Commit History

Fix running condition of translate_llama2 (#16)
03a3e66
Running
verified

Vokturz cieske commited on

fixed mem_LORA's formula
7e1cbde
verified

Vokturz commited on

added llama-3 (from nousreasearch)
fb765e5

Vokturz commited on

hide mistralai/Mixtral-8x7B-Instruct-v0.1 since is a gated model
b10516b

Vokturz commited on

update default model list
1ba133e

Vokturz commited on

modified default model list
eddcb6b

Vokturz commited on

cached model list to memory (exclude falcon)
6826b0f

Vokturz commited on

fix typo in model_list
34fc3dd

Vokturz commited on

added a list of some models
5c9514a

Vokturz commited on

added Apple vendor
d37299b

Vokturz commited on

fix way num parameters are displayed
0cc3d3a

Vokturz commited on

solve a minor bug
e8be103

Vokturz commited on

cache default model
fddae32

Vokturz commited on

fix a warning
2d9aa2d

Vokturz commited on

improved how memory is managed
a0b9dac

Vokturz commited on

fix typo
74c26d6

Vokturz commited on

remove unnecesary line
204281c

Vokturz commited on

improve the way results are displayed
ae0011e

Vokturz commited on

modify title
992ded3

Vokturz commited on

improve how gpu are displayed
161a324

Vokturz commited on

hide year filter
79399de

Vokturz commited on

add app
76398c6

Vokturz commited on

first version
3fe032d

Vokturz commited on