norbert4-xlarge / modeling_gptbert.py

Commit History

Make the FlashAttention logic more robust
269f48e
verified

davda54 commited on

fix
45d8be8
verified

davda54 commited on

removed SDPA
b50a33c
verified

davda54 commited on

Update modeling_gptbert.py
9bd525c
verified

davda54 commited on

fixed SDPA for older PyTorch versions
b190823
verified

davda54 commited on

FlashAttention support
8e9223a
verified

davda54 commited on

Update modeling_gptbert.py
a974f9c
verified

davda54 commited on

Fixes and optimizations
51fbecf
verified

davda54 commited on

Update modeling_gptbert.py
86e8462
verified

lgcharpe commited on

Upload folder using huggingface_hub
2a8e9bc
verified

davda54 commited on