Instructions to use distilbert/distilbert-base-uncased with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use distilbert/distilbert-base-uncased with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="distilbert/distilbert-base-uncased")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("distilbert/distilbert-base-uncased") model = AutoModelForMaskedLM.from_pretrained("distilbert/distilbert-base-uncased") - Inference
- Notebooks
- Google Colab
- Kaggle
Poor Performance on multi class
#22
by eyinlojuoluwa - opened
I tried to fine-tune this model with just 800 datapoints, but failed woefully. I might have been doing a poor job though. But, the truth is that the model didnt perform at all. May be it is because I have ups to 15 unique labels though.