Instructions to use answerdotai/ModernBERT-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use answerdotai/ModernBERT-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="answerdotai/ModernBERT-base")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("answerdotai/ModernBERT-base") model = AutoModelForMaskedLM.from_pretrained("answerdotai/ModernBERT-base") - Notebooks
- Google Colab
- Kaggle
modernBERT training learning rate=0 and validation_loss=nan
#66
by devs9 - opened
I have latest version of transformers, torch installed. I train the model using AutoModelForSequenceClassification but I keep getting learning rate as 0 and validation loss as nan. I have not installed flash-attn
What are the correct version of packages that I should install ?
Any help is appreciated.
This comment has been hidden
I have the same problem. How to solve it?