 Hamid Shojanazeri
|
8776ceb833
update with the HF flash attention native
|
hai 1 ano |
|
Hamid Shojanazeri
|
dbfea484c6
Feature : Enable Intel GPU/XPU finetuning and inference (#116)
|
hai 1 ano |
 Beto
|
d92226a873
Removing option for local model, it's not working as expected. Would need further testing with the models from HF
|
hai 1 ano |
|
Beto
|
7881b3bb99
Changing safety utils to use HF classes to load Llama Guard. Removing Llama plain inference code
|
hai 1 ano |
|
Beto
|
109b728d02
Adding Llama Guard safety checker.
|
hai 1 ano |
 Abhilash Majumder
|
6a78b96764
Merge branch 'main' into ipex_feature
|
hai 1 ano |
 Matthias Reso
|
8ac44ef3be
Fix vocab size mismatch in inference due to added pad token
|
hai 1 ano |
 abhilash1910
|
ad6b27d316
merge conflicts
|
hai 1 ano |
|
abhilash1910
|
33da341af5
upstream resolve conflict
|
hai 1 ano |
|
Matthias Reso
|
ccda6fb8ca
Move inference scripts into example folder
|
hai 1 ano |
