README.md

---
tags:
- model_hub_mixin
- pytorch_model_hub_mixin
- code
- azure logic
- logic apps
license: mit
datasets:
- albertleigh/az-logic-apps-dataset
language:
- en
base_model:
- google-bert/bert-base-uncased
---

This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
- Code: [More Information Needed]
- Paper: [More Information Needed]
- Docs: [More Information Needed]


### BERT Expression Classifier

Classify whether text is an Azure Logic App expression:

```bash
python clis/run_bert_model.py
```

**Example Session**:
```
Loading model... ✓

============================================================
AzLgcExp BERT Classifier - Interactive CLI
============================================================

> @{body('Parse_JSON')?['content']?['main_text']}

============================================================
Result: Azure Logic App Expression
============================================================
Non-Azure Logic App: 0.0006 (0.06%)
Azure Logic App:     0.9994 (99.94%)

> tokenizer(text, return_tensors='pt')

============================================================
Result: Non-Azure Logic App Expression
============================================================
Non-Azure Logic App: 0.9831 (98.31%)
Azure Logic App:     0.0169 (1.69%)
```


![image](https://cdn-uploads.huggingface.co/production/uploads/695505b065df8d6e6401cced/v7mHHQiSQYtH-7goyh6so.png)

**Repo**: Available on Github
https://github.com/albertleigh/az-lgc-finetuned