Instructions to use Rasooli/ParsBERT-sentiment-fa-finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use Rasooli/ParsBERT-sentiment-fa-finetuned with Keras:
# !pip install -U keras tensorflow huggingface_hub # Keras needs TensorFlow installed to read "hf://" paths, so the tensorflow backend is selected here; # "jax" and "torch" also work for computation once TensorFlow is installed. import os os.environ["KERAS_BACKEND"] = "tensorflow" import keras model = keras.saving.load_model("hf://Rasooli/ParsBERT-sentiment-fa-finetuned") - Notebooks
- Google Colab
- Kaggle
ParsBERT Sentiment (Fine-tuned)
This repository contains a Persian sentiment analysis model trained using a custom TensorFlow/Keras classifier on top of ParsBERT.
Label mapping
- 0 → Negative
- 1 → Positive
- 2 → Neutral
Usage note
This is a custom Keras architecture.
To use the model, rebuild the architecture and load the provided
parsbert_sentiment.weights.h5 file.
- Downloads last month
- 4
Model tree for Rasooli/ParsBERT-sentiment-fa-finetuned
Base model
HooshvareLab/bert-base-parsbert-uncased