KoalaAI/Text-Moderation

Puedes utilizar cURL para acceder a este modelo:

$ curl -X POST -H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoTrain"}' https://api-inference.huggingface.co/models/KoalaAI/Text-Moderation

O la API de Python:

from transformers import AutoModelForSequenceClassification, AutoTokenizer

# Carga el modelo y el tokenizer
model = AutoModelForSequenceClassification.from_pretrained("KoalaAI/Text-Moderation")
tokenizer = AutoTokenizer.from_pretrained("KoalaAI/Text-Moderation")

# Ejecuta el modelo en tu entrada
inputs = tokenizer("I love AutoTrain", return_tensors="pt")
outputs = model(**inputs)

# Obtén las predicciones
logits = outputs.logits

# Aplica softmax para obtener probabilidades (puntuaciones)
probabilities = logits.softmax(dim=-1).squeeze()

# Recupera las etiquetas
id2label = model.config.id2label
labels = [id2label[idx] for idx in range(len(probabilities))]

# Combina etiquetas y probabilidades, luego ordena
label_prob_pairs = list(zip(labels, probabilities))
label_prob_pairs.sort(key=lambda item: item[1], reverse=True)

# Imprime los resultados ordenados
for label, probability in label_prob_pairs:
    print(f"Label: {label} - Probability: {probability:.4f}")

El resultado del código Python anterior se verá así:

Label: OK - Probability: 0.9840
Label: H - Probability: 0.0043
Label: SH - Probability: 0.0039
Label: V - Probability: 0.0019
Label: S - Probability: 0.0018
Label: HR - Probability: 0.0015
Label: V2 - Probability: 0.0011
Label: S3 - Probability: 0.0010
Label: H2 - Probability: 0.0006