 Alex Cheema
|
e68d06f4ef
move model-selector styles to index.css
|
1 rok temu |
|
Alex Cheema
|
78db451d7e
add pillow to main dependencies
|
1 rok temu |
|
Alex Cheema
|
824f05263f
Merge branch 'main' into HEAD
|
1 rok temu |
|
Alex Cheema
|
142682645f
bump up tinygrad version
|
1 rok temu |
 Varshith
|
8d3d3df1dd
update readme
|
1 rok temu |
|
Varshith
|
acc94b50c7
chatgpt api integration
|
1 rok temu |
|
Alex Cheema
|
33cbacf513
fix llava sanitize
|
1 rok temu |
|
Alex Cheema
|
2fb961fccd
stick to same convention as new llama
|
1 rok temu |
|
Alex Cheema
|
b44b917151
add pillow as testing dependency
|
1 rok temu |
|
Alex Cheema
|
2aa1e24ea9
remove unused torch import
|
1 rok temu |
|
Alex Cheema
|
833e7f3396
rename sharded_llava -> llava to match new convention
|
1 rok temu |
|
Alex Cheema
|
7d5eed1111
Merge branch 'main' into HEAD
|
1 rok temu |
 Alex Cheema
|
044d189ccc
Merge pull request #94 from mzbac/mlx_refactor
|
1 rok temu |
|
Alex Cheema
|
909d5ef8ba
Merge branch 'main' into mlx_refactor
|
1 rok temu |
|
Alex Cheema
|
63e51a8270
formatting
|
1 rok temu |
|
Alex Cheema
|
6695b019a2
format format.py
|
1 rok temu |
|
Alex Cheema
|
1dc08fecaa
increase max line length to 200
|
1 rok temu |
|
Alex Cheema
|
444137776a
formatting
|
1 rok temu |
 Anchen
|
a6bb8ddf41
update deepseek sanitize to shard layers first before handle switch
|
1 rok temu |
|
Alex Cheema
|
cb217b7b77
format format.py
|
1 rok temu |
|
Alex Cheema
|
4cb36a7f55
increase max line length to 200
|
1 rok temu |
|
Alex Cheema
|
d94e3f9ce4
formatting
|
1 rok temu |
|
Anchen
|
666b1c83ee
refactor(mlx): model sharding and add deepseek v2 support
|
1 rok temu |
|
Alex Cheema
|
931ced7c01
fix a few more linter errors
|
1 rok temu |
|
Alex Cheema
|
57b2f2a4e2
fix ruff lint errors
|
1 rok temu |
|
Alex Cheema
|
ce761038ac
formatting / linting
|
1 rok temu |
|
Alex Cheema
|
f1bd5fe152
Merge pull request #90 from xeb/main
|
1 rok temu |
|
Alex Cheema
|
f051ebe6e0
remove accidentally added files
|
1 rok temu |
 Mark Kockerbeck
|
5eafd5a305
try/except for decode, #75
|
1 rok temu |
|
Varshith
|
2849128d6a
processor load
|
1 rok temu |
