phi-1 / modeling_mixformer_sequential.py

Commit History

fix(phi-1): Checks length of `attention_mask`if it is passed as direct tensor.
1f890f7

gugarosa commited on

Support for `attention_mask` in forward pass.
d22f35e

gugarosa commited on

Upload MixFormerSequentialForCausalLM
44cca9f

suriyagunasekar commited on

Upload MixFormerSequentialForCausalLM
0f4ae0e

suriyagunasekar commited on