Add README.md

README.md

@@ -0,0 +1,75 @@
+---
+license: apache-2.0
+language:
+- en
+library_name: transformers
+pipeline_tag: text-classification
+base_model: distilroberta-base
+datasets:
+- aitrainingdatabroker/synthetic-inbound-inquiries-by-intent
+tags:
+- intent-classification
+- email
+- triage
+- text-classification
+- synthetic
+---
+
+# Inbound Inquiry Intent Classifier
+
+Reads an inbound message to a data business and names its intent out of eight: `seller_interest`, `buyer_request`, `referral_offer`, `press_media`, `vendor_pitch`, `support_question`, `opt_out` or `spam`.
+
+Every name, number and sentence it was trained on is made up. Nothing comes from a real person, customer or business.
+
+## Why it exists
+
+Sorting an inbox by intent lets the right person answer first, and makes sure an opt-out is never missed.
+
+## Use it
+
+```python
+from transformers import pipeline
+
+classify = pipeline("text-classification", model="aitrainingdatabroker/inbound-inquiry-intent-classifier", top_k=3)
+print(classify("Please take our company off your mailing list and confirm it is done."))
+```
+
+## How it was trained
+
+Fine-tuned from `distilroberta-base` for 6 epochs on one RTX 3070. Training data: 458 rows from [synthetic-inbound-inquiries-by-intent](https://huggingface.co/datasets/aitrainingdatabroker/synthetic-inbound-inquiries-by-intent), all invented, with test rows built from templates the model never saw in training. The scripts that built the data and trained the model are in `source/`; the full scores are in `scores.json`.
+
+## Test scores
+
+On 154 held-out rows: accuracy 1.0, macro F1 1.0.
+
+| Label | F1 | Count |
+|---|---|---|
+| `buyer_request` | 1.0 | 20 |
+| `opt_out` | 1.0 | 18 |
+| `press_media` | 1.0 | 19 |
+| `referral_offer` | 1.0 | 19 |
+| `seller_interest` | 1.0 | 20 |
+| `spam` | 1.0 | 20 |
+| `support_question` | 1.0 | 18 |
+| `vendor_pitch` | 1.0 | 20 |
+
+## Limits
+
+- Trained only on invented text from templates, with test sentences built from templates it never saw. Real text varies far more.
+- Never use it alone to suppress a real message: an `opt_out` or `spam` guess should be confirmed by a person.
+- A score of 1.0 on generated text says little about real text: the test sentences are new templates, but they are written in the same plain style. Test it on a labelled sample of your own.
+- This model is not legal advice and not a certification. A person should review its output before anything is shared or decided, and your counsel decides what a rule requires.
+
+## Read more
+
+- [Contact AI Training Data Broker](https://aitrainingdatabroker.com/contact/?utm_source=huggingface&utm_medium=model&utm_campaign=inbound-inquiry-intent-classifier)
+- [The referral program](https://aitrainingdatabroker.com/referral-program/?utm_source=huggingface&utm_medium=model&utm_campaign=inbound-inquiry-intent-classifier)
+- [Free tools](https://aitrainingdatabroker.com/tools/?utm_source=huggingface&utm_medium=model&utm_campaign=inbound-inquiry-intent-classifier)
+
+## License and credit
+
+Apache 2.0. Please credit **AI Training Data Broker** and link to https://aitrainingdatabroker.com/ when you share or build on it.
+
+## About
+
+AI Training Data Broker is a broker and technical advisor for companies that sell or license their data to AI labs. It guides the technical side, including export, format, de-identification and compliance, and publishes free guides, checklists and tools.