Commit History
-
lora model, need gpu
5923c3d
-
q4
e349edf -
faster q4
db8f193 -
q4 model fast
957293d -
q8 model
42390f7 -
streaming
29d2150 -
llama app
d8958cb -
llama app
82a4b2b -
test
cecbdb4 -
lab2 test
7702794 -
lab2 test
659d5ba -
lab2 test
2cd6927 -
lab2 test
8ea8a6a -
lab2 test
33780b7 -
lab2 test
66d8dc1 -
lab2 test
f81fade
-
lab2 test
7ca3ebf -
added requirements
59b7c26 -
test app
11c7c05
-
test app
bde77a1 -
test app
bee75d0 -
test app
c54c38e