Instructions to use edsi-umd/on-task-bert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use edsi-umd/on-task-bert with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="edsi-umd/on-task-bert")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("edsi-umd/on-task-bert") model = AutoModelForSequenceClassification.from_pretrained("edsi-umd/on-task-bert", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 4cd8edf6a1c0dd1cdb1918e761964a624812269c583aaa5052e7c57d530233f3
- Size of remote file:
- 5.27 kB
- SHA256:
- 3e0ca78c1abe6f6db6b6c961587b1aae528f81270b504da69957ed9a0ba28b7b
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.