Instructions to use KingsleyElo/naija-sentiment-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KingsleyElo/naija-sentiment-models with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="KingsleyElo/naija-sentiment-models")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("KingsleyElo/naija-sentiment-models", device_map="auto") - Notebooks
- Google Colab
- Kaggle
NaijaSenti Model Weights
Trained model weights for the NaijaSenti sentiment analysis project.
logreg_tfidf.pklβ Logistic Regression pipeline (TF-IDF + classifier)rnn_tokenizer.pklβ Keras tokenizer shared by RNN and LSTMlstm_v2.kerasβ Best LSTM model (Macro F1: 0.71)best_afroxlmr_model_f1_0.7727.ptβ Fine-tuned AfroXLMR (Macro F1: 0.74)afro_xlmr_tokenizer/β AfroXLMR tokenizer files
Project: naija-sentiment on GitHub
Live Demo: Hugging Face Spaces
Model tree for KingsleyElo/naija-sentiment-models
Base model
Davlan/afro-xlmr-base