model and quantized model both with attention
c3f9e2b
Liman
commited on
Commit History
add output_attentions true to config
89238ad
Liman
commited on
replace fp32 model with one with attention layers
c916fce
Liman
commited on
onnx model with attention
998e725
Liman
commited on
rename q8 model
a5f4313
Liman
commited on
add quantized models
18a990c
Liman
commited on
onnx model
8d104f2
Liman
commited on