Commit History
-
Update README.md
Verified signature8915843 -
Update README.md
Verified signature7ea4ee7 -
Update README.md
Verified signaturea899994 -
Upload tokenizer
Verified signaturec49b2bc -
Upload RobertaForSequenceClassification
Verified signaturefc00447
-
Update README.md
Verified signature# 🧠 Toxicity_model_RoBERTa-base-bne– Spanish Toxicity Classifier (Fine-tuned) ## 📌 Model Description This model is a fine-tuned version** of `RoBERTa-base-bne`, specifically trained to classify the toxicity level of **Spanish-language user comments on news articles**. It distinguishes between three categories: - **Non-toxic** -**Slightly-toxic** - **Toxic** ## 📂 Training Data The model was fine-tuned on the **[SocialTOX dataset](https://huggingface.co/datasets/gplsi/SocialTOX)**, a collection of Spanish-language comments annotated for varying levels of toxicity. These comments come from news platforms and represent real-world scenarios of online discourse. --- ## Training hyperparameters - epochs: 7 - learning_rate: 1.51e-6 - beta1: 0.9 - beta2: 0.95 -Adam_epsilon: 2.8e-8 - weight_decay: 3.88e-12 - batch_size: 16 - max_seq_length: 5126458120
-
Update README.md
Verified signaturef510b1c
-
model detail
0f7267b -
Upload config.json
update config.json file092644b -
Update README.md
Comment classification model according to their toxicity. This model has been obtained by fine-tuning the RoBERTa language model in Spanish (https://huggingface.co/PlanTL-GOB-ES/roberta-base-bne)eb96b79 -
Upload 11 files
Comment classification model according to their toxicity. This model has been obtained by fine-tuning the RoBERTa language model in Spanish (https://huggingface.co/PlanTL-GOB-ES/roberta-base-bne). To classify use this mapping: map_labels={0: '1. No tóxico', 1: '2. Ligeramente tóxico', 2: '3. Tóxico', 3: '4. Muy tóxico'}ee8d5cb -
initial commit
0d674fa