Update README.md
Browse files
README.md
CHANGED
|
@@ -4,4 +4,43 @@ language:
|
|
| 4 |
- en
|
| 5 |
base_model:
|
| 6 |
- google-bert/bert-base-uncased
|
| 7 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
- en
|
| 5 |
base_model:
|
| 6 |
- google-bert/bert-base-uncased
|
| 7 |
+
tags:
|
| 8 |
+
- text-classification
|
| 9 |
+
- bert
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# BERT Fine-tuned on PV-Inspection Reports
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of `bert-base-uncased` on multiple PV inspection reports in the US.
|
| 15 |
+
|
| 16 |
+
## Model Description
|
| 17 |
+
|
| 18 |
+
- **Base model:** bert-base-uncased
|
| 19 |
+
- **Task:** classify type of issue reported
|
| 20 |
+
- **Training data:** PV inspection reports
|
| 21 |
+
|
| 22 |
+
## Intended Uses
|
| 23 |
+
|
| 24 |
+
[Describe what your model is good for]
|
| 25 |
+
|
| 26 |
+
## How to Use
|
| 27 |
+
```python
|
| 28 |
+
from transformers import AutoModelForSequenceClassification, AutoTokenizer
|
| 29 |
+
|
| 30 |
+
model = AutoModelForSequenceClassification.from_pretrained("castelao/pvi-issue-classification")
|
| 31 |
+
tokenizer = AutoTokenizer.from_pretrained("castelao/pvi-issue-classification")
|
| 32 |
+
|
| 33 |
+
# Example usage
|
| 34 |
+
inputs = tokenizer("NEC 110.26 specifies working space clearance about electrical equipment.", return_tensors="pt")
|
| 35 |
+
outputs = model(**inputs)
|
| 36 |
+
```
|
| 37 |
+
|
| 38 |
+
## Training Details
|
| 39 |
+
|
| 40 |
+
- **Training epochs:** [number]
|
| 41 |
+
- **Learning rate:** [value]
|
| 42 |
+
- **Batch size:** [value]
|
| 43 |
+
|
| 44 |
+
## Evaluation Results
|
| 45 |
+
|
| 46 |
+
[Add your metrics: accuracy, F1, etc.]
|