DeBERTa (v1 / v2 / v3)
Collection
Pure Keras 3, backend-agnostic (JAX / TensorFlow / PyTorch) ports of DeBERTa, DeBERTa-v2, and DeBERTa-v3 encoders. • 8 items • Updated
How to use kerasformers/deberta_v3_base with Keras:
# Available backend options are: "jax", "torch", "tensorflow".
import os
os.environ["KERAS_BACKEND"] = "jax"
import keras
model = keras.saving.load_model("hf://kerasformers/deberta_v3_base")
How to use kerasformers/deberta_v3_base with KerasFormers:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
A pure Keras 3 port of DeBERTa-v3, converted from microsoft/deberta-v3-base (Hugging Face Transformers).
The weights are backend-agnostic: the same checkpoint loads and runs identically under the JAX, TensorFlow, or PyTorch Keras backend (KERAS_BACKEND=jax|tensorflow|torch), via kerasformers.
from kerasformers.models.deberta_v3 import DebertaV3Model
model = DebertaV3Model.from_weights("kerasformers/deberta_v3_base")
Base model
microsoft/deberta-v3-base