Downloads · 30 days
10
9% of all-time downloads
SallySims/equibert-awareness-scorer
equibert-awareness-scorer is a text classification model from SallySims. Use it when you need a label for a piece of text. The card lists the license as apache-2.0.
Model ID: SallySims/equibert-awareness-scorer
Downloads · 30 days
10
9% of all-time downloads
All-time downloads
114
Public
Parameters
311M
2.6 GB on disk
Likes
0
Public
Click a slice to open those files.
.bin877 MB · 50%
How the weights are stored.
F16184M · 59%
From the Hugging Face model README
Model ID: SallySims/equibert-awareness-scorer
Scores individual statements and reflections on a five-level DEI awareness continuum — from pre-awareness through to structural advocacy.
| Index | Dimension |
|---|---|
| 0 | awareness_score — overall level (main score) |
| 1 | self_awareness — recognises own biases |
| 2 | systemic_awareness — understands structural causes |
| 3 | empathy_depth — centres others' experiences |
| 4 | allyship_action — acts beyond awareness |
| 5 | intersectional_lens — holds multiple identities |
| 6 | growth_orientation — committed to continuous learning |
| Score | Level | Description |
|---|---|---|
| 0.0–0.2 | LEVEL_1 | Pre-awareness — meritocracy belief, colourblind |
| 0.2–0.4 | LEVEL_2 | Awareness — beginning to recognise bias |
| 0.4–0.6 | LEVEL_3 | Understanding — grasps systemic dimension |
| 0.6–0.8 | LEVEL_4 | Active learning — challenging own assumptions |
| 0.8–1.0 | LEVEL_5 | Advocacy — structural action and allyship |
EquiBERT is a multi-task DEI (Diversity, Equity and Inclusion) transformer built on a dual-encoder backbone that fuses RoBERTa-base and DeBERTa-v3-base via a learned weighted sum (α parameter). The fused representation is fed into task-specific heads covering 17 distinct DEI analysis tasks.
Organisation: SallySims Framework: PyTorch + HuggingFace Transformers Backbone: RoBERTa-base + DeBERTa-v3-base (dual encoder, fused) Language: English Domain: Organisational DEI text — HR communications, policies, job descriptions, performance reviews, leadership statements, reports
Input Text
│
├──▶ RoBERTa-base encoder ──▶ Linear projection
│ │
└──▶ DeBERTa-v3-base encoder ──▶ Linear projection
│
Weighted fusion (learned α)
│
Layer Norm + Dropout
│
Task-specific head (see below)
Trained on synthetic DEI organisational text generated by the EquiBERT synthetic data pipeline, covering 20 DEI categories across HR, policy, leadership, and workforce analytics domains. For production use, fine-tune on real labelled DEI data.
If you use EquiBERT in your research, please cite:
@misc{equibert2024,
author = {SallySims},
title = {EquiBERT: A Multi-Task DEI Transformer},
year = {2024},
publisher = {HuggingFace},
url = {https://huggingface.co/SallySims}
}
| Model | Task | Primary Metric |
|---|---|---|
| equibert-bias-classifier | Bias Detection | Macro F1 |
| equibert-microaggression | Microaggression Detection | Macro F1 |
| equibert-category-tagger | DEI Category Tagging | Macro F1 |
| equibert-event-exclusion | Event Exclusion Classification | Macro F1 |
| equibert-inclusive-language | Inclusive Language Scoring | Span F1 |
| equibert-review-auditor | Performance Review Auditing | Span F1 |
| equibert-washing-detector | DEI Washing Detection | MAE |
| equibert-framing-scorer | Report Framing Scoring | MAE |
| equibert-awareness-scorer | DEI Awareness Scoring | MAE |
| equibert-similarity | Semantic Similarity | Accuracy |
| equibert-ner | DEI Entity Recognition | Span F1 |
| equibert-relation-extraction | Relation Extraction | Macro F1 |
| equibert-qa | Extractive QA | Span EM |
| equibert-search | Semantic Search | MRR@10 |
| equibert-nli | NLI / Textual Entailment | Macro F1 |
| equibert-generator | DEI Text Generation | ROUGE-L |