Text Classification
Transformers
PyTorch
Safetensors
Arabic
bert
custom_code
text-embeddings-inference
Instructions to use tunis-ai/TunBERT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tunis-ai/TunBERT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="tunis-ai/TunBERT", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("tunis-ai/TunBERT", trust_remote_code=True) model = AutoModelForSequenceClassification.from_pretrained("tunis-ai/TunBERT", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
add a more meaningful label names
#3
by not-lain - opened
change LABEL_1 and LABEL_0 to a more meaningful names
labels will be disabled as soon as we enable trust_remote_code
TODO: add custom config_class
not-lain changed discussion status to closed
not-lain changed discussion status to open
not-lain changed discussion status to closed
@not-lain
So basically to use it effectivelly i need to finetune it on my specific dataet to get meaningful labels ?
It can not be used directly ?
@hamzabouajila i do advise you to finetune https://huggingface.co/google-bert/bert-base-uncased instead.
the implementation in this repo is somewhat broken , also the model head in this one has 2 layers which is a bit unconventional for transformer models.