Question Answering
Transformers
PyTorch
TensorFlow
Safetensors
English
deberta-v2
deberta
deberta-v3
squad
squad_v2
Eval Results (legacy)
Instructions to use sjrhuschlee/deberta-v3-base-squad2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sjrhuschlee/deberta-v3-base-squad2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="sjrhuschlee/deberta-v3-base-squad2")# Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("sjrhuschlee/deberta-v3-base-squad2") model = AutoModelForQuestionAnswering.from_pretrained("sjrhuschlee/deberta-v3-base-squad2") - Notebooks
- Google Colab
- Kaggle
Add TF weights
#1
by sjrhuschlee - opened
Model converted by the transformers' pt_to_tf CLI. All converted model outputs and hidden layers were validated against its PyTorch counterpart.
Maximum crossload output difference=5.484e-06; Maximum crossload hidden layer difference=2.339e-05;
Maximum conversion output difference=5.484e-06; Maximum conversion hidden layer difference=2.339e-05;
sjrhuschlee changed pull request status to merged