|
--- |
|
language: |
|
- en |
|
base_model: |
|
- microsoft/deberta-v3-base |
|
pipeline_tag: text-classification |
|
license: mit |
|
--- |
|
Binary classification model for ad-detection on QA Systems. |
|
|
|
## Sample usage |
|
|
|
```python |
|
import torch |
|
from transformers import AutoTokenizer, AutoModelForSequenceClassification |
|
classifier_model_path = "teknology/ad-classifier-v0.4" |
|
tokenizer = AutoTokenizer.from_pretrained(classifier_model_path) |
|
model = AutoModelForSequenceClassification.from_pretrained(classifier_model_path) |
|
model.eval() |
|
device = torch.device("cuda" if torch.cuda.is_available() else "cpu") |
|
model.to(device) |
|
def classify(passages): |
|
inputs = tokenizer( |
|
passages, padding=True, truncation=True, max_length=512, return_tensors="pt" |
|
) |
|
inputs = {k: v.to(device) for k, v in inputs.items()} |
|
with torch.no_grad(): |
|
outputs = model(**inputs) |
|
logits = outputs.logits |
|
predictions = torch.argmax(logits, dim=-1) |
|
return predictions.cpu().tolist() |
|
preds = classify(["sample_text_1", "sample_text_2"]) |
|
``` |
|
|
|
|
|
## Version |
|
|
|
Previous versions can be found at: |
|
- v0.0: https://huggingface.co/jmvcoelho/ad-classifier-v0.0 |
|
Trained with the official data from Webis Generated Native Ads 2024 |
|
- v0.1: https://huggingface.co/jmvcoelho/ad-classifier-v0.1 |
|
Trained with v0.0 data + new synthetic data |
|
- v0.2: https://huggingface.co/jmvcoelho/ad-classifier-v0.2 |
|
Similar to v0.1, but include more diversity in ad placement startegies through prompting. |
|
- v0.3: https://huggingface.co/teknology/ad-classifier-v0.3 |
|
Continued from v0.2, added a new synthetic dataset generated based on Wikipedia articles. |
|
- **v0.4**: Same training data composition as v0.3, but curriculum learning with the mixed data. |
|
|
