model and quantized model both with attention
56bbff3
Liman
commited on
Commit History
replace fp32 model with one with attention layers
1dc2600
Liman
commited on
onnx model with attention
af82537
Liman
commited on
include output_attentions in tokenizer_config.json
b5158fd
Liman
commited on
include output_attentions config in config.json
48ebe5a
Liman
commited on
rename q8 model
1b1a2ec
Liman
commited on
add quantized models
7187111
Liman
commited on
Imported model from jaxmef repo
71772cd
Liman
commited on