's assessment as to the nature of a decline in fair value is based\
20
+ \ on, among other things, the length of time and the extent to which the market\
21
+ \ value has been less than our cost basis, the financial condition and near-term\
22
+ \ prospects of the issuer, and our intent and ability to retain the investment\
23
+ \ in the issuer for a period of time sufficient to allow for any anticipated recovery\
24
+ \ in market value. \n\nAs of December 31, 2009, the Company had several investments\
25
+ \ classified as available-for-sale securities in which our cost basis had exceeded\
26
+ \ the fair value of the investment. Unrealized gains and losses on available-for-sale\
27
+ \ securities, as of December 31, 2009, were approximately $176 million and $21\
28
+ \ million, respectively. Management assessed each individual investment with unrealized\
29
+ \ losses to determine if the decline in fair value was other than temporary. Based\
30
+ \ on these assessments, management determined that the decline in fair value of\
31
+ \ each of these investments was temporary in nature. We will continue to monitor\
32
+ \ these investments in future periods. Refer to Note 2 of Notes to Consolidated\
33
+ \ Financial Statements. \n\nDuring the first quarter of 2009, the Company recorded\
34
+ \ a charge of approximately $27 million in other income\n\n(loss) — net as a result\
35
+ \ of an other-than-temporary decline in the fair value of a cost method investment.\
36
+ \ As of December 31, 2008, the estimated fair value of this investment approximated\
37
+ \ the Company's carrying value in the investment. However, during the first quarter\
38
+ \ of 2009, the Company was informed by the investee of its intent to reorganize\
39
+ \ its capital structure in 2009, which would result in the Company's shares in\
40
+ \ the investee being canceled. As a result, the Company determined that the decline\
41
+ \ in fair value of this cost method investment was other than temporary. This\
42
+ \ impairment charge impacted the Corporate operating segment. Refer to the heading\
43
+ \ \"Operations Review — Other Income (Loss) — Net,\" and Note 13 and Note 14 of\
44
+ \ Notes to Consolidated Financial Statements. \n\nAs of December 31, 2008, the\
45
+ \ Company had several investments classified as available-for-sale securities\
46
+ \ in which our cost basis exceeded the fair value of the investment, each of which\
47
+ \ initially occurred between the end of the second quarter and the beginning of\
48
+ \ the third quarter of 2008. Management assessed each individual investment to\
49
+ \ determine if the decline in fair value was other than temporary. Based on these\
50
+ \ assessments, management determined that the decline in fair value of each investment\
51
+ \ was other than temporary based on a number of factors, including, but not limited\
52
+ \ to, uncertainty regarding our intent to hold certain of these investments for\
53
+ \ a period of time that"
54
+ - text: "inflation, political climate, local and national laws and regulations, foreign\
55
+ \ currency exchange fluctuations, fuel prices and weather patterns. \n\nOur Objective\
56
+ \ \n\nOur objective is to use our formidable assets — our brands, financial strength,\
57
+ \ unrivaled distribution system, global reach, and the talent and strong commitment\
58
+ \ of our management and associates — to achieve long-term sustainable growth.\
59
+ \ Our vision for sustainable growth includes the following: \n\nPeople:Beingagreatplacetoworkwherepeopleareinspiredtobethebesttheycan\
60
+ \ be. \n\nPortfolio:Bringingtotheworldaportfolioofbeveragebrandsthatanticipatesandsatisfiespeople'sdesiresand\
61
+ \ needs. \n\nPartners:Nurturingawinningnetworkofpartnersandbuildingmutual loyalty.\
62
+ \ \n\nPlanet:Beingaresponsibleglobalcitizenthatmakesa difference. \n\nProfit:Maximizingreturntoshareownerswhilebeingmindfulofouroverall\
63
+ \ responsibilities. \n\nProductivity:Managingourpeople,timeandmoneyforgreatest\
64
+ \ effectiveness. \n\nStrategic Priorities \n\nWe have four strategic priorities\
65
+ \ designed to create long-term sustainable growth for our Company and the Coca-Cola\
66
+ \ system and value for our shareowners. These strategic priorities are driving\
67
+ \ global beverage leadership; accelerating innovation; leveraging our balanced\
68
+ \ geographic portfolio; and leading the Coca-Cola system for growth. To enable\
69
+ \ the entire Coca-Cola system so that we can deliver on these strategic priorities,\
70
+ \ we must further enhance our core capabilities of consumer marketing; commercial\
71
+ \ leadership; franchise leadership; and bottling and distribution operations.\
72
+ \ \n\nCore Capabilities \n\nConsumer Marketing \n\nMarketing investments are designed\
73
+ \ to enhance consumer awareness of, and increase consumer preference for, our\
74
+ \ brands. This produces long-term growth in unit case volume, per capita consumption\
75
+ \ and our share of worldwide nonalcoholic beverage sales. Through our relationships\
76
+ \ with our bottling partners and those who sell our products in the marketplace,\
77
+ \ we create and implement integrated marketing programs, both globally and locally,\
78
+ \ that are designed to heighten consumer awareness of and product appeal for our\
79
+ \ brands. In developing a strategy for a Company brand, we conduct product and\
80
+ \ packaging research, establish brand positioning, develop precise consumer communications\
81
+ \ and solicit consumer feedback. Our integrated marketing activities include,\
82
+ \ but are not limited to, advertising, point-of-sale merchandising and sales promotions.\
83
+ \ \n\nWe have disciplined marketing strategies that focus on driving volume in\
84
+ \ emerging markets, increasing our brand value in developing markets and growing\
85
+ \ profit in our developed markets. In emerging markets, we are investing in infrastructure\
86
+ \ programs that drive volume through increased access to consumers. In developing\
87
+ \ markets, where consumer access has largely been established, our focus is on\
88
+ \ differentiating our brands. In our developed markets, we continue to invest\
89
+ \ in brands and infrastructure programs, but at a slower rate than revenue growth.\
90
+ \ \n\nWe are focused on affordability and ensuring we are communicating the appropriate\
91
+ \ message based on the current economic environment. \n\nCommercial Leadership\
92
+ \ \n\nThe Coca-Cola system has millions of customers"
93
+ - text: "to 2005, led by double-digit growth in China, Russia and Turkey, partially\
94
+ \ offset by a 3 percent decline in Japan. The increase in unit case volume in\
95
+ \ China was led by significant growth in both sparkling and still beverages. The\
96
+ \ unit case volume growth in Russia and Turkey was the result of improving macroeconomic\
97
+ \ trends, strong bottler execution and successful marketing programs. Unit case\
98
+ \ volume in Russia also benefited from the full-year impact of the joint acquisition\
99
+ \ of Multon, compared to a partial year in 2005. The Company and Coca-Cola HBC\
100
+ \ jointly acquired Multon, a Russian juice company, in April 2005. The decrease\
101
+ \ in unit case volume in Japan was primarily due to weakness across core brands\
102
+ \ including Trademark Coca-Cola, Georgia Coffee and our green tea brands. However,\
103
+ \ results in Japan gradually improved during 2006 and position Japan for growth\
104
+ \ in 2007. \n\nUnit case volume for Bottling Investments increased 16 percent\
105
+ \ in 2006 versus 2005, primarily due to the acquisition of Kerry Beverages Limited,\
106
+ \ which was subsequently renamed Coca-Cola China Industries Limited (\"CCCIL\"\
107
+ ), and the acquisitions of TJC Holdings (Pty) Ltd., a South African bottling company\
108
+ \ (\"TJC\"), and Apollinaris. The Company intends to sell a portion of its investment\
109
+ \ in TJC to Black Economic Empowerment entities at a future date. Unit case volume\
110
+ \ for Bottling Investments also increased due to the consolidation of Brucephil,\
111
+ \ Inc. (\"Brucephil\"), the parent company of The Philadelphia Coca-Cola Bottling\
112
+ \ Company. In the third quarter of 2006, our Company signed agreements with J.\
113
+ \ Bruce Llewellyn and Brucephil for the potential purchase of the remaining shares\
114
+ \ of Brucephil not currently owned by the Company. The agreements provide for\
115
+ \ the Company's purchase of the shares upon the election of Mr. Llewellyn or the\
116
+ \ election of the Company. Based on the terms of these agreements, the Company\
117
+ \ concluded that it must consolidate Brucephil under Interpretation No. 46(R).\
118
+ \ Brucephil's financial statements were consolidated effective September 29, 2006.\
119
+ \ The acquisition of the German bottling company Bremer Erfrischungsgetraenke\
120
+ \ GmbH (\"Bremer\") during the third quarter of 2005 also contributed to unit\
121
+ \ case volume increases in 2006, reflecting the impact of full-year unit case\
122
+ \ volume in 2006 for Bremer compared to a partial year in 2005. The unit case\
123
+ \ volume increase was partially offset by a decline in India. \n\nIn Africa, unit\
124
+ \ case volume increased 6 percent in 2005 compared to 2004. This increase was\
125
+ \ driven by growth in core sparkling beverages as well as still beverages across\
126
+ \ all divisions in this operating segment. \n\nIn East, South Asia and Pacific\
127
+ \ Rim, unit case volume decreased 4 percent in 2005 compared to 2004, primarily\
128
+ \ due to declines in India and the Philippines. The decline in India was related\
129
+ \ to the impact of price increases to cover rising raw material and distribution\
130
+ \ costs and the lingering effects of the 2003 pesticide allegations. The decline\
131
+ \ in the Philippines was primarily related to affordability and availability issues.\
132
+ \ \n\nUnit case volume in the European Union was even in 2005 versus 2004, primarily\
133
+ \ due to strong growth in Spain and Central Europe"
134
+ pipeline_tag: text-classification
135
+ inference: true
136
+ model-index:
137
+ - name: SetFit
138
+ results:
139
+ - task:
140
+ type: text-classification
141
+ name: Text Classification
142
+ dataset:
143
+ name: CabraVC/vector_dataset_stratified_ttv_split_2023-12-05_21-07
144
+ type: CabraVC/vector_dataset_stratified_ttv_split_2023-12-05_21-07
145
+ split: test
146
+ metrics:
147
+ - type: accuracy
148
+ value: 0.3333333333333333
149
+ name: Accuracy
150
+ ---
151
+
152
+ # SetFit
153
+
154
+ This is a [SetFit](https://github.com/huggingface/setfit) model trained on the [CabraVC/vector_dataset_stratified_ttv_split_2023-12-05_21-07](https://huggingface.co/datasets/CabraVC/vector_dataset_stratified_ttv_split_2023-12-05_21-07) dataset that can be used for Text Classification. A MLP instance is used for classification.
155
+
156
+ The model has been trained using an efficient few-shot learning technique that involves:
157
+
158
+ 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
159
+ 2. Training a classification head with features from the fine-tuned Sentence Transformer.
160
+
161
+ ## Model Details
162
+
163
+ ### Model Description
164
+ - **Model Type:** SetFit
165
+ <!-- - **Sentence Transformer:** [Unknown](https://huggingface.co/unknown) -->
166
+ - **Classification head:** a MLP instance
167
+ - **Maximum Sequence Length:** 512 tokens
168
+ - **Number of Classes:** 3 classes
169
+ - **Training Dataset:** [CabraVC/vector_dataset_stratified_ttv_split_2023-12-05_21-07](https://huggingface.co/datasets/CabraVC/vector_dataset_stratified_ttv_split_2023-12-05_21-07)
170
+ <!-- - **Language:** Unknown -->
171
+ <!-- - **License:** Unknown -->
172
+
173
+ ### Model Sources
174
+
175
+ - **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
176
+ - **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
177
+ - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
178
+
179
+ ### Model Labels
180
+ | Label | Examples |
181
+ |:------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
182
+ | BUY | <ul><li>'mix, the mix of sales by us and by other sellers, our continuing focus on in-stock inventory availability, our investment in new geographies and product lines, and the extent to which we choose to utilize outsource fulfillment providers. Accounts payable days were 62, 57, and 53 for 2008, 2007 and 2006. We expect some variability in accounts payable days over time since they are affected by several factors, including the mix of product sales, the mix of sales by other sellers, the mix of suppliers, seasonality, and changes in payment terms over time, including the effect of balancing pricing and timing of payment terms with suppliers. \n\nWe expect spending in technology and content will increase over time as we add computer scientists, software engineers, and employees involved in category expansion, editorial content, buying, merchandising selection, and systems support. We seek to efficiently invest in several areas of technology and content, including seller platforms, web services, digital initiatives, and expansion of new and existing product categories, as well as in technology infrastructure to enhance the customer experience, improve our process efficiencies and support our infrastructure web services. We believe that advances in technology, specifically the speed and reduced cost of processing power, the improved consumer experience of the Internet outside of the workplace through lower-cost broadband service to the home, and the advances of wireless connectivity, will continue to improve the consumer experience on the Internet and increase its ubiquity in people’s lives. We are investing in Amazon Web Services, which provides technology services that give developers access to technology infrastructure that they can use to enable virtually any type of business. A continuing challenge will be to continue to build and deploy innovative and efficient software that will best take advantage of continued advances in technology. \n\nOur financial reporting currency is the U.S. Dollar and changes in exchange rates significantly affect our reported results and consolidated trends. For example, if the U.S. Dollar weakens year-over-year relative to currencies in our international locations, our consolidated net sales, gross profit, and operating expenses will be higher than if currencies had remained constant. Likewise, if the U.S. Dollar strengthens year-over-year relative to currencies in our international locations, our consolidated net sales, gross profit, and operating expenses will be lower than if currencies had remained constant. We believe that our increasing diversification beyond the U.S. economy through our growing international businesses benefits our shareholders over the long term. We also believe it is important to evaluate our operating results and growth rates before and after the effect of currency changes. \n\nIn addition, the remeasurement of our 6.875% PEACS and intercompany balances can result in significant gains and charges associated with the effect of movements in currency exchange rates. Currency volatilities may continue, which may significantly impact (either positively or negatively) our reported results and'</li></ul> |
183
+ | SELL | <ul><li>'estimates and changes to these estimates will cause the fair values of our stock awards and related stock-based compensation expense that we record to vary.\n\nWe record deferred tax assets for stock-based compensation awards that result in deductions on our income tax returns, based on the amount of stock-based compensation recognized and the fair values attributable to the vested portion of stock awards assumed in connection with a business combination, at the statutory tax rate in the jurisdiction in which we will receive a tax deduction. Because the deferred tax assets we record are based upon the stock-based compensation expenses in a particular jurisdiction, the aforementioned inputs that affect the fair values of our stock awards may also indirectly affect our income tax expense. In addition, differences between the deferred tax assets recognized for financial reporting purposes and the actual tax deduction reported on our income tax returns are recorded in additional paid-in capital. If the tax deduction is less than the deferred tax asset, the calculated shortfall reduces our pool of excess tax benefits. If the pool of excess tax benefits is reduced to zero, then subsequent shortfalls would increase our income tax expense.\n\nTo the extent we change the terms of our employee stock-based compensation programs, experience market volatility in the pricing of our common stock that increases the implied volatility calculation of publicly traded options in our stock, refine different assumptions in future periods such as forfeiture rates that differ from our current estimates, or assume stock awards from acquired companies that are different in nature than our stock award arrangements, among other potential impacts, the stock-based compensation expense that we record in future periods and the tax benefits that we realize may differ significantly from what we have recorded in previous reporting periods.\n\nResults of Operations\n\nImpact of Acquisitions\n\nThe comparability of our operating results in fiscal 2014 compared to fiscal 2013 is impacted by our acquisitions, primarily our acquisitions of Responsys in the third quarter of fiscal 2014, Tekelec in the first quarter of fiscal 2014 and Acme Packet in the fourth quarter of fiscal 2013.\n\nThe comparability of our operating results in fiscal 2013 compared to fiscal 2012 is impacted by our acquisitions, primarily our acquisitions of Acme Packet in the fourth quarter of fiscal 2013, Taleo Corporation (Taleo) in the fourth quarter of fiscal 2012 and RightNow Technologies, Inc. (RightNow) during the third quarter of fiscal 2012.\n\nIn our discussion of changes in our results of operations from fiscal 2014 compared to fiscal 2013 and fiscal 2013 compared to fiscal 2012, we may qualitatively disclose the impacts of our acquired products (for the one year period subsequent to the acquisition date) to the growth in our new software licenses revenues, cloud SaaS and PaaS revenues, software license updates and product support revenues, hardware systems products revenues and hardware systems support revenues where such qualitative discussions would be meaningful for an understanding of the factors that'</li></ul> |
184
+ | HOLD | <ul><li>'both historical and projected future operating results, the reversal of existing taxable temporary differences, taxable income in prior carryback years (if permitted) and the availability of tax planning strategies. A valuation allowance is required to be established unless management determines that it is more likely than not that the Company will ultimately realize the tax benefit associated with a deferred tax asset. \n\nAdditionally, undistributed earnings of a subsidiary are accounted for as a temporary difference, except that deferred tax liabilities are not recorded for undistributed earnings of a foreign subsidiary that are deemed to be indefinitely reinvested in the foreign jurisdiction. The Company has formulated a specific plan for reinvestment of undistributed earnings of its foreign subsidiaries which demonstrates that such earnings will be indefinitely reinvested in the applicable tax jurisdictions. Should we change our plans, we would be required to record a significant amount of deferred tax liabilities. \n\nThe Company\'s effective tax rate is expected to be approximately 23.0 percent to 24.0 percent in 2009. This estimated tax rate does not reflect the impact of any unusual or special items that may affect our tax rate in 2009. \n\nContingencies \n\nOur Company is subject to various claims and contingencies, mostly related to legal proceedings and tax matters (both income taxes and indirect taxes). Due to their nature, such legal proceedings and tax matters involve inherent uncertainties including, but not limited to, court rulings, negotiations between affected parties and governmental actions. Management assesses the probability of loss for such contingencies and accrues a liability and/or discloses the relevant circumstances, as appropriate. Management believes that any liability to the Company that may arise as a result of currently pending legal proceedings, tax matters or other contingencies will not have a material adverse effect on the financial condition of the Company taken as a whole. Refer to Note 13 of Notes to Consolidated Financial Statements. \n\nRecent Accounting Standards and Pronouncements \n\nRefer to Note 1 of Notes to Consolidated Financial Statements for a discussion of recent accounting standards and pronouncements. \n\nOperations Review \n\nWe manufacture, distribute and market nonalcoholic beverage concentrates and syrups. We also manufacture, distribute and market finished beverages. Our organizational structure as of December 31, 2008, consisted of the following operating segments, the first six of which are sometimes referred to as "operating groups" or "groups": Eurasia and Africa; Europe; Latin America; North America; Pacific; Bottling Investments; and Corporate. We revised previously reported group information to conform to our operating structure in effect as of December 31, 2008. For further information regarding our operating segments, including a discussion of changes made to our operating segments effective July 1, 2008, refer to Note 21 of Notes to Consolidated Financial Statements. \n\nBeverage Volume \n\nWe measure our sales volume in two ways: (1) unit cases of finished products and (2) concentrate'</li></ul> |
185
+
186
+ ## Evaluation
187
+
188
+ ### Metrics
189
+ | Label | Accuracy |
190
+ |:--------|:---------|
191
+ | **all** | 0.3333 |
192
+
193
+ ## Uses
194
+
195
+ ### Direct Use for Inference
196
+
197
+ First install the SetFit library:
198
+
199
+ ```bash
200
+ pip install setfit
201
+ ```
202
+
203
+ Then you can load this model and run inference.
204
+
205
+ ```python
206
+ from setfit import SetFitModel
207
+
208
+ # Download from the 🤗 Hub
209
+ model = SetFitModel.from_pretrained("setfit_model_id")
210
+ # Run inference
211
+ preds = model("to 2005, led by double-digit growth in China, Russia and Turkey, partially offset by a 3 percent decline in Japan. The increase in unit case volume in China was led by significant growth in both sparkling and still beverages. The unit case volume growth in Russia and Turkey was the result of improving macroeconomic trends, strong bottler execution and successful marketing programs. Unit case volume in Russia also benefited from the full-year impact of the joint acquisition of Multon, compared to a partial year in 2005. The Company and Coca-Cola HBC jointly acquired Multon, a Russian juice company, in April 2005. The decrease in unit case volume in Japan was primarily due to weakness across core brands including Trademark Coca-Cola, Georgia Coffee and our green tea brands. However, results in Japan gradually improved during 2006 and position Japan for growth in 2007.
212
+
213
+ Unit case volume for Bottling Investments increased 16 percent in 2006 versus 2005, primarily due to the acquisition of Kerry Beverages Limited, which was subsequently renamed Coca-Cola China Industries Limited (\"CCCIL\"), and the acquisitions of TJC Holdings (Pty) Ltd., a South African bottling company (\"TJC\"), and Apollinaris. The Company intends to sell a portion of its investment in TJC to Black Economic Empowerment entities at a future date. Unit case volume for Bottling Investments also increased due to the consolidation of Brucephil, Inc. (\"Brucephil\"), the parent company of The Philadelphia Coca-Cola Bottling Company. In the third quarter of 2006, our Company signed agreements with J. Bruce Llewellyn and Brucephil for the potential purchase of the remaining shares of Brucephil not currently owned by the Company. The agreements provide for the Company's purchase of the shares upon the election of Mr. Llewellyn or the election of the Company. Based on the terms of these agreements, the Company concluded that it must consolidate Brucephil under Interpretation No. 46(R). Brucephil's financial statements were consolidated effective September 29, 2006. The acquisition of the German bottling company Bremer Erfrischungsgetraenke GmbH (\"Bremer\") during the third quarter of 2005 also contributed to unit case volume increases in 2006, reflecting the impact of full-year unit case volume in 2006 for Bremer compared to a partial year in 2005. The unit case volume increase was partially offset by a decline in India.
214
+
215
+ In Africa, unit case volume increased 6 percent in 2005 compared to 2004. This increase was driven by growth in core sparkling beverages as well as still beverages across all divisions in this operating segment.
216
+
217
+ In East, South Asia and Pacific Rim, unit case volume decreased 4 percent in 2005 compared to 2004, primarily due to declines in India and the Philippines. The decline in India was related to the impact of price increases to cover rising raw material and distribution costs and the lingering effects of the 2003 pesticide allegations. The decline in the Philippines was primarily related to affordability and availability issues.
218
+
219
+ Unit case volume in the European Union was even in 2005 versus 2004, primarily due to strong growth in Spain and Central Europe")
220
+ ```
221
+
222
+ <!--
223
+ ### Downstream Use
224
+
225
+ *List how someone could finetune this model on their own dataset.*
226
+ -->
227
+
228
+ <!--
229
+ ### Out-of-Scope Use
230
+
231
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
232
+ -->
233
+
234
+ <!--
235
+ ## Bias, Risks and Limitations
236
+
237
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
238
+ -->
239
+
240
+ <!--
241
+ ### Recommendations
242
+
243
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
244
+ -->
245
+
246
+ ## Training Details
247
+
248
+ ### Training Set Metrics
249
+ | Training set | Min | Median | Max |
250
+ |:-------------|:----|:---------|:----|
251
+ | Word count | 466 | 473.6667 | 485 |
252
+
253
+ | Label | Training Sample Count |
254
+ |:------|:----------------------|
255
+ | BUY | 1 |
256
+ | HOLD | 1 |
257
+ | SELL | 1 |
258
+
259
+ ### Training Hyperparameters
260
+ - batch_size: (16, 2)
261
+ - num_epochs: (1, 16)
262
+ - max_steps: -1
263
+ - sampling_strategy: oversampling
264
+ - body_learning_rate: (2e-05, 1e-05)
265
+ - head_learning_rate: 0.01
266
+ - loss: CosineSimilarityLoss
267
+ - distance_metric: cosine_distance
268
+ - margin: 0.25
269
+ - end_to_end: True
270
+ - use_amp: False
271
+ - warmup_proportion: 0.1
272
+ - max_length: 512
273
+ - seed: 1003200212
274
+ - eval_max_steps: -1
275
+ - load_best_model_at_end: False
276
+
277
+ ### Training Results
278
+ | Epoch | Step | Training Loss | Validation Loss |
279
+ |:-----:|:----:|:-------------:|:---------------:|
280
+ | 1.0 | 1 | 0.194 | 0.1151 |
281
+
282
+ ### Framework Versions
283
+ - Python: 3.11.6
284
+ - SetFit: 1.0.1
285
+ - Sentence Transformers: 2.2.2
286
+ - Transformers: 4.35.2
287
+ - PyTorch: 2.1.1
288
+ - Datasets: 2.15.0
289
+ - Tokenizers: 0.15.0
290
+
291
+ ## Citation
292
+
293
+ ### BibTeX
294
+ ```bibtex
295
+ @article{https://doi.org/10.48550/arxiv.2209.11055,
296
+ doi = {10.48550/ARXIV.2209.11055},
297
+ url = {https://arxiv.org/abs/2209.11055},
298
+ author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
299
+ keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
300
+ title = {Efficient Few-Shot Learning Without Prompts},
301
+ publisher = {arXiv},
302
+ year = {2022},
303
+ copyright = {Creative Commons Attribution 4.0 International}
304
+ }
305
+ ```
306
+
307
+ <!--
308
+ ## Glossary
309
+
310
+ *Clearly define terms in order to be accessible across audiences.*
311
+ -->
312
+
313
+ <!--
314
+ ## Model Card Authors
315
+
316
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
317
+ -->
318
+
319
+ <!--
320
+ ## Model Card Contact
321
+
322
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
323
+ -->
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/Users/tarassvystun/.cache/torch/sentence_transformers/sentence-transformers_all-distilroberta-v1/",
3
+ "architectures": [
4
+ "RobertaModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 514,
18
+ "model_type": "roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 6,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.35.2",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 50265
28
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.0.0",
4
+ "transformers": "4.6.1",
5
+ "pytorch": "1.8.1"
6
+ }
7
+ }
config_setfit.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "labels": [
3
+ "BUY",
4
+ "HOLD",
5
+ "SELL"
6
+ ],
7
+ "normalize_embeddings": false
8
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cc07598b724b5db480ca02da43c621ecec29c43ebcb527b2978c3a900273ee0
3
+ size 328485128
model_head.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95c6198a66410ce3ceb2bc2c03db0ec23eaf32a6b3cc244f1489b1d631723fce
3
+ size 799300
modules.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ },
14
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_Normalize",
18
+ "type": "sentence_transformers.models.Normalize"
19
+ }
20
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 512,
3
+ "do_lower_case": false
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "max_length": 128,
52
+ "model_max_length": 512,
53
+ "pad_to_multiple_of": null,
54
+ "pad_token": "<pad>",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
+ "sep_token": "</s>",
58
+ "stride": 0,
59
+ "tokenizer_class": "RobertaTokenizer",
60
+ "trim_offsets": true,
61
+ "truncation_side": "right",
62
+ "truncation_strategy": "longest_first",
63
+ "unk_token": "<unk>"
64
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff