 Alex Cheema
|
57c88f6bb7
add smollm2 models
|
1 anno fa |
|
Alex Cheema
|
e80ed76c03
ignore in test-tokenizers
|
1 anno fa |
|
Alex Cheema
|
36c1f68cc7
update llama-3.1-405b-8bit model id to IntuitIntel/Meta-Llama-3.1-405B-Instruct-8bit
|
1 anno fa |
|
Alex Cheema
|
c8438b6d23
add llama-3.1-405b-8bit
|
1 anno fa |
|
Alex Cheema
|
6ae6ebeb05
revert back to CORRECTED
|
1 anno fa |
|
Alex Cheema
|
e8e05e15a1
remove CORRECTED llama 70b
|
1 anno fa |
|
Alex Cheema
|
436709e509
revert back to CORRECTED
|
1 anno fa |
|
Alex Cheema
|
8d524bfe71
change mlx-community/Meta-Llama-3.1-70B-Instruct-bf16-CORRECTED to mlx-community/Meta-Llama-3.1-70B-Instruct-bf16 since it works now
|
1 anno fa |
|
Alex Cheema
|
ab91f20296
Revert "add max-caches option"
|
1 anno fa |
|
Alex Cheema
|
9e3ae2b4b4
add max-caches option
|
1 anno fa |
|
Alex Cheema
|
bc7acfd37b
update mlx to 0.19.3, mlx-lm to 0.19.2
|
1 anno fa |
|
Alex Cheema
|
661035f0e0
use KVCache instead of RotatingKVCache
|
1 anno fa |
 Alex Cheema
|
3d9c58464e
Merge pull request #403 from maujim/api/small-model-default
|
1 anno fa |
 Mukund Mauji
|
d0b7154f63
set fallback llama model to use smallest one also
|
1 anno fa |
|
Mukund Mauji
|
9987ce840e
use the smallest possible model as the default_model
|
1 anno fa |
|
Mukund Mauji
|
f523713417
add a default_model in ChatGPTAPI
|
1 anno fa |
|
Alex Cheema
|
7e539672b2
Merge pull request #399 from thenatlog/tidy/models
|
1 anno fa |
 thenatlog
|
8b23f124c9
update js
|
1 anno fa |
|
thenatlog
|
ac49b2a2d3
revert main.py
|
1 anno fa |
|
thenatlog
|
f5d5e44146
Merge remote-tracking branch 'upstream/main' into tidy/models
|
1 anno fa |
|
Alex Cheema
|
bf1f21da67
Merge pull request #400 from exo-explore/fix_formatting
|
1 anno fa |
|
Alex Cheema
|
f82410f808
clear instructions on formatting with yapf, remove linting
|
1 anno fa |
|
Alex Cheema
|
478db26bd7
get rid of all the different linters. we just use yapf now
|
1 anno fa |
|
Alex Cheema
|
98ea71edda
run format.py on ./exo
|
1 anno fa |
|
thenatlog
|
7dfe856fe3
remove buggy select logic
|
1 anno fa |
|
thenatlog
|
29ca6ad1ed
cehckpoint
|
1 anno fa |
|
Alex Cheema
|
50a1b171f6
Merge pull request #398 from exo-explore/fix_flops_parsing
|
1 anno fa |
|
Alex Cheema
|
9dc93fd53e
add traceback.print_exc on topology collection errors from peers
|
1 anno fa |
|
Alex Cheema
|
eb8a444e4c
fix flops parsing
|
1 anno fa |
|
Alex Cheema
|
bc1d88d86d
ignore dummy
|
1 anno fa |
