README.md

---
base_model:
- nasa-impact/nasa-smd-ibm-v0.1
tags:
- single-label
pipeline_tag: text-classification
library_name: transformers
---
# Division Classification Model

This is a single label classification task for automated tagging of documents in Science Discovery Engine. Based on [INDUS Model](https://huggingface.co/nasa-impact/nasa-smd-ibm-v0.1)

The idx to label mapping is:
```
"0": "Astrophysics",
"1": "Biological and Physical Sciences",
"2": "Earth Science",
"3": "Heliophysics",
"4": "Planetary Science"
```

## Data distribution

![image/png](https://cdn-uploads.huggingface.co/production/uploads/675c4e0a0fd4155cb71fc2a6/yr-bXZRTtVO-6Be_PM2SY.png)

## Evalution of the model:

![image/png](https://cdn-uploads.huggingface.co/production/uploads/675c4e0a0fd4155cb71fc2a6/Vz4R0i_q0Uklwv8uZcdhS.png)


![image/png](https://cdn-uploads.huggingface.co/production/uploads/675c4e0a0fd4155cb71fc2a6/Lh7CPtHpXUtiZWd0k3eKr.png)


## How to Use
You can load this model using the Hugging Face 🤗 Transformers library:

### Using the Pipeline
```python
from transformers import pipeline

classifier = pipeline("text-classification", model="nasa-impact/division-classifier")
prediction = classifier("Your input text", truncation=True, padding="max_length", max_length=512)
print(prediction)
```

### Using the Model
```python
from transformers import AutoTokenizer, AutoModelForSequenceClassification
model_name = "nasa-impact/division-classifier"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)

inputs = tokenizer("Your input text", return_tensors="pt", truncation=True, max_length=512, padding="max_length")
outputs = model(**inputs)
predicted_label = outputs.logits.argmax(-1).item()
print(predicted_label)
```