lambdavi commited on
Commit
41f1ee9
1 Parent(s): 89596ab

Model save

Browse files
Files changed (1) hide show
  1. README.md +243 -0
README.md ADDED
@@ -0,0 +1,243 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: span-marker
3
+ tags:
4
+ - span-marker
5
+ - token-classification
6
+ - ner
7
+ - named-entity-recognition
8
+ - generated_from_span_marker_trainer
9
+ metrics:
10
+ - precision
11
+ - recall
12
+ - f1
13
+ widget:
14
+ - text: The seven-judge Constitution Bench of the Supreme Court in SBP and Co. (supra)
15
+ while reversing earlier five-judge Constitution Bench judgment in Konkan Railway
16
+ Corpn. Ltd. vs. Rani Construction (P) Ltd., (2002) 2 SCC 388 held that the power
17
+ exercised by the Chief Justice of the High Court or the Chief justice of India
18
+ under Section 11(6) of the Arbitration Act is not an administrative power but
19
+ is a judicial power.
20
+ - text: 'In The High Court Of Judicature At Patna Criminal Writ Jurisdiction Case
21
+ No.160 of 2021 Arising Out of Ps. Case No.-58 Year-2020 Thana- Bakhari District-
22
+ Begusarai ====================================================== Hanif Ur Rahman,
23
+ son of Azhar Rahman, Resident of C-39, East Nizamuddin, New Delhi....... Petitioner
24
+ Versus 1. The State of Bihar (through Chief Secretary, Govt. of Bihar) Main Secretariat,
25
+ Patna - 800015. 2. Meena Khatoon, wife of Mastan @ Noor Mohammad, Resident of
26
+ Village- Mansurpur Chaksikandar, P.S.- Bidupur, District- Vaishali (Bihar) 3.
27
+ The Bihar Police, through Standing Counsel. 4. Child Welfare Committee, through
28
+ Chairperson, Chanakyanagar, Mahmadpur, Begusarai. 5. The Superintendent, Alpawas
29
+ Grih, Nirala Nagar, Behind G.D. College, Ratanpur, Begusarai....... Respondents
30
+ ====================================================== Appearance:For the Petitioner:Ms.
31
+ Kriti Awasthi, Advocate Mr. Sambhav Gupta, Advocate Mr. Navnit Kumar, Advocate
32
+ Mr. Shyam Kumar, Advocate For the Respondents:Mr.Nadim Seraj, G.P.5 For the Resp.
33
+ No. 2:Ms. Archana Sinha, Advocate For the Resp. No. 4:Mr. Prabhu Narain Sharma,
34
+ Advocate ====================================================== Coram: Honourable
35
+ Mr. Justice Rajeev Ranjan Prasad C.A.V. Judgment'
36
+ - text: '1 R In The High Court Of Karnataka At Bengaluru Dated This The 19Th Day Of
37
+ February, 2021 Before The Hon''Ble Mr. Justice H.P. Sandesh Criminal Appeal No.176/2011
38
+ Between: Sri G.L. Jagadish, S/O Sri G.N. Lingappa, Aged About 52 Years, Residing
39
+ At No.29, 3Rd Main, Basaveshwara Housing Society Layout, Vijayanagar, Near Bts
40
+ Depot, Bengaluru-40....Appellant [By Sri H. Ramachandra, Advocate For Sri H.R.
41
+ Anantha Krishna Murthy And Associates - (Through V.C.)] And: Smt. Vasantha Kokila,
42
+ W/O Late N.R. Somashekhar, Aged About 58 Years, Residing At No.322, 8Th Main,
43
+ 3Rd Stage, 4Th Block, Basaveshwaranagar, Bengaluru....Respondent [By Sri K.R.
44
+ Lakshminarayana Rao, Advocate] This Criminal Appeal Is Filed Under Section 378(4)
45
+ Of Cr.P.C. Praying To Set Aside The Order Dated 06.07.2010 Passed By The P.O.
46
+ Ftc-Ii, Bengaluru In Crl.A. No.470/2009 And Confirming The Order Dated 27.05.2009
47
+ Passed By The Xxii Acmm And Xxiv Ascj, Bengaluru In C.C.No.17229/2004 Convicting
48
+ The Respondent/Accused For The Offence Punishable Under Section 138 Of Ni Act.
49
+ 2 This Criminal Appeal Having Been Heard And Reserved For Orders On 06.02.2021
50
+ This Day, The Court Pronounced The Following: Judgment'
51
+ - text: The petition was filed through Sh. Vijay Pahwa, General Power of Attorney
52
+ and it was asserted in the petition under Section 13-B of the Rent Act that 1
53
+ of 23 50% share of the demised premises had been purchased by the landlord from
54
+ Sh. Vinod Malhotra vide sale deed No.4226 registered on 20.12.2007 with Sub Registrar,
55
+ Chandigarh.
56
+ - text: Mr. Arun Bharadwaj, ld. CGSC, appearing for the Union of India, has Signature
57
+ Not Verified Digitally Signed By:PRATHIBA M SINGH Signing Date:09.10.2020 16:15
58
+ Digitally Signed By:SINDHU KRISHNAKUMAR Signing Date:09.10.2020 16:50:02 reiterated
59
+ the submissions made by Dr. Singhvi and has further submitted that this petition
60
+ ought to be heard with the OA No. 291/138/2020 pending before the CAT.
61
+ pipeline_tag: token-classification
62
+ model-index:
63
+ - name: SpanMarker
64
+ results:
65
+ - task:
66
+ type: token-classification
67
+ name: Named Entity Recognition
68
+ dataset:
69
+ name: Unknown
70
+ type: unknown
71
+ split: eval
72
+ metrics:
73
+ - type: f1
74
+ value: 0.9099756690997567
75
+ name: F1
76
+ - type: precision
77
+ value: 0.9089703932832524
78
+ name: Precision
79
+ - type: recall
80
+ value: 0.9109831709477414
81
+ name: Recall
82
+ ---
83
+
84
+ # SpanMarker
85
+
86
+ This is a [SpanMarker](https://github.com/tomaarsen/SpanMarkerNER) model that can be used for Named Entity Recognition.
87
+
88
+ ## Model Details
89
+
90
+ ### Model Description
91
+ - **Model Type:** SpanMarker
92
+ <!-- - **Encoder:** [Unknown](https://huggingface.co/unknown) -->
93
+ - **Maximum Sequence Length:** 128 tokens
94
+ - **Maximum Entity Length:** 6 words
95
+ <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
96
+ <!-- - **Language:** Unknown -->
97
+ <!-- - **License:** Unknown -->
98
+
99
+ ### Model Sources
100
+
101
+ - **Repository:** [SpanMarker on GitHub](https://github.com/tomaarsen/SpanMarkerNER)
102
+ - **Thesis:** [SpanMarker For Named Entity Recognition](https://raw.githubusercontent.com/tomaarsen/SpanMarkerNER/main/thesis.pdf)
103
+
104
+ ### Model Labels
105
+ | Label | Examples |
106
+ |:-------------|:------------------------------------------------------------------------------------------------------------------------------------|
107
+ | CASE_NUMBER | "Section 80", "Section 66 (1)", "Section 26-A" |
108
+ | COURT | "(1962) 45 ITR 210 (SC)", "Writ Appeal No. 479 of 2005.", "CMA No. 6727 of 93" |
109
+ | DATE | "A. SHANKAR NARAYANA", "B.N. Srikrishna,", "(Jarat" |
110
+ | GPE | "Hongkong Bank", "HDFC Bank, Noida,", "Rahul & Co." |
111
+ | JUDGE | "Chandigarh", "UP", "Lakhaya," |
112
+ | LAWYER | "the", "Vijay Mishra", "Chandregowda" |
113
+ | ORG | "The", "A. Sandeep", "For" |
114
+ | OTHER_PERSON | "Indian Income-tax Act", "POTA", "Indian Income-tax Act, 1922," |
115
+ | PETITIONER | "Supreme Court.", "Supreme Court,", "Sessions Judge Jaipur City," |
116
+ | PRECEDENT | "C.C. Alavi Hazi Vs.Palapetty Mohd. & Anr", "Susamma Thomas, 1994 ACJ 1 (SC),", "United India Insurance Co. Ltd. v. Rajendra Singh" |
117
+ | PROVISION | "Jagdish Prasad Sharma,", "Bhanwarial,", "Amarsingh," |
118
+ | RESPONDENT | "19.8.1998", "28 March, 1959,", "29.4.1968," |
119
+ | STATUTE | "Kaur,", "Tarlochan Singh.", "Agya" |
120
+ | WITNESS | "Manju", "Sameer.", "Abid @ Guddu" |
121
+
122
+ ## Uses
123
+
124
+ ### Direct Use for Inference
125
+
126
+ ```python
127
+ from span_marker import SpanMarkerModel
128
+
129
+ # Download from the 🤗 Hub
130
+ model = SpanMarkerModel.from_pretrained("lambdavi/span-marker-luke-legal")
131
+ # Run inference
132
+ entities = model.predict("The petition was filed through Sh. Vijay Pahwa, General Power of Attorney and it was asserted in the petition under Section 13-B of the Rent Act that 1 of 23 50% share of the demised premises had been purchased by the landlord from Sh. Vinod Malhotra vide sale deed No.4226 registered on 20.12.2007 with Sub Registrar, Chandigarh.")
133
+ ```
134
+
135
+ ### Downstream Use
136
+ You can finetune this model on your own dataset.
137
+
138
+ <details><summary>Click to expand</summary>
139
+
140
+ ```python
141
+ from span_marker import SpanMarkerModel, Trainer
142
+
143
+ # Download from the 🤗 Hub
144
+ model = SpanMarkerModel.from_pretrained("lambdavi/span-marker-luke-legal")
145
+
146
+ # Specify a Dataset with "tokens" and "ner_tag" columns
147
+ dataset = load_dataset("conll2003") # For example CoNLL2003
148
+
149
+ # Initialize a Trainer using the pretrained model & dataset
150
+ trainer = Trainer(
151
+ model=model,
152
+ train_dataset=dataset["train"],
153
+ eval_dataset=dataset["validation"],
154
+ )
155
+ trainer.train()
156
+ trainer.save_model("lambdavi/span-marker-luke-legal-finetuned")
157
+ ```
158
+ </details>
159
+
160
+ <!--
161
+ ### Out-of-Scope Use
162
+
163
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
164
+ -->
165
+
166
+ <!--
167
+ ## Bias, Risks and Limitations
168
+
169
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
170
+ -->
171
+
172
+ <!--
173
+ ### Recommendations
174
+
175
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
176
+ -->
177
+
178
+ ## Training Details
179
+
180
+ ### Training Set Metrics
181
+ | Training set | Min | Median | Max |
182
+ |:----------------------|:----|:--------|:-----|
183
+ | Sentence length | 3 | 44.5113 | 2795 |
184
+ | Entities per sentence | 0 | 2.7232 | 68 |
185
+
186
+ ### Training Hyperparameters
187
+ - learning_rate: 0.0001
188
+ - train_batch_size: 8
189
+ - eval_batch_size: 8
190
+ - seed: 42
191
+ - gradient_accumulation_steps: 2
192
+ - total_train_batch_size: 16
193
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
194
+ - lr_scheduler_type: linear
195
+ - lr_scheduler_warmup_ratio: 0.06
196
+ - num_epochs: 5
197
+
198
+ ### Training Results
199
+ | Epoch | Step | Validation Loss | Validation Precision | Validation Recall | Validation F1 | Validation Accuracy |
200
+ |:------:|:----:|:---------------:|:--------------------:|:-----------------:|:-------------:|:-------------------:|
201
+ | 0.9997 | 1837 | 0.0137 | 0.7773 | 0.7994 | 0.7882 | 0.9577 |
202
+ | 2.0 | 3675 | 0.0090 | 0.8751 | 0.8348 | 0.8545 | 0.9697 |
203
+ | 2.9997 | 5512 | 0.0077 | 0.8777 | 0.8959 | 0.8867 | 0.9770 |
204
+ | 4.0 | 7350 | 0.0061 | 0.8941 | 0.9083 | 0.9011 | 0.9811 |
205
+ | 4.9986 | 9185 | 0.0064 | 0.9090 | 0.9110 | 0.9100 | 0.9824 |
206
+
207
+ ### Framework Versions
208
+ - Python: 3.10.12
209
+ - SpanMarker: 1.5.0
210
+ - Transformers: 4.36.0
211
+ - PyTorch: 2.0.0
212
+ - Datasets: 2.17.1
213
+ - Tokenizers: 0.15.0
214
+
215
+ ## Citation
216
+
217
+ ### BibTeX
218
+ ```
219
+ @software{Aarsen_SpanMarker,
220
+ author = {Aarsen, Tom},
221
+ license = {Apache-2.0},
222
+ title = {{SpanMarker for Named Entity Recognition}},
223
+ url = {https://github.com/tomaarsen/SpanMarkerNER}
224
+ }
225
+ ```
226
+
227
+ <!--
228
+ ## Glossary
229
+
230
+ *Clearly define terms in order to be accessible across audiences.*
231
+ -->
232
+
233
+ <!--
234
+ ## Model Card Authors
235
+
236
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
237
+ -->
238
+
239
+ <!--
240
+ ## Model Card Contact
241
+
242
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
243
+ -->