Instructions to use albert/albert-xxlarge-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use albert/albert-xxlarge-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="albert/albert-xxlarge-v1")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("albert/albert-xxlarge-v1") model = AutoModelForMaskedLM.from_pretrained("albert/albert-xxlarge-v1") - Inference
- Notebooks
- Google Colab
- Kaggle
Custom Training Albert-xxlarge-v1
#1
by sahmed31 - opened
I wish to train the Albert-xxlarge-v1 model on different datasets. Can we do that?
Hey @sahmed31 ,
Yes, you can do that. I recommend taking a look at the examples in the transformers repository to see possible training pipelines.
Once you have trained your model on a dataset, you can re-use the resulting checkpoint and train it on another similar dataset or another task altogether (dropping task-specific weights in the process).