fix mixed precision loading with recent transformers versions (#39)

fix-device-issues (#38)

cpu-inference (#35)

feat: configurable use_reentrant (#37)

refine-codebase (#33)

fix-adapter-masks (#32)

change rotary base (#31)

2-adapter-tuning (#29)

Update modeling_xlm_roberta.py

2-adapter-tuning-initial-impl (#30)

Update modeling_xlm_roberta.py

make-lora-stateless (#25)

feat-routing (#26)

rope-embeddings (#20)

alibi (#19)

Update modeling_xlm_roberta.py (#13)

Update modeling_xlm_roberta.py (#12)

truncate-embedding-dimension (#10)

Refactor LoRA (#8)

Support for SequenceClassification (#7)

Support torch_dtype and CLS pooling (#6)

add-encode-function (#5)

support-cpu (#2)

add stochastic_depth

support activation checkpointing

add mlm model and adjust naming