model and quantized model both with attention
7c7c3b6
Liman
commited on
Commit History
add output_attentions true to config
fc60a15
Liman
commited on
replace fp32 model with one with attention layers
1d87473
Liman
commited on
onnx model with attention
25edbdb
Liman
commited on
rename q8 model
2c3fa66
Liman
commited on
add quantized models
95f2179
Liman
commited on
config files
02fc9c9
Liman
commited on
onnx model
66a59f9
Liman
commited on