Add SetFit model

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,265 @@
+---
+library_name: setfit
+metrics:
+- accuracy
+pipeline_tag: text-classification
+tags:
+- setfit
+- sentence-transformers
+- text-classification
+- generated_from_setfit_trainer
+widget:
+- text: '(a) The terms below are defined for the purposes of this section: (1) Smoke
+    or Smoking means the inhaling, exhaling, burning, or carrying of any lit cigarette,
+    cigar, pipe, or smoking paraphernalia used for consuming the smoke of tobacco
+    or any other burning product. (2) Use means the use of any tobacco product. (3)
+    Residential Space means the private living areas of staff. Residential Space does
+    not include the living areas of incarcerated persons or family visiting areas.
+    Residential space includes, but is not limited to, residential areas at institutions,
+    correctional training academies, and conservation camps. (4) Facility means any
+    building, areas of any building, or group of buildings owned, leased, or utilized
+    by the Department. This shall include, but not be limited to, institutions, conservation
+    camps, community correctional facility, and reentry furlough, and restitution
+    centers. (b) No person shall smoke within 20 feet of any operative window of,
+    entrance/exit to, or within the interior of any state owned or state occupied
+    building, with the following exceptions: (1) Residential spaces of staff excluding
+    correctional training academies, Staff Quarters at conservation camps, and designated
+    non-smoking housing on institutional grounds. For these excluded areas, smoking
+    will be permitted for staff in designated areas at designated times. (2) In areas
+    designated by each institution head for the purpose of approved incarcerated person
+    religious ceremonies as specified. (c) In addition to (b), no person shall smoke
+    in any area that may pose a safety or security risk, e.g., within any fire hazardous
+    areas. (d) Signs shall be posted at entrances of all areas designated no smoking
+    and, as necessary, any other outside areas of a facility not designated for smoking,
+    along with a citation of the authority requiring such prohibition. (e) No person
+    shall smoke in any vehicle that is state-owned or -leased by the state.'
+- text: 'The purpose of this chapter is to set forth the rules and requirements which
+    the Commissioner deems necessary to apply to producers marketing credit insurance
+    coverage, as described in the Alabama Consumer Credit Act, Title 5, Chapter 19,
+    Code of Ala. 1975, (commonly referred to as the "Mini-Code"); the Alabama Small
+    Loan Act, Title 5, Chapter 18, Code of Ala. 1975; the Alabama Insurance Code,
+    Title 27, Code of Ala. 1975; as well as rules and regulations promulgated pursuant
+    to these statutes. This chapter is to clarify future licensing procedures concerning
+    credit insurance and in no way reflects on previous practices. The information
+    required by this chapter is hereby declared to be necessary and appropriate and
+    in the public interest and for the protection of policyholders in this state.
+    Additionally this chapter is to promote the public welfare by regulating credit
+    insurance in this state. Author: Reyn Norman, Associate Counsel'
+- text: 'Creation of this program was directed by Act 94-680, Regular Session 1994,
+    Alabama State Legislature. Concurrently, there was established the State Employee
+    Injury Compensation Trust Fund, with all receipts deposited in the Trust Fund
+    used only to carry out the provisions of Act 94-680. The purpose of the Employee
+    Injury Compensation Program is to provide compensation for employees of the state
+    and its agencies, departments, boards, or commissions, except as excluded by law,
+    who suffer personal injury as a result of accidents arising out of and in the
+    course of their state employment. Terms and conditions of the Program are to be
+    determined by the Director of Finance, State of Alabama. The Program is effective
+    October 1, 1994. The cost of the program and its administration will be paid from
+    the funds appropriated for the operation of state departments, agencies, boards
+    and commissions, to which the Director of Finance may apportion the cost. Author:'
+- text: The purpose of this Part is to establish the new source review (NSR) preconstruction,
+    construction and operation requirements for new and modified facilities in a manner
+    which furthers the policy and objectives of article 19 of the Environmental Conservation
+    Law, and meets the plan requirements for nonattainment areas (part D) and prevention
+    of significant deterioration (PSD) of air quality (part C) of subchapter I of
+    the act.
+- text: '(a) Chapter 864 of the Laws of 1985 amended section 4240 of the Insurance
+    Law (relating to separate accounts) to add to the circumstances in which an insurance
+    company may guarantee the value of assets allocated to a separate account, or
+    any interest therein, or the investment results thereof. The amendment allows
+    such a guarantee to be made if the insurance company submits annually to the superintendent
+    an opinion and memorandum of a qualified actuary, in form and substance satisfactory
+    to the superintendent, that, after taking into account any risk charge payable
+    from the assets of the separate account with respect to such guarantee, the assets
+    in the separate account make good and sufficient provision for the liabilities
+    of the insurance company with respect thereto. (b) Section 4240 of the Insurance
+    Law was also amended to permit the insurance company to value the assets allocated
+    to such a separate account at their market value, and section 4217 was amended
+    to authorize the valuation of the benefits funded by the separate account on a
+    consistent basis. (c) The purpose of this Part is to prescribe: (1) the terms
+    and conditions under which life insurance companies may issue contracts (of the
+    kind described in section 97.2[a] of this Part) that: (i) are funded by separate
+    accounts in which assets are valued at market; and (ii) provide for fixed or guaranteed
+    minimum benefits; (2) the procedures for establishing and maintaining such separate
+    accounts; and (3) the reserve requirements for such contracts and agreements.'
+inference: true
+---
+
+# SetFit
+
+This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
+
+The model has been trained using an efficient few-shot learning technique that involves:
+
+1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
+2. Training a classification head with features from the fine-tuned Sentence Transformer.
+
+## Model Details
+
+### Model Description
+- **Model Type:** SetFit
+<!-- - **Sentence Transformer:** [Unknown](https://huggingface.co/unknown) -->
+- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
+- **Maximum Sequence Length:** 512 tokens
+- **Number of Classes:** 200 classes
+<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
+- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
+- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
+
+## Uses
+
+### Direct Use for Inference
+
+First install the SetFit library:
+
+```bash
+pip install setfit
+```
+
+Then you can load this model and run inference.
+
+```python
+from setfit import SetFitModel
+
+# Download from the 🤗 Hub
+model = SetFitModel.from_pretrained("rkoh/setfit-bert-a6")
+# Run inference
+preds = model("The purpose of this Part is to establish the new source review (NSR) preconstruction, construction and operation requirements for new and modified facilities in a manner which furthers the policy and objectives of article 19 of the Environmental Conservation Law, and meets the plan requirements for nonattainment areas (part D) and prevention of significant deterioration (PSD) of air quality (part C) of subchapter I of the act.")
+```
+
+<!--
+### Downstream Use
+
+*List how someone could finetune this model on their own dataset.*
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Set Metrics
+| Training set | Min        | Median           | Max          |
+|:-------------|:-----------|:-----------------|:-------------|
+| Word count   | tensor(15) | tensor(242.2050) | tensor(4265) |
+
+| Label                          | Training Sample Count |
+|:-------------------------------|:----------------------|
+| Purpose - Regulatory Objective | 0                     |
+| Scope and Applicability        | 0                     |
+| Authority and Legal Basis      | 0                     |
+| Administrative Details         | 0                     |
+| Non-Purpose                    | 0                     |
+
+### Training Hyperparameters
+- batch_size: (32, 32)
+- num_epochs: (1, 1)
+- max_steps: -1
+- sampling_strategy: oversampling
+- num_iterations: 20
+- body_learning_rate: (2e-05, 1e-05)
+- head_learning_rate: 0.01
+- loss: CosineSimilarityLoss
+- distance_metric: cosine_distance
+- margin: 0.25
+- end_to_end: False
+- use_amp: False
+- warmup_proportion: 0.1
+- l2_weight: 0.01
+- seed: 42
+- eval_max_steps: -1
+- load_best_model_at_end: True
+
+### Training Results
+| Epoch | Step | Training Loss | Validation Loss |
+|:-----:|:----:|:-------------:|:---------------:|
+| 0.004 | 1    | 0.3869        | -               |
+| 0.04  | 10   | 0.4354        | -               |
+| 0.08  | 20   | 0.3435        | -               |
+| 0.12  | 30   | 0.2742        | -               |
+| 0.16  | 40   | 0.2615        | -               |
+| 0.2   | 50   | 0.2462        | -               |
+| 0.24  | 60   | 0.2092        | -               |
+| 0.28  | 70   | 0.2323        | -               |
+| 0.32  | 80   | 0.1956        | -               |
+| 0.36  | 90   | 0.2324        | -               |
+| 0.4   | 100  | 0.2026        | -               |
+| 0.44  | 110  | 0.1941        | -               |
+| 0.48  | 120  | 0.1728        | -               |
+| 0.52  | 130  | 0.1674        | -               |
+| 0.56  | 140  | 0.1754        | -               |
+| 0.6   | 150  | 0.1746        | -               |
+| 0.64  | 160  | 0.1502        | -               |
+| 0.68  | 170  | 0.1704        | -               |
+| 0.72  | 180  | 0.1373        | -               |
+| 0.76  | 190  | 0.152         | -               |
+| 0.8   | 200  | 0.15          | -               |
+| 0.84  | 210  | 0.1397        | -               |
+| 0.88  | 220  | 0.135         | -               |
+| 0.92  | 230  | 0.137         | -               |
+| 0.96  | 240  | 0.106         | -               |
+| 1.0   | 250  | 0.1309        | 0.2323          |
+
+### Framework Versions
+- Python: 3.10.12
+- SetFit: 1.1.0
+- Sentence Transformers: 3.2.1
+- Transformers: 4.44.2
+- PyTorch: 2.4.1+cu121
+- Datasets: 3.0.2
+- Tokenizers: 0.19.1
+
+## Citation
+
+### BibTeX
+```bibtex
+@article{https://doi.org/10.48550/arxiv.2209.11055,
+    doi = {10.48550/ARXIV.2209.11055},
+    url = {https://arxiv.org/abs/2209.11055},
+    author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
+    keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
+    title = {Efficient Few-Shot Learning Without Prompts},
+    publisher = {arXiv},
+    year = {2022},
+    copyright = {Creative Commons Attribution 4.0 International}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "/content/drive/My Drive/Fall-2024/models/legal-bert",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_ids": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.2.1",
+    "transformers": "4.44.2",
+    "pytorch": "2.4.1+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

config_setfit.json

@@ -0,0 +1,10 @@
+{
+  "normalize_embeddings": false,
+  "labels": [
+    "Purpose - Regulatory Objective",
+    "Scope and Applicability",
+    "Authority and Legal Basis",
+    "Administrative Details",
+    "Non-Purpose"
+  ]
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0de423173c99ff60b0c234cc275ec27ab1eadbf3c217d3ecc0c2a7df4277ec64
+size 437951328

model_head.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b97dddc6e1e38bf981cdc8b9763a1744a204b4d7c49496af841fffedbc61b1a7
+size 31647

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}