jupyterjazz's picture
refine-codebase (#33)
2646361 verified
|
raw
history blame
557 Bytes

Core implementation of Jina XLM-RoBERTa

This implementation is adapted from XLM-Roberta. In contrast to the original implementation, this model uses Rotary positional encodings and supports flash-attention 2.

Models that use this implementation

to be added soon

Converting weights

Weights from an original XLMRoberta model can be converted using the convert_roberta_weights_to_flash.py script in the model repository.