Hugging Face's logo

amplyfi
/
all-labels

Text Classification
setfit
Safetensors
sentence-transformers
bert
generated_from_setfit_trainer
Eval Results
Model card Files Community
luis-espinosa commited on
Commit
88baec5
·
verified ·
1 Parent(s): c13b950

Upload trained SetFit model

Browse files
Files changed (13) hide show
  1. 1_Pooling/config.json +10 -0
  2. README.md +312 -0
  3. config.json +32 -0
  4. config_sentence_transformers.json +10 -0
  5. config_setfit.json +47 -0
  6. model.safetensors +3 -0
  7. model_head.pkl +3 -0
  8. modules.json +14 -0
  9. sentence_bert_config.json +4 -0
  10. special_tokens_map.json +37 -0
  11. tokenizer.json +0 -0
  12. tokenizer_config.json +57 -0
  13. vocab.txt +0 -0
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
README.md ADDED
@@ -0,0 +1,312 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - setfit
4
+ - sentence-transformers
5
+ - text-classification
6
+ - generated_from_setfit_trainer
7
+ widget:
8
+ - text: Ofgem secures £450k from GDF SUEZ/IPM for environmental obligation failure
9
+ - text: Forwarder ICL opens in Rotterdam
10
+ - text: Ofgem issues three final orders for £15 million in unpaid Renewables Obligation
11
+ and Feed-in Tariff payments
12
+ - text: DP world partners with China’s Zhejiang Seaport Group
13
+ - text: Ofgem completes investigation into EDF Energy networks - finds no breach of
14
+ obligations
15
+ metrics:
16
+ - accuracy
17
+ pipeline_tag: text-classification
18
+ library_name: setfit
19
+ inference: true
20
+ base_model: infgrad/stella-base-en-v2
21
+ model-index:
22
+ - name: SetFit with infgrad/stella-base-en-v2
23
+ results:
24
+ - task:
25
+ type: text-classification
26
+ name: Text Classification
27
+ dataset:
28
+ name: Unknown
29
+ type: unknown
30
+ split: test
31
+ metrics:
32
+ - type: accuracy
33
+ value: 0.7162162162162162
34
+ name: Accuracy
35
+ ---
36
+
37
+ # SetFit with infgrad/stella-base-en-v2
38
+
39
+ This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [infgrad/stella-base-en-v2](https://huggingface.co/infgrad/stella-base-en-v2) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
40
+
41
+ The model has been trained using an efficient few-shot learning technique that involves:
42
+
43
+ 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
44
+ 2. Training a classification head with features from the fine-tuned Sentence Transformer.
45
+
46
+ ## Model Details
47
+
48
+ ### Model Description
49
+ - **Model Type:** SetFit
50
+ - **Sentence Transformer body:** [infgrad/stella-base-en-v2](https://huggingface.co/infgrad/stella-base-en-v2)
51
+ - **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
52
+ - **Maximum Sequence Length:** 512 tokens
53
+ - **Number of Classes:** 42 classes
54
+ <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
55
+ <!-- - **Language:** Unknown -->
56
+ <!-- - **License:** Unknown -->
57
+
58
+ ### Model Sources
59
+
60
+ - **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
61
+ - **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
62
+ - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
63
+
64
+ ### Model Labels
65
+ | Label | Examples |
66
+ |:----------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
67
+ | ['supply'] | <ul><li>'Consumer Electronics Supply Chain Strain: Apple Faces Delays in iPhone Production'</li><li>'Airline Supply Chain Struggles: Delta Airlines Faces Fuel Supply Issues'</li><li>'Construction Industry Supply Chain Issues: Concrete Shortages Delay Major Projects'</li></ul> |
68
+ | ['part'] | <ul><li>'Tide partners with Connect Earth to help SMEs reach Net Zero'</li><li>'Wisk, Archer and Boeing settle litigation and chart the future'</li><li>'Live Oak Bank Launches First Embedded Banking Partnership'</li></ul> |
69
+ | ['objs'] | <ul><li>'BenevolentAI to participate in Goldman Sachs 45th Annual Global Healthcare Conference'</li><li>'Thames becomes first UK utility to join refugee employment scheme'</li><li>'Ofgem publishes 2017 annual iteration process for energy network price controls'</li></ul> |
70
+ | ['funding'] | <ul><li>'Ethiopian Airlines secures financing for two 777Fs'</li><li>'Ofwat awards £5.8m to 44 network innovation projects'</li><li>'Clean energy in rural America gets another big boost of federal funding'</li></ul> |
71
+ | ['c-change'] | <ul><li>'Prospector Metals Corp.: Prospector Appoints Monty Sutton as CFO'</li><li>'Qatar Airways appoints new head of cargo'</li><li>'On the move | Eon shakes up board; former Southern Water CEO becomes chair of consultancy'</li></ul> |
72
+ | ['innov'] | <ul><li>'Alaska Airlines Invests in New World-class Training Facility'</li><li>'Syngenta Group: Syngenta opens rights to genome-editing and breeding technologies to boost agricultural innovation'</li><li>'DHL Global Forwarding adds chatbot to customer portal'</li></ul> |
73
+ | ['market-decline'] | <ul><li>'Media Industry Struggles: Print Advertising Revenues Continue to Decline Year Over Year'</li><li>'Pharmaceutical Market Decline: Generic Drug Prices Continue to Fall, Hitting Profits'</li><li>'Construction Industry Slowdown: New Housing Starts Decline Amid Rising Interest Rates'</li></ul> |
74
+ | ['m&a'] | <ul><li>'CMA CGM completes Bolloré Logistics acquisition'</li><li>'Three NY offshore wind projects unravel after GE scraps turbine plans'</li><li>'Centrica asset sales & the current market environment'</li></ul> |
75
+ | ['new-prod'] | <ul><li>'Airbus Unveils New Stealthy Loyal Wingman Concept'</li><li>'Hawaiian Airlines Previews New Boeing 787-9 Dreamliner'</li><li>'Embraer boosts comfort and safety with the Phenom 100EX'</li></ul> |
76
+ | ['c-mention'] | <ul><li>'Dame Mary Archer and ex-EDF nuclear boss join DESNZ board - Utility Week'</li><li>'Lok Sabha Elections 2024: Rahul Gandhi Comfortably Leads In Wayanad, Raebareli'</li><li>'Steve Smith Ofgem Senior Partner Local Grids and RPI-X@20 - statement'</li></ul> |
77
+ | ['awards'] | <ul><li>'Best in Show: Local Artisan Wins Craft Fair Top Prize'</li><li>'Frankfurt high-flier wins IATA talent competition'</li><li>"Best International Film: 'Parasite' Takes Home the Oscar"</li></ul> |
78
+ | ['regulatory'] | <ul><li>'Ofgem’s response to National Grid’s proposed network upgrade to connect the new Hinkley Point C nuclear power station'</li><li>'Ofgem appoints Utilita Energy to take on customers of Eversmart Energy'</li><li>'Ofgem response to UK power failures'</li></ul> |
79
+ | ['new-prod', 'objs'] | <ul><li>'Severn Trent launches multi-million pound scheme to reduce storm overflow spills'</li><li>'Drax gets planning go ahead for £2bn BECCS project'</li><li>'National Grid begins work on substation for major EV hub'</li></ul> |
80
+ | ['market-entry'] | <ul><li>'Aer Lingus to Launch Las Vegas Flights in Fall 2024'</li><li>'Air Canada Announces Major Expansion Of Flight Network To India For Winter 2024-25'</li><li>'Menzies Aviation secures new Heathrow cargo contracts'</li></ul> |
81
+ | ['esg'] | <ul><li>'BP Announces Major Investment in Renewable Energy Projects'</li><li>"Apple's Environmental Progress Report Highlights Carbon Footprint Reduction"</li><li>'Silk Way West joins the UN’s Global Compact Initiative'</li></ul> |
82
+ | ['new-prod', 'innov'] | <ul><li>'World’s largest direct air capture plant starts sucking CO2 from the sky'</li><li>'Airbus advances development of A350F'</li></ul> |
83
+ | ['market-growth'] | <ul><li>'Power prices tumble amid mild winter and record renewable output'</li><li>'WestJet Cargo network branches out'</li><li>'LNG contract value swinging with gas & oil markets'</li></ul> |
84
+ | ['market-exit'] | <ul><li>'El Al Israel Airlines to Stop Flying to Dublin, Marrakesh'</li><li>'Energy Exit: BP Sells Off U.S. Oil Assets as Part of Green Transition'</li><li>'Retail Shakeup: J.C. Penney Closes All Stores Following Bankruptcy Filing'</li></ul> |
85
+ | ['market-entry', 'new-prod'] | <ul><li>'Delta Resuming Tel Aviv Flights From June 7'</li><li>'DHL Air sets up MRO facility at East Midlands Airport'</li><li>'TAAG Angola Airlines adds Luanda-Lisbon belly capacity'</li></ul> |
86
+ | ['layoffs'] | <ul><li>'FedEx offers pilots $250,000 to leave ‘overstaffed’ cargo company'</li><li>'Fashion Retailer Announces Layoffs Amid Changing Consumer Trends'</li><li>'Media Company Layoffs: CNN Cuts Jobs as Part of Strategic Shift'</li></ul> |
87
+ | ['regulatory', 'objs'] | <ul><li>'Energy minister announces post-Brexit energy trading boost'</li><li>'Ofgem gives go-ahead to Orkney transmission link subject to conditions'</li></ul> |
88
+ | ['hiring'] | <ul><li>'Logistics Company Hiring Drivers to Meet Increased Demand'</li><li>'Octopus seeks 4,000 new recruits to tackle heat pump rollout'</li><li>'Financial Services Company Expands Team with New Analysts'</li></ul> |
89
+ | ['m&a', 'part'] | <ul><li>'UPS to Replace FedEx as USPS Primary Air Cargo Provider'</li></ul> |
90
+ | ['regulatory', 'c-change'] | <ul><li>'Water companies ordered to upgrade 140 wastewater treatment works'</li><li>'Delay to SGN’s hydrogen trial ‘strengthens case’ for taking heating decision now'</li></ul> |
91
+ | ['market-entry', 'part'] | <ul><li>'Matador AI Launches International Expansion Through Exclusive Canadian Partnership with AutoSync'</li><li>'Delta Air Lines Resuming Flights To Tel Aviv, Israel'</li></ul> |
92
+ | ['innov', 'new-prod'] | <ul><li>'SmartAir upgrades real-time safety awareness for UAS and eVTOL'</li><li>'Emirates gets ready for SAF at Schiphol'</li></ul> |
93
+ | ['new-prod', 'market-entry'] | <ul><li>'Maersk Air Cargo to trial new UK-China route'</li></ul> |
94
+ | ['objs', 'market-growth'] | <ul><li>'Sonoco Products Company: Sonoco To Implement Further Price Increase for Core Board and Paperboard in Europe'</li><li>'1Password Strengthens EMEA Presence with Significant Business Growth, Key Customer Wins, and Region-Specific Product Capabilities'</li></ul> |
95
+ | ['c-change', 'c-mention'] | <ul><li>'Government selects Martin Cave as preferred candidate to be next Ofgem chairman'</li></ul> |
96
+ | ['new-prod', 'funding'] | <ul><li>'Eon to install UK’s largest roof-mounted solar project'</li><li>'US Steel plant in Indiana to host a $150M carbon capture experiment'</li></ul> |
97
+ | ['part', 'objs'] | <ul><li>'New supplier is appointed for customers of the Team Group of Companies Limited'</li><li>'Ofgem appoints British Gas to take on customers of PfP Energy and MoneyPlus Energy'</li><li>'Ofgem chooses preferred bidder for link to Race Bank Wind Farm'</li></ul> |
98
+ | ['funding', 'objs'] | <ul><li>'Ofgem boosts investment for Britain’s electricity networks'</li><li>'Ofgem announces £17 billion new investment package and reduces pressure on customer bills'</li></ul> |
99
+ | ['new-prod', 'm&a'] | <ul><li>'Mexicana de Aviación orders 20 Embraer E2 aircraft to enhance fleet and connectivity'</li></ul> |
100
+ | ['objs', 'funding'] | <ul><li>"Google's investment in Singapore reaches $5B, underpinned by data center expansion"</li></ul> |
101
+ | ['objs', 'new-prod'] | <ul><li>'Korean Air Orders 33 Airbus A350s, including -1000s and -900s'</li></ul> |
102
+ | ['c-mention', 'c-change'] | <ul><li>"Ofgem welcomes DECC's announcement of David Gray as new Chairman"</li></ul> |
103
+ | ['m&a', 'objs'] | <ul><li>'Carnival Corporation & plc: Carnival Corporation to Strategically Align Portfolio and Absorb P&O Cruises Australia into Carnival Cruise Line'</li></ul> |
104
+ | ['new-prod', 'market-growth'] | <ul><li>'Minnesota’s biggest solar project will help replace a huge coal plant'</li></ul> |
105
+ | ['market-decline', 'supply'] | <ul><li>'Qantas Freight makes progress but backlog unlikely to be cleared this week'</li></ul> |
106
+ | ['m&a', 'market-exit'] | <ul><li>'Korean Air poised to sell off Asiana cargo business'</li><li>'Air France-KLM Group Reduces Stake in Kenya Airways'</li></ul> |
107
+ | ['objs', 'c-change'] | <ul><li>'Ofgem confirms approach to boosting green and smart investment in local grids'</li></ul> |
108
+ | ['market-entry', 'market-growth'] | <ul><li>'Emirates expands e-commerce service to Kuwait'</li><li>'Air Canada to Expand Service from Ottawa Year Round'</li></ul> |
109
+
110
+ ## Evaluation
111
+
112
+ ### Metrics
113
+ | Label | Accuracy |
114
+ |:--------|:---------|
115
+ | **all** | 0.7162 |
116
+
117
+ ## Uses
118
+
119
+ ### Direct Use for Inference
120
+
121
+ First install the SetFit library:
122
+
123
+ ```bash
124
+ pip install setfit
125
+ ```
126
+
127
+ Then you can load this model and run inference.
128
+
129
+ ```python
130
+ from setfit import SetFitModel
131
+
132
+ # Download from the 🤗 Hub
133
+ model = SetFitModel.from_pretrained("amplyfi/all-labels")
134
+ # Run inference
135
+ preds = model("Forwarder ICL opens in Rotterdam")
136
+ ```
137
+
138
+ <!--
139
+ ### Downstream Use
140
+
141
+ *List how someone could finetune this model on their own dataset.*
142
+ -->
143
+
144
+ <!--
145
+ ### Out-of-Scope Use
146
+
147
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
148
+ -->
149
+
150
+ <!--
151
+ ## Bias, Risks and Limitations
152
+
153
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
154
+ -->
155
+
156
+ <!--
157
+ ### Recommendations
158
+
159
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
160
+ -->
161
+
162
+ ## Training Details
163
+
164
+ ### Training Set Metrics
165
+ | Training set | Min | Median | Max |
166
+ |:-------------|:----|:--------|:----|
167
+ | Word count | 4 | 10.0203 | 30 |
168
+
169
+ | Label | Training Sample Count |
170
+ |:----------------------------------|:----------------------|
171
+ | ['awards'] | 17 |
172
+ | ['c-change', 'c-mention'] | 1 |
173
+ | ['c-change'] | 64 |
174
+ | ['c-mention', 'c-change'] | 1 |
175
+ | ['c-mention'] | 9 |
176
+ | ['esg'] | 16 |
177
+ | ['funding', 'objs'] | 2 |
178
+ | ['funding'] | 46 |
179
+ | ['hiring'] | 17 |
180
+ | ['innov', 'new-prod'] | 2 |
181
+ | ['innov'] | 16 |
182
+ | ['layoffs'] | 16 |
183
+ | ['m&a', 'market-exit'] | 2 |
184
+ | ['m&a', 'objs'] | 1 |
185
+ | ['m&a', 'part'] | 1 |
186
+ | ['m&a'] | 57 |
187
+ | ['market-decline', 'supply'] | 1 |
188
+ | ['market-decline'] | 19 |
189
+ | ['market-entry', 'market-growth'] | 2 |
190
+ | ['market-entry', 'new-prod'] | 5 |
191
+ | ['market-entry', 'part'] | 2 |
192
+ | ['market-entry'] | 46 |
193
+ | ['market-exit'] | 19 |
194
+ | ['market-growth'] | 31 |
195
+ | ['new-prod', 'funding'] | 2 |
196
+ | ['new-prod', 'innov'] | 2 |
197
+ | ['new-prod', 'm&a'] | 1 |
198
+ | ['new-prod', 'market-entry'] | 1 |
199
+ | ['new-prod', 'market-growth'] | 1 |
200
+ | ['new-prod', 'objs'] | 3 |
201
+ | ['new-prod'] | 116 |
202
+ | ['objs', 'c-change'] | 1 |
203
+ | ['objs', 'funding'] | 1 |
204
+ | ['objs', 'market-growth'] | 2 |
205
+ | ['objs', 'new-prod'] | 1 |
206
+ | ['objs'] | 42 |
207
+ | ['part', 'objs'] | 5 |
208
+ | ['part'] | 99 |
209
+ | ['regulatory', 'c-change'] | 2 |
210
+ | ['regulatory', 'objs'] | 2 |
211
+ | ['regulatory'] | 191 |
212
+ | ['supply'] | 20 |
213
+
214
+ ### Training Hyperparameters
215
+ - batch_size: (16, 16)
216
+ - num_epochs: (3, 3)
217
+ - max_steps: -1
218
+ - sampling_strategy: oversampling
219
+ - num_iterations: 5
220
+ - body_learning_rate: (2e-05, 2e-05)
221
+ - head_learning_rate: 2e-05
222
+ - loss: CosineSimilarityLoss
223
+ - distance_metric: cosine_distance
224
+ - margin: 0.25
225
+ - end_to_end: False
226
+ - use_amp: False
227
+ - warmup_proportion: 0.1
228
+ - l2_weight: 0.01
229
+ - seed: 42
230
+ - eval_max_steps: -1
231
+ - load_best_model_at_end: False
232
+
233
+ ### Training Results
234
+ | Epoch | Step | Training Loss | Validation Loss |
235
+ |:------:|:----:|:-------------:|:---------------:|
236
+ | 0.0018 | 1 | 0.2357 | - |
237
+ | 0.0903 | 50 | 0.2131 | - |
238
+ | 0.1805 | 100 | 0.1775 | - |
239
+ | 0.2708 | 150 | 0.1474 | - |
240
+ | 0.3610 | 200 | 0.0981 | - |
241
+ | 0.4513 | 250 | 0.0772 | - |
242
+ | 0.5415 | 300 | 0.063 | - |
243
+ | 0.6318 | 350 | 0.063 | - |
244
+ | 0.7220 | 400 | 0.0539 | - |
245
+ | 0.8123 | 450 | 0.0448 | - |
246
+ | 0.9025 | 500 | 0.0494 | - |
247
+ | 0.9928 | 550 | 0.0395 | - |
248
+ | 1.0830 | 600 | 0.0319 | - |
249
+ | 1.1733 | 650 | 0.0316 | - |
250
+ | 1.2635 | 700 | 0.0297 | - |
251
+ | 1.3538 | 750 | 0.0237 | - |
252
+ | 1.4440 | 800 | 0.0267 | - |
253
+ | 1.5343 | 850 | 0.0158 | - |
254
+ | 1.6245 | 900 | 0.0273 | - |
255
+ | 1.7148 | 950 | 0.0217 | - |
256
+ | 1.8051 | 1000 | 0.0173 | - |
257
+ | 1.8953 | 1050 | 0.0159 | - |
258
+ | 1.9856 | 1100 | 0.0196 | - |
259
+ | 2.0758 | 1150 | 0.0123 | - |
260
+ | 2.1661 | 1200 | 0.0102 | - |
261
+ | 2.2563 | 1250 | 0.0135 | - |
262
+ | 2.3466 | 1300 | 0.0121 | - |
263
+ | 2.4368 | 1350 | 0.0091 | - |
264
+ | 2.5271 | 1400 | 0.0139 | - |
265
+ | 2.6173 | 1450 | 0.0119 | - |
266
+ | 2.7076 | 1500 | 0.0069 | - |
267
+ | 2.7978 | 1550 | 0.008 | - |
268
+ | 2.8881 | 1600 | 0.0081 | - |
269
+ | 2.9783 | 1650 | 0.0072 | - |
270
+
271
+ ### Framework Versions
272
+ - Python: 3.10.12
273
+ - SetFit: 1.1.0
274
+ - Sentence Transformers: 3.3.1
275
+ - Transformers: 4.42.2
276
+ - PyTorch: 2.5.1+cu124
277
+ - Datasets: 3.1.0
278
+ - Tokenizers: 0.19.1
279
+
280
+ ## Citation
281
+
282
+ ### BibTeX
283
+ ```bibtex
284
+ @article{https://doi.org/10.48550/arxiv.2209.11055,
285
+ doi = {10.48550/ARXIV.2209.11055},
286
+ url = {https://arxiv.org/abs/2209.11055},
287
+ author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
288
+ keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
289
+ title = {Efficient Few-Shot Learning Without Prompts},
290
+ publisher = {arXiv},
291
+ year = {2022},
292
+ copyright = {Creative Commons Attribution 4.0 International}
293
+ }
294
+ ```
295
+
296
+ <!--
297
+ ## Glossary
298
+
299
+ *Clearly define terms in order to be accessible across audiences.*
300
+ -->
301
+
302
+ <!--
303
+ ## Model Card Authors
304
+
305
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
306
+ -->
307
+
308
+ <!--
309
+ ## Model Card Contact
310
+
311
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
312
+ -->
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "infgrad/stella-base-en-v2",
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "LABEL_0": 0
19
+ },
20
+ "layer_norm_eps": 1e-12,
21
+ "max_position_embeddings": 512,
22
+ "model_type": "bert",
23
+ "num_attention_heads": 12,
24
+ "num_hidden_layers": 12,
25
+ "pad_token_id": 0,
26
+ "position_embedding_type": "absolute",
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.42.2",
29
+ "type_vocab_size": 2,
30
+ "use_cache": true,
31
+ "vocab_size": 30522
32
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.3.1",
4
+ "transformers": "4.42.2",
5
+ "pytorch": "2.5.1+cu124"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": "cosine"
10
+ }
config_setfit.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "normalize_embeddings": false,
3
+ "labels": [
4
+ "['awards']",
5
+ "['c-change', 'c-mention']",
6
+ "['c-change']",
7
+ "['c-mention', 'c-change']",
8
+ "['c-mention']",
9
+ "['esg']",
10
+ "['funding', 'objs']",
11
+ "['funding']",
12
+ "['hiring']",
13
+ "['innov', 'new-prod']",
14
+ "['innov']",
15
+ "['layoffs']",
16
+ "['m&a', 'market-exit']",
17
+ "['m&a', 'objs']",
18
+ "['m&a', 'part']",
19
+ "['m&a']",
20
+ "['market-decline', 'supply']",
21
+ "['market-decline']",
22
+ "['market-entry', 'market-growth']",
23
+ "['market-entry', 'new-prod']",
24
+ "['market-entry', 'part']",
25
+ "['market-entry']",
26
+ "['market-exit']",
27
+ "['market-growth']",
28
+ "['new-prod', 'funding']",
29
+ "['new-prod', 'innov']",
30
+ "['new-prod', 'm&a']",
31
+ "['new-prod', 'market-entry']",
32
+ "['new-prod', 'market-growth']",
33
+ "['new-prod', 'objs']",
34
+ "['new-prod']",
35
+ "['objs', 'c-change']",
36
+ "['objs', 'funding']",
37
+ "['objs', 'market-growth']",
38
+ "['objs', 'new-prod']",
39
+ "['objs']",
40
+ "['part', 'objs']",
41
+ "['part']",
42
+ "['regulatory', 'c-change']",
43
+ "['regulatory', 'objs']",
44
+ "['regulatory']",
45
+ "['supply']"
46
+ ]
47
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27f740e3083cd98f982466f1e5c5d5dd288bc177075cb2f7fb28f9961597c898
3
+ size 437951328
model_head.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3623a97dbeef8fcacd32a76661b1665e894d01721c7874e5269e0d9e6fd1d20f
3
+ size 264775
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": 512,
3
+ "do_lower_case": false
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff