metadata
base_model: FacebookAI/roberta-large
language: en
license: apache-2.0
model_name: gender-marker-classifier
pipeline_tag: text-classification
tags:
- CRS
- OECD CRS
- text-classification
- lora
- transformers
funded_by: DEval - Deutsches Evaluierungsinstitut der Entwicklungszusammenarbeit gGmbH
tasks:
- text-classification
shared_by: DEval - Deutsches Evaluierungsinstitut der Entwicklungszusammenarbeit gGmbH
This model identifies the relevance of CRS projects to feminist development policy. It is trained on manually annotated CRS data and uses the Gender Marker classification. Labels 0, 1, and 2 represent whether a project has no, significant, or primary focus on feminist policy objectives, such as strengthening rights, resources, and representation (“3R”), advancing gender-transformative and intersectional approaches, or supporting the broader goals of feminist development policy. (CRS Gender Marker)
Evaluation metrics
| precision | recall | f1-score | support | |
|---|---|---|---|---|
| 0 | 0.93 | 0.95 | 0.94 | 234 |
| 1 | 0.82 | 0.68 | 0.74 | 34 |
| 2 | 0.88 | 0.95 | 0.91 | 55 |
| 3 | 0.70 | 0.62 | 0.66 | 34 |
| -- | -- | -- | -- | -- |
| accuracy | 0.89 | 357 | ||
| macro | avg | 0.83 | 0.80 | 0.81 |
| weighted | avg | 0.89 | 0.89 | 0.89 |
Usage
```python
from transformers import AutoModelForSequenceClassification, AutoTokenizer
model = AutoModelForSequenceClassification.from_pretrained("namespace/my-model")
tokenizer = AutoTokenizer.from_pretrained("namespace/my-model")
inputs = tokenizer("hello world", return_tensors="pt")
outputs = model(**inputs)
print(outputs)"
or
from transformers import TextClassificationPipeline
model = TextClassificationPipeline("namespace/my-model")
outputs = model("Hello World!")
print(outputs)"