Upload folder using huggingface_hub

README.md

@@ -0,0 +1,48 @@
+---
+license: cc-by-nc-4.0
+tags:
+- social-media-analysis
+- compulsion-detection
+- political-tweets
+- bayesian-classifier
+- digital-phenotyping
+pipeline_tag: text-classification
+---
+
+# X-Box Compulsion Classifier
+
+Bayesian classifier for detecting compulsive social media usage patterns
+in political Twitter/X accounts.
+
+## Architecture
+
+- **12 classification heads**: 6 CardiffNLP (sentiment, emotion, offensive, irony, hate, toxicity) + 6 custom SetFit (ragebait, tribal signal, performative outrage, epistemic manipulation, engagement bait, agency language)
+- **Compulsion signatures**: Burstiness (Goh-Barabasi), time-of-day entropy, Hawkes self-excitation, night intensity, weekend ratio
+- **Bayesian posterior**: Calibrated P(compulsive | features) with 95% credible intervals
+- **Disorder baseline**: DSM-5-adjacent criteria mapping with clinical thresholds
+
+## Validation
+
+- LOO cross-validation: F1=1.000, AUC=1.000 on 16-account ground truth cohort
+- Ground truth: 8 known-compulsive accounts (Trump Android, Mike Lee, Cruz, Hawley, Blackburn, Rubio, Murphy) + 8 known-strategic accounts (Feinstein, Risch, Tester, etc.)
+
+## Feature Importance
+
+| Feature | Mean |LLR| |
+|---------|---------|
+| Night intensity (00-05 UTC) | 28.1 |
+| Time-of-day entropy | 8.0 |
+| Burstiness B parameter | 4.8 |
+| Hawkes self-excitation n* | 4.6 |
+| Weekend ratio | 0.05 |
+
+## Theoretical Framework
+
+Inspired by Recovery Viability Theory (Kepner, White, O'Neill):
+- Logit-bounded state space
+- Cusp catastrophe dynamics for sudden behavioral transitions
+- Critical slowing down as early warning signals
+
+## Citation
+
+Research by O'Neill Lab. Not for clinical diagnosis.

bayesian_model_results.json

@@ -0,0 +1,210 @@
+{
+  "model_params": {
+    "prior": {
+      "compulsive": 0.5,
+      "strategic": 0.5
+    },
+    "class_params": {
+      "compulsive": {
+        "burstiness_B": {
+          "mean": 0.3774861927721671,
+          "std": 0.22938978696976464,
+          "n": 8
+        },
+        "time_entropy": {
+          "mean": 4.14209602761983,
+          "std": 0.1735837176764721,
+          "n": 8
+        },
+        "night_intensity": {
+          "mean": 0.2286008328329098,
+          "std": 0.10958901025874938,
+          "n": 8
+        },
+        "hawkes_n": {
+          "mean": 0.9475845074610829,
+          "std": 0.03725061990326155,
+          "n": 8
+        },
+        "weekend_ratio": {
+          "mean": 0.7103416736296673,
+          "std": 0.1981138498143343,
+          "n": 8
+        }
+      },
+      "strategic": {
+        "burstiness_B": {
+          "mean": 0.10522888954988305,
+          "std": 0.08097919025103344,
+          "n": 8
+        },
+        "time_entropy": {
+          "mean": 3.541328083305317,
+          "std": 0.15778381821874674,
+          "n": 8
+        },
+        "night_intensity": {
+          "mean": 0.037430947815364754,
+          "std": 0.022583595321530345,
+          "n": 8
+        },
+        "hawkes_n": {
+          "mean": 0.8163132264766522,
+          "std": 0.06881668997824561,
+          "n": 8
+        },
+        "weekend_ratio": {
+          "mean": 0.6636698298243918,
+          "std": 0.19803933864431938,
+          "n": 8
+        }
+      }
+    },
+    "features": [
+      "burstiness_B",
+      "time_entropy",
+      "night_intensity",
+      "hawkes_n",
+      "weekend_ratio"
+    ],
+    "feature_weights": {
+      "burstiness_B": 1.0,
+      "time_entropy": 1.2,
+      "night_intensity": 1.2,
+      "hawkes_n": 1.0,
+      "weekend_ratio": 0.3
+    }
+  },
+  "cv_results": {
+    "accuracy": 1.0,
+    "f1": 1.0,
+    "precision": 1.0,
+    "recall": 1.0,
+    "auc": 1.0,
+    "n_samples": 16,
+    "confusion_matrix": [
+      [
+        8,
+        0
+      ],
+      [
+        0,
+        8
+      ]
+    ]
+  },
+  "cv_details": [
+    {
+      "account": "BasedMikeLee",
+      "true": "compulsive",
+      "pred": "compulsive",
+      "posterior": 1.0,
+      "correct": true
+    },
+    {
+      "account": "Trump_Android",
+      "true": "compulsive",
+      "pred": "compulsive",
+      "posterior": 1.0,
+      "correct": true
+    },
+    {
+      "account": "Trump_Full",
+      "true": "compulsive",
+      "pred": "compulsive",
+      "posterior": 1.0,
+      "correct": true
+    },
+    {
+      "account": "marcorubio",
+      "true": "compulsive",
+      "pred": "compulsive",
+      "posterior": 1.0,
+      "correct": true
+    },
+    {
+      "account": "ChrisMurphyCT",
+      "true": "compulsive",
+      "pred": "compulsive",
+      "posterior": 1.0,
+      "correct": true
+    },
+    {
+      "account": "HawleyMO",
+      "true": "compulsive",
+      "pred": "compulsive",
+      "posterior": 0.9996,
+      "correct": true
+    },
+    {
+      "account": "SenTedCruz",
+      "true": "compulsive",
+      "pred": "compulsive",
+      "posterior": 1.0,
+      "correct": true
+    },
+    {
+      "account": "MarshaBlackburn",
+      "true": "compulsive",
+      "pred": "compulsive",
+      "posterior": 1.0,
+      "correct": true
+    },
+    {
+      "account": "SenatorCollins",
+      "true": "strategic",
+      "pred": "strategic",
+      "posterior": 0.0002,
+      "correct": true
+    },
+    {
+      "account": "SenGillibrand",
+      "true": "strategic",
+      "pred": "strategic",
+      "posterior": 0.0,
+      "correct": true
+    },
+    {
+      "account": "SenJohnHoeven",
+      "true": "strategic",
+      "pred": "strategic",
+      "posterior": 0.0,
+      "correct": true
+    },
+    {
+      "account": "SenShelby",
+      "true": "strategic",
+      "pred": "strategic",
+      "posterior": 0.0,
+      "correct": true
+    },
+    {
+      "account": "SenHydeSmith",
+      "true": "strategic",
+      "pred": "strategic",
+      "posterior": 0.0,
+      "correct": true
+    },
+    {
+      "account": "SenatorTester",
+      "true": "strategic",
+      "pred": "strategic",
+      "posterior": 0.0,
+      "correct": true
+    },
+    {
+      "account": "SenatorRisch",
+      "true": "strategic",
+      "pred": "strategic",
+      "posterior": 0.0,
+      "correct": true
+    },
+    {
+      "account": "SenFeinstein",
+      "true": "strategic",
+      "pred": "strategic",
+      "posterior": 0.0,
+      "correct": true
+    }
+  ]
+}

cohort_signatures.csv

@@ -0,0 +1,17 @@
+account,category,n_tweets,p_compulsive,classification,burstiness_B,time_entropy,weekend_ratio,night_intensity,hawkes_n,gap_shape,z_state
+BasedMikeLee,compulsive,49415,0.9406263649632571,compulsive,0.7545326278796666,4.208015373082699,0.8377908084105669,0.40184154608924416,0.9837007722574105,power_law,2.7626957258242157
+Trump_Android,compulsive,14545,0.8823061825550056,compulsive,0.5253151861781247,4.284990749399817,1.033448438141054,0.3969749054657958,0.9798360265680514,power_law,2.0144526567129484
+Trump_Full,compulsive,32797,0.875071775820615,compulsive,0.6452797417842915,4.412102033911361,0.7814768927434289,0.22367899503003325,0.9769165070058401,power_law,1.9465665466849962
+marcorubio,compulsive,766,0.7678070462143948,compulsive,0.2524741167614851,4.219965321149076,0.7440161104718067,0.1566579634464752,0.9219944937289691,power_law,1.1959697363233344
+ChrisMurphyCT,compulsive,1283,0.7509103949248175,compulsive,0.19841235471107352,4.146720586553414,0.703444490188006,0.20187061574434917,0.933657627820327,log_normal,1.103473638827422
+HawleyMO,compulsive,499,0.7228518121340829,compulsive,0.24958015504551243,3.9194049186207964,0.7014571331751949,0.14228456913827656,0.8735398679532758,power_law,0.9586519012961181
+SenTedCruz,compulsive,1723,0.6980689954332613,compulsive,0.23902570871834355,3.961771111478407,0.4073355263157895,0.1323273360417876,0.9504588739607008,power_law,0.8381194156289073
+MarshaBlackburn,compulsive,2050,0.6948594811223766,compulsive,0.1552696510988397,3.9837981267630704,0.47376398959149135,0.17317073170731706,0.9605718903940886,log_normal,0.8229372515459503
+SenatorCollins,strategic,232,0.6322980420959895,mixed,0.09764735011166781,3.785114614422353,0.9807692307692308,0.08620689655172414,0.72,log_normal,0.5420881555550405
+SenGillibrand,strategic,524,0.5746443007024875,mixed,-0.017533957525227656,3.632842523682244,0.6962025316455697,0.03625954198473282,0.8443915501338887,log_normal,0.3008254834974807
+SenJohnHoeven,strategic,330,0.5741204562695057,mixed,0.05252092123115066,3.6349489923808225,0.6592713209851414,0.048484848484848485,0.7715277777777778,log_normal,0.29868268334246456
+SenShelby,strategic,205,0.5718305322286668,mixed,0.1351874084196579,3.401485372907101,0.89586969168121,0.02926829268292683,0.7272727272727273,log_normal,0.28932360520501765
+SenHydeSmith,strategic,553,0.5654565962665936,mixed,0.03903979866952534,3.6503894273604685,0.6369230769230769,0.018083182640144666,0.8526821457165733,log_normal,0.26333770653226224
+SenatorTester,strategic,604,0.5642272020191504,mixed,0.12048563517633806,3.4525234462090433,0.551470588235294,0.039735099337748346,0.8724079559881507,log_normal,0.2583360088612716
+SenatorRisch,strategic,462,0.5458959564095442,mixed,0.17832433600182634,3.4591774752403817,0.513530522341095,0.015151515151515152,0.834529791816224,log_normal,0.18410205887052772
+SenFeinstein,strategic,914,0.5423587988964276,mixed,0.23615962431412627,3.3141428142401184,0.3753216760145167,0.0262582056892779,0.9076938631078758,log_normal,0.1698422996151933

setfit_agency_language/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
+}

setfit_agency_language/README.md

@@ -0,0 +1,210 @@
+---
+tags:
+- setfit
+- sentence-transformers
+- text-classification
+- generated_from_setfit_trainer
+widget:
+- text: 'RT @BasedMikeLee: If she didn’t know of Biden’s condition all along, then—by
+    repeatedly and emphatically telling us Biden was fit for offic…'
+- text: 'One more win and the @braves take the #WorldSeriesweve got this, yall! #BattleATL
+    https://t.co/iEw8Nx7LIP'
+- text: While SCOTUS has allowed challenges to SB to proceed, it's outrageous that
+    the Court has again decided not to block Texas' unconstitutional abortion ban.
+    More Texans are harmed every day this law is allowed to stand. The Senate must
+    pass the Women's Health Protection Act.
+- text: The @TulsiGabbard vote needs to be public  Her nomination isn’t classified  The
+    vote on her nomination shouldn’t be treated as if it were https://t.co/Rd4RfFxWmF
+- text: 'The Executive Branch should be under the direction of the president   That’s
+    how the Constitution was designed   The Federal Reserve is one of many examples
+    of how we’ve deviated from the Constitution in that regard   Yet another reason
+    why we should #EndTheFed https://t.co/qfW7tFdhe8'
+metrics:
+- accuracy
+pipeline_tag: text-classification
+library_name: setfit
+inference: true
+base_model: sentence-transformers/all-mpnet-base-v2
+model-index:
+- name: SetFit with sentence-transformers/all-mpnet-base-v2
+  results:
+  - task:
+      type: text-classification
+      name: Text Classification
+    dataset:
+      name: Unknown
+      type: unknown
+      split: test
+    metrics:
+    - type: accuracy
+      value: 0.8375
+      name: Accuracy
+---
+
+# SetFit with sentence-transformers/all-mpnet-base-v2
+
+This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-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.
+
+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 body:** [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2)
+- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
+- **Maximum Sequence Length:** 384 tokens
+- **Number of Classes:** 2 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)
+
+### Model Labels
+| Label | Examples                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
+|:------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| 0     | <ul><li>"President Joe Biden just signed the #AmericanRescuePlan. Help is on the way. I'll say it again: Thank God for Georgia."</li><li>'@1stacyphillips Odd that he didn’t tell us himself'</li><li>'Stablecoins pose risks to consumers and  to our economy. Theyre propping up one of the shadiest parts of the crypto world, DeFi, where consumers are least protected from getting scammed. Our regulators need to get serious about clamping down before it is too late. https://t.co/hMOT1HIQgn'</li></ul>                                       |
+| 1     | <ul><li>'Hassan Sheikh Mohamud, the president of Somalia, is *not* “our president���  It’s troubling that any member of Congress—regardless of her party affiliation or national origin—would suggest otherwise   Who’s with me? https://t.co/7NBXuQeu6R https://t.co/AgfvVWL4PD'</li><li>'RT @BasedMikeLee: This familiar headline—“Congress announces a deal to avoid a shutdown”—is premature &amp; misleading.   “Congress” hasn’t eve…'</li><li>'El Salvador is safe because @nayibbukele locked up the people who had long made it unsafe'</li></ul> |
+
+## Evaluation
+
+### Metrics
+| Label   | Accuracy |
+|:--------|:---------|
+| **all** | 0.8375   |
+
+## 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("setfit_model_id")
+# Run inference
+preds = model("One more win and the @braves take the #WorldSeriesweve got this, yall! #BattleATL https://t.co/iEw8Nx7LIP")
+```
+
+<!--
+### 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   | 2   | 25.8156 | 57  |
+
+| Label | Training Sample Count |
+|:------|:----------------------|
+| 0     | 158                   |
+| 1     | 162                   |
+
+### Training Hyperparameters
+- batch_size: (16, 16)
+- num_epochs: (1, 1)
+- max_steps: -1
+- sampling_strategy: oversampling
+- num_iterations: 5
+- 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: False
+
+### Training Results
+| Epoch | Step | Training Loss | Validation Loss |
+|:-----:|:----:|:-------------:|:---------------:|
+| 0.005 | 1    | 0.5111        | -               |
+| 0.25  | 50   | 0.2576        | -               |
+| 0.5   | 100  | 0.1736        | -               |
+| 0.75  | 150  | 0.0497        | -               |
+| 1.0   | 200  | 0.0204        | -               |
+
+### Framework Versions
+- Python: 3.12.3
+- SetFit: 1.1.3
+- Sentence Transformers: 5.3.0
+- Transformers: 4.57.6
+- PyTorch: 2.10.0+cpu
+- Datasets: 4.8.3
+- Tokenizers: 0.22.2
+
+## 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.*
+-->

setfit_agency_language/config.json

@@ -0,0 +1,23 @@
+{
+  "architectures": [
+    "MPNetModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "mpnet",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "relative_attention_num_buckets": 32,
+  "transformers_version": "4.57.6",
+  "vocab_size": 30527
+}

setfit_agency_language/config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "sentence_transformers": "5.3.0",
+    "transformers": "4.57.6",
+    "pytorch": "2.10.0+cpu"
+  },
+  "model_type": "SentenceTransformer",
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

setfit_agency_language/config_setfit.json

@@ -0,0 +1,4 @@
+{
+  "labels": null,
+  "normalize_embeddings": false
+}

setfit_agency_language/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ffba55d5078f6853e0f2ba7861b3f1867289354b9248c358f835877407a44ff
+size 437967672

setfit_agency_language/model_head.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5818380ccbf4631b795e15086104391abc774bb1e42d81c250071ec707b50329
+size 7007

setfit_agency_language/modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

setfit_agency_language/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 384,
+    "do_lower_case": false
+}

setfit_agency_language/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

setfit_agency_language/tokenizer_config.json

@@ -0,0 +1,73 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30526": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 384,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MPNetTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

setfit_engagement_bait/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
+}

setfit_engagement_bait/README.md

@@ -0,0 +1,204 @@
+---
+tags:
+- setfit
+- sentence-transformers
+- text-classification
+- generated_from_setfit_trainer
+widget:
+- text: 'Congratulations to Floridians @eddyalvarez90, Nick Martinez and Tristian
+    Casas for winning silver in baseball at the #Tokyo2020 Olympics! Keep up this
+    great work. https://t.co/QUQQYjcNSk'
+- text: Saudi Arabia should fight their own wars, which they won't, or pay us an absolute
+    fortune to protect them and their great wealth-$ trillion!
+- text: Mmmm.  So much logic happening here. https://t.co/vuVETxXUU7
+- text: Who’s not ready for “Mamala the Country”? https://t.co/ROT1RXTOHH
+- text: 'Big Balls for the Medal of Freedom  Who agrees? #FederalizeDC'
+metrics:
+- accuracy
+pipeline_tag: text-classification
+library_name: setfit
+inference: true
+base_model: sentence-transformers/all-mpnet-base-v2
+model-index:
+- name: SetFit with sentence-transformers/all-mpnet-base-v2
+  results:
+  - task:
+      type: text-classification
+      name: Text Classification
+    dataset:
+      name: Unknown
+      type: unknown
+      split: test
+    metrics:
+    - type: accuracy
+      value: 0.8
+      name: Accuracy
+---
+
+# SetFit with sentence-transformers/all-mpnet-base-v2
+
+This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-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.
+
+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 body:** [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2)
+- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
+- **Maximum Sequence Length:** 384 tokens
+- **Number of Classes:** 2 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)
+
+### Model Labels
+| Label | Examples                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     |
+|:------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| 0     | <ul><li>'Those closest to the disease should be the closest to the vaccine. Thats the moment were in." - @macurry01 @MassLeague https://t.co/wDB80seVEC'</li><li>'The Pioneers for Womans Suffrage statue can be found in the US Capitol Rotunda. It celebrates those who led the way for womens right to vote #realhistorychannel #womenshistorymonth @ United States Capitol https://t.co/7D3Xr3uAID'</li><li>'Last week I was proud to introduce my Improving Care for Veterans Actwhich would raise the standard of care in Veterans Homes to better protect our courageous veterans, prevent outbreaks and improve health outcomes for our heroes in Georgia and nationwide.'</li></ul> |
+| 1     | <ul><li>'So … why didn’t they beef up Trump’s security detail after learning of an Iranian plot to assassinate him?  It seems likely that this would’ve thwarted what happened on Saturday. https://t.co/qn4NkryBkl'</li><li>'Who else would like once again to be able to buy “real” light bulbs, showerheads, and household appliances—i.e., these products as they existed before federal bureaucrats ruined them by forcing manufacturers to comply with rigid energy- and water-efficiency standards?'</li><li>'Who else voted for this? https://t.co/TTKaTaahEI'</li></ul>                                                                                                             |
+
+## Evaluation
+
+### Metrics
+| Label   | Accuracy |
+|:--------|:---------|
+| **all** | 0.8      |
+
+## 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("setfit_model_id")
+# Run inference
+preds = model("Mmmm.  So much logic happening here. https://t.co/vuVETxXUU7")
+```
+
+<!--
+### 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   | 1   | 22.1375 | 60  |
+
+| Label | Training Sample Count |
+|:------|:----------------------|
+| 0     | 158                   |
+| 1     | 162                   |
+
+### Training Hyperparameters
+- batch_size: (16, 16)
+- num_epochs: (1, 1)
+- max_steps: -1
+- sampling_strategy: oversampling
+- num_iterations: 5
+- 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: False
+
+### Training Results
+| Epoch | Step | Training Loss | Validation Loss |
+|:-----:|:----:|:-------------:|:---------------:|
+| 0.005 | 1    | 0.4707        | -               |
+| 0.25  | 50   | 0.2633        | -               |
+| 0.5   | 100  | 0.2054        | -               |
+| 0.75  | 150  | 0.0767        | -               |
+| 1.0   | 200  | 0.0234        | -               |
+
+### Framework Versions
+- Python: 3.12.3
+- SetFit: 1.1.3
+- Sentence Transformers: 5.3.0
+- Transformers: 4.57.6
+- PyTorch: 2.10.0+cpu
+- Datasets: 4.8.3
+- Tokenizers: 0.22.2
+
+## 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.*
+-->

setfit_engagement_bait/config.json

@@ -0,0 +1,23 @@
+{
+  "architectures": [
+    "MPNetModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "mpnet",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "relative_attention_num_buckets": 32,
+  "transformers_version": "4.57.6",
+  "vocab_size": 30527
+}

setfit_engagement_bait/config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "sentence_transformers": "5.3.0",
+    "transformers": "4.57.6",
+    "pytorch": "2.10.0+cpu"
+  },
+  "model_type": "SentenceTransformer",
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

setfit_engagement_bait/config_setfit.json

@@ -0,0 +1,4 @@
+{
+  "labels": null,
+  "normalize_embeddings": false
+}

setfit_engagement_bait/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89716348b8b0105e8838a547f6a45b091697bd9ef70bef472e14361c753f767b
+size 437967672

setfit_engagement_bait/model_head.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35d91fe08a147c561a79c0100b29170f012e7c79467abec89f2e659fc23b7ceb
+size 7007

setfit_engagement_bait/modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

setfit_engagement_bait/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 384,
+    "do_lower_case": false
+}

setfit_engagement_bait/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

setfit_engagement_bait/tokenizer_config.json

@@ -0,0 +1,73 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30526": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 384,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MPNetTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

setfit_epistemic_manipulation/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
+}

setfit_epistemic_manipulation/README.md

@@ -0,0 +1,201 @@
+---
+tags:
+- setfit
+- sentence-transformers
+- text-classification
+- generated_from_setfit_trainer
+widget:
+- text: 'Democrats two months ago: “Noncitizens don’t vote—or even *register* to vote.”  Democrats
+    now: “We’re suing states that try to remove noncitizens from voter rolls.”'
+- text: Who else wishes we could swear in Trump tomorrow?
+- text: Should we take the remittance tax to 35%? https://t.co/rBKwjuBu1S
+- text: Good idea, right? https://t.co/XyoWzUzT4a
+- text: I’ve found another good defamation lawsuit for the estate of Charlie Kirk
+    to bring  Charlie was *none* of the things this headline falsely accuses him of
+    being  Who else finds this reprehensible? https://t.co/LdS3XqY9pL
+metrics:
+- accuracy
+pipeline_tag: text-classification
+library_name: setfit
+inference: true
+base_model: sentence-transformers/all-mpnet-base-v2
+model-index:
+- name: SetFit with sentence-transformers/all-mpnet-base-v2
+  results:
+  - task:
+      type: text-classification
+      name: Text Classification
+    dataset:
+      name: Unknown
+      type: unknown
+      split: test
+    metrics:
+    - type: accuracy
+      value: 0.8
+      name: Accuracy
+---
+
+# SetFit with sentence-transformers/all-mpnet-base-v2
+
+This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-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.
+
+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 body:** [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2)
+- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
+- **Maximum Sequence Length:** 384 tokens
+- **Number of Classes:** 2 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)
+
+### Model Labels
+| Label | Examples                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
+|:------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| 1     | <ul><li>'RT @realDonaldTrump: Wow! York County, Pennsylvania, received THOUSANDS of potentially FRAUDULENT Voter Registration Forms and Mail-In Ball…'</li><li>'Only an enemy would do this to another country   Only a traitor would do it to his own  Share if you agree that there must be consequences for this betrayal https://t.co/BkqsRstugX'</li><li>'I hope @Kash_Patel fires the “Patriot Front” wing of the FBI before tomorrow morning https://t.co/hcyGgidDbu'</li></ul> |
+| 0     | <ul><li>'Is @JDVance the GOAT Vice President of the United States?  A—Yes  B—No https://t.co/yoZH89jkpx'</li><li>'I’m grateful to @elonmusk for buying Twitter  And turning it into X  Raise your hand if you agree https://t.co/ToOjLY56xU'</li><li>'🚨 I’m thrilled to receive the news that Senator Susan Collins has announced her support for the SAVE America Act!🚨   This is huge! https://t.co/PxAvRD2C5N'</li></ul>                                                            |
+
+## Evaluation
+
+### Metrics
+| Label   | Accuracy |
+|:--------|:---------|
+| **all** | 0.8      |
+
+## 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("setfit_model_id")
+# Run inference
+preds = model("Good idea, right? https://t.co/XyoWzUzT4a")
+```
+
+<!--
+### 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   | 2   | 25.1625 | 106 |
+
+| Label | Training Sample Count |
+|:------|:----------------------|
+| 0     | 41                    |
+| 1     | 39                    |
+
+### Training Hyperparameters
+- batch_size: (16, 16)
+- num_epochs: (1, 1)
+- max_steps: -1
+- sampling_strategy: oversampling
+- num_iterations: 5
+- 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: False
+
+### Training Results
+| Epoch | Step | Training Loss | Validation Loss |
+|:-----:|:----:|:-------------:|:---------------:|
+| 0.02  | 1    | 0.3921        | -               |
+| 1.0   | 50   | 0.2153        | -               |
+
+### Framework Versions
+- Python: 3.12.3
+- SetFit: 1.1.3
+- Sentence Transformers: 5.3.0
+- Transformers: 4.57.6
+- PyTorch: 2.10.0+cpu
+- Datasets: 4.8.3
+- Tokenizers: 0.22.2
+
+## 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.*
+-->

setfit_epistemic_manipulation/config.json

@@ -0,0 +1,23 @@
+{
+  "architectures": [
+    "MPNetModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "mpnet",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "relative_attention_num_buckets": 32,
+  "transformers_version": "4.57.6",
+  "vocab_size": 30527
+}

setfit_epistemic_manipulation/config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "sentence_transformers": "5.3.0",
+    "transformers": "4.57.6",
+    "pytorch": "2.10.0+cpu"
+  },
+  "model_type": "SentenceTransformer",
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

setfit_epistemic_manipulation/config_setfit.json

@@ -0,0 +1,4 @@
+{
+  "normalize_embeddings": false,
+  "labels": null
+}

setfit_epistemic_manipulation/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21af567e3db9aaa645421df60d72e2a000c6b8819ef16fdaf2fcab95f7f12780
+size 437967672

setfit_epistemic_manipulation/model_head.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eb09e0eb43d28b5b1b4e45484bc4f7362972da5087c339f2c1fd369598f52c4
+size 7007

setfit_epistemic_manipulation/modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

setfit_epistemic_manipulation/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 384,
+    "do_lower_case": false
+}

setfit_epistemic_manipulation/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

setfit_epistemic_manipulation/tokenizer_config.json

@@ -0,0 +1,73 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30526": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 384,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MPNetTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

setfit_performative_outrage/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
+}

setfit_performative_outrage/README.md

@@ -0,0 +1,212 @@
+---
+tags:
+- setfit
+- sentence-transformers
+- text-classification
+- generated_from_setfit_trainer
+widget:
+- text: President Erdogans free pass from the Trump White House to commit abuses has
+    officially expired. My legislation with @RonWyden and @SenJeffMerkley makes clear
+    that President Biden must use all diplomatic tools to hold the Erdogan government
+    accountable. https://t.co/ker7Y54wsz
+- text: Every day reports of how the open border policy of Pres Biden is enriching
+    cartel bc no migrant can get in US w/o paying cartel All adding up to multi million
+    $$ every wk Open borders also national security issue when we arrest ppl on our
+    terrorist list
+- text: '@SASCGOP Alabama wins in #FY22NDAA include funding authorizations for: hypersonic
+    development and  testing at Huntsvilles Missile Defense Agency repair and  maintenance
+    at Dannelly Field barracks renovations at Ft. Rucker Expeditionary Fast Transport
+    vessels to be built in Mobile'
+- text: America is the land of the free because we are the home of the brave. Someone
+    please tell Biden what brave means.
+- text: The radical left hates SCOTUS because it’s no longer willing to improperly
+    advance and protect the radical left’s legislative agenda.
+metrics:
+- accuracy
+pipeline_tag: text-classification
+library_name: setfit
+inference: true
+base_model: sentence-transformers/all-mpnet-base-v2
+model-index:
+- name: SetFit with sentence-transformers/all-mpnet-base-v2
+  results:
+  - task:
+      type: text-classification
+      name: Text Classification
+    dataset:
+      name: Unknown
+      type: unknown
+      split: test
+    metrics:
+    - type: accuracy
+      value: 0.85
+      name: Accuracy
+---
+
+# SetFit with sentence-transformers/all-mpnet-base-v2
+
+This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-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.
+
+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 body:** [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2)
+- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
+- **Maximum Sequence Length:** 384 tokens
+- **Number of Classes:** 2 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)
+
+### Model Labels
+| Label | Examples                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    |
+|:------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| 0     | <ul><li>'@RyanGreenfield_ Folded napkin in lap.'</li><li>'As we reflect, we should acknowledge the dark underbelly of mistrust and fear that reared its ugly head, particularly against Muslim, Middle Eastern, North African, and wider South Asian communities.'</li><li>'Dems rammed thru $1.9T under guise of COVID relief when Republicans proposed providing same relief for fraction of cost. Biden now proposing bills for $4 trillion+ w a grab bag of items. Total Biden extra spending over X annual discretionary budget incl military, schools, etc'</li></ul> |
+| 1     | <ul><li>'Later today I’ll be calling up the SAVE Act on the Senate floor, seeking immediate passage.  It makes sense to oppose this bill only if you want noncitizens to vote.'</li><li>'@beaustin24 Make America Flat Again'</li><li>'Who else is frustrated that we still know almost *nothing* about either of the guys who tried to kill Trump last summer?'</li></ul>                                                                                                                                                                                                  |
+
+## Evaluation
+
+### Metrics
+| Label   | Accuracy |
+|:--------|:---------|
+| **all** | 0.85     |
+
+## 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("setfit_model_id")
+# Run inference
+preds = model("America is the land of the free because we are the home of the brave. Someone please tell Biden what brave means.")
+```
+
+<!--
+### 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   | 1   | 23.8813 | 58  |
+
+| Label | Training Sample Count |
+|:------|:----------------------|
+| 0     | 158                   |
+| 1     | 162                   |
+
+### Training Hyperparameters
+- batch_size: (16, 16)
+- num_epochs: (1, 1)
+- max_steps: -1
+- sampling_strategy: oversampling
+- num_iterations: 5
+- 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: False
+
+### Training Results
+| Epoch | Step | Training Loss | Validation Loss |
+|:-----:|:----:|:-------------:|:---------------:|
+| 0.005 | 1    | 0.4729        | -               |
+| 0.25  | 50   | 0.2338        | -               |
+| 0.5   | 100  | 0.1118        | -               |
+| 0.75  | 150  | 0.0188        | -               |
+| 1.0   | 200  | 0.003         | -               |
+
+### Framework Versions
+- Python: 3.12.3
+- SetFit: 1.1.3
+- Sentence Transformers: 5.3.0
+- Transformers: 4.57.6
+- PyTorch: 2.10.0+cpu
+- Datasets: 4.8.3
+- Tokenizers: 0.22.2
+
+## 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.*
+-->

setfit_performative_outrage/config.json

@@ -0,0 +1,23 @@
+{
+  "architectures": [
+    "MPNetModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "mpnet",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "relative_attention_num_buckets": 32,
+  "transformers_version": "4.57.6",
+  "vocab_size": 30527
+}

setfit_performative_outrage/config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "sentence_transformers": "5.3.0",
+    "transformers": "4.57.6",
+    "pytorch": "2.10.0+cpu"
+  },
+  "model_type": "SentenceTransformer",
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

setfit_performative_outrage/config_setfit.json

@@ -0,0 +1,4 @@
+{
+  "labels": null,
+  "normalize_embeddings": false
+}

setfit_performative_outrage/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9b270225a8e8e82b072cdd9727ea2be52e7ec26077cf774e165ce070e1bc397
+size 437967672

setfit_performative_outrage/model_head.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20acfa973d206bea711e9b5b8d88fe657b355bedf0cd3248f5e6aa490660b1b1
+size 7007

setfit_performative_outrage/modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]