Commit History
-
model and quantized model both with attention
Limanc3f9e2b
-
add output_attentions true to config
Liman89238ad -
replace fp32 model with one with attention layers
Limanc916fce -
onnx model with attention
Liman998e725
-
rename q8 model
Limana5f4313 -
add quantized models
Liman18a990c -
onnx model
Liman8d104f2 -
initial commit
Verified signatureb4850a4