Commit History
-
model and quantized model both with attention
Liman7c7c3b6
-
add output_attentions true to config
Limanfc60a15 -
replace fp32 model with one with attention layers
Liman1d87473 -
onnx model with attention
Liman25edbdb
-
rename q8 model
Liman2c3fa66 -
add quantized models
Liman95f2179
-
config files
Liman02fc9c9 -
onnx model
Liman66a59f9 -
initial commit
Verified signature4c2780c