Code for "Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal" (ACL 2024)
-
Updated
Oct 21, 2024 - Python
Code for "Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal" (ACL 2024)
"An Investigation of the Combination of Rehearsal and Knowledge Distillation in Continual Learning for Spoken Language Understanding", accepted at INTERSPEECH 2023.
Towards Rehearsal-based Continual Learning at Scale: distributed CL using Horovod + PyTorch on up to 128 GPUs
Add a description, image, and links to the rehearsal topic page so that developers can more easily learn about it.
To associate your repository with the rehearsal topic, visit your repo's landing page and select "manage topics."