Commit History

cpu quantiziation config
9939aee

BoostedJonP commited on

revert quantization removal breaking tensor shape
185a134

BoostedJonP commited on

removed quanitization config
30494ce

BoostedJonP commited on

preserve quantization config
f2c56b3

BoostedJonP commited on

remove cache usage in model
6cbf469

BoostedJonP commited on

added bits and bytes
6f78921

BoostedJonP commited on

fixed cpu loading issue
476d1eb

BoostedJonP commited on

additional cpu fallback
5119833

BoostedJonP commited on

fixed cpu running issue
8b45180

BoostedJonP commited on

fixed tensor types
c58fada

BoostedJonP commited on

remove bits and bytes
ebfdc68

BoostedJonP commited on

removed bnb config
c7aa5b3

BoostedJonP commited on

added quantization for performance
25ab7b8

BoostedJonP commited on

added torhc.compile and system prompt
1748543

BoostedJonP commited on

fixed DynamicCache issue
ac7d9e3

BoostedJonP commited on

Fix short_description length for Hugging Face Spaces
f89d70e

BoostedJonP commited on

add app file, requirements and readme
957f61b

BoostedJonP commited on

initial commit
62dbd7b
verified

BoostedJonP commited on