card: ModernBERT SST-2 sentiment, 0.9461

README.md

@@ -0,0 +1,113 @@
+---
+base_model: answerdotai/ModernBERT-base
+base_model_relation: finetune
+datasets:
+- nyu-mll/glue
+license: apache-2.0
+language:
+- en
+pipeline_tag: text-classification
+library_name: transformers
+widget:
+- text: This movie was absolutely wonderful, a joy from start to finish.
+- text: The plot was a mess and the acting felt phoned in.
+- text: Support resolved my issue in minutes — genuinely impressed.
+tags:
+- sentiment-analysis
+- sentiment
+- text-classification
+- sst-2
+- sst2
+- modernbert
+- reviews
+- english
+- positive-negative
+- distilbert-sst2-alternative
+---
+
+# 💬 ModernBERT Sentiment Analysis
+
+### The modern replacement for the classic SST-2 sentiment model — **0.946 vs 0.913** on the exact same benchmark, one `pipeline()` line.
+
+```python
+from transformers import pipeline
+
+clf = pipeline("text-classification", model="AnkitAI/ModernBERT-Sentiment-Analysis")
+clf("This movie was absolutely wonderful!")
+# [{'label': 'positive', 'score': 0.99}]
+```
+
+**positive / negative** for reviews, comments, feedback, social text. Built on [ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) — Flash-Attention-fast, 149M params, CPU-friendly.
+
+---
+
+## 📊 Benchmarks
+
+SST-2 official validation set (872 examples) — the same split every SST-2 model reports on:
+
+| Model | Accuracy |
+|---|---|
+| 💬 **This model** | **0.9461** |
+| distilbert-base-uncased-finetuned-sst-2-english (the 3.9M-downloads/month default) | 0.9130 |
+
+**+3.3 points over the model most pipelines still default to** — from an encoder released five years later. Training script and raw eval outputs ship in this repo; the reported split was never used for training or checkpoint selection.
+
+## 🏷 Labels
+
+| id | label |
+|---|---|
+| 0 | negative |
+| 1 | positive |
+
+**Batch scoring:**
+
+```python
+texts = ["Best purchase I've made all year.",
+         "Waited 40 minutes and the order was still wrong."]
+for t, r in zip(texts, clf(texts, batch_size=64)):
+    print(f"{r['label']:<9} {r['score']:.2f}  {t}")
+```
+
+## 💼 Built for
+
+- **Product & review analytics** — score feedback streams at scale
+- **Social/comment moderation dashboards** — fast, CPU-deployable
+- **Drop-in upgrade** — same task and label semantics as the distilbert-sst2 default your stack probably uses
+
+## ⚠️ Good to know
+
+- Two classes only (no neutral) — SST-2 convention; genuinely neutral text gets forced to a side
+- English, sentence/short-paragraph level
+- Trained on movie-review sentences (SST-2); transfers well to general reviews/comments, less so to domain jargon — for financial text use [FinSense](https://huggingface.co/AnkitAI/FinSense-ModernBERT-Financial-News-Sentiment-Analysis)
+
+## 🔧 Training details
+
+Full fine-tune of ModernBERT-base on SST-2 (GLUE, 67k sentences): 2 epochs, lr 2e-5, batch 32, fp32, best checkpoint by held-back 5% of train — the official validation set stayed untouched until final reporting.
+
+## 📖 Citation
+
+```bibtex
+@misc{modernbertsentiment2026,
+  author = {Aglawe, Ankit},
+  title = {ModernBERT Sentiment Analysis},
+  year = {2026},
+  publisher = {Hugging Face},
+  url = {https://huggingface.co/AnkitAI/ModernBERT-Sentiment-Analysis}
+}
+```
+
+## 📚 Base & license
+
+**Apache-2.0** ([ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base), Answer.AI). Trained on [SST-2](https://huggingface.co/datasets/nyu-mll/glue) (Socher et al., 2013 / GLUE).
+
+## 🧭 More from AnkitAI
+
+| Model | Task | Score |
+|---|---|---|
+| [FinSense ModernBERT](https://huggingface.co/AnkitAI/FinSense-ModernBERT-Financial-News-Sentiment-Analysis) | financial news sentiment (3-class) | 0.8675 |
+| [FinSense distilbert v2](https://huggingface.co/AnkitAI/distilbert-base-uncased-financial-news-sentiment-analysis) | financial news sentiment, tiny | 0.8447 |
+| [Parable](https://huggingface.co/collections/AnkitAI/parable-6a4fac60f4b35afca3019621) | local agent LLMs (GGUF) | — |
+
+## 🗂 Version history
+
+- **v1** (2026-07-20) — initial release: ModernBERT-base, SST-2, seed 42.