Alex Cheema
|
295f41c5cc
increase bench job timeout to give enough time to download
|
7 maanden geleden |
Alex Cheema
|
19a27c5bfd
HF_HOME -> EXO_HOME
|
7 maanden geleden |
Alex Cheema
|
d7ca9b7732
show each node id in the tinychat topology viz
|
7 maanden geleden |
Alex Cheema
|
b349e48b0d
fix visual bug where frontend would show the full hf repo size, but in some cases that includes redundant files so we should use the model index in those cases too
|
7 maanden geleden |
Alex Cheema
|
21586063f6
use llama-3.2-1b in tinygrad test
|
7 maanden geleden |
Alex Cheema
|
277d63d860
special case when a model doesnt have a model index file, then use wildcard for allow_patterns
|
7 maanden geleden |
Alex Cheema
|
74379ef671
log download logs with DEBUG>=6 very verbose
|
7 maanden geleden |
Alex Cheema
|
3c7bd48aa3
get rid of some more hf bloat
|
7 maanden geleden |
Alex Cheema
|
1df023023e
remove a lot of hf bloat
|
7 maanden geleden |
Alex Cheema
|
b89495f444
rewrite ShardDownloader, simplify significantly
|
7 maanden geleden |
Alex Cheema
|
a3766f538a
add exception for mlx-community/DeepSeek-R1-3bit and mlx-community/DeepSeek-V3-3bit in tokenizers test
|
7 maanden geleden |
Alex Cheema
|
82ef086010
add deepseek-v3-3bit and deepseek-r1-3bit
|
7 maanden geleden |
Alex Cheema
|
55ea366932
fix post_init deepseek v3
|
7 maanden geleden |
Alex Cheema
|
63318983de
Merge pull request #631 from sigseg5/main
|
7 maanden geleden |
sigseg5
|
fb841a1f50
Adjust truncate size in history list for text without any spaces
|
7 maanden geleden |
sigseg5
|
4512366580
Fix bubble behavior when user passes long text without any spaces
|
7 maanden geleden |
sigseg5
|
9525c0e7a7
Add adaptive padding for user and assistant messages on width <= 1480px
|
7 maanden geleden |
Alex Cheema
|
66f73768cc
Merge pull request #627 from exo-explore/deepseek
|
7 maanden geleden |
Alex Cheema
|
fdd05baddb
fix tokenizer tests
|
7 maanden geleden |
Alex Cheema
|
59174bdc62
we have a lot of models so group them nicely
|
7 maanden geleden |
Alex Cheema
|
cfdaaef8e6
handle thinking outputs nicely, format latex beautifully
|
7 maanden geleden |
Alex Cheema
|
d8ffa59dba
add deepseek v1, v3 and all the distills
|
7 maanden geleden |
Alex Cheema
|
aa1ce21f82
Merge pull request #625 from eltociear/patch-1
|
7 maanden geleden |
Ikko Eltociear Ashimine
|
4fb01f516d
chore: update manual_discovery.py
|
7 maanden geleden |
Alex Cheema
|
a635b23044
Merge pull request #619 from exo-explore/runners2
|
7 maanden geleden |
Alex Cheema
|
ad0e0d02d8
fix readme images
|
7 maanden geleden |
Alex Cheema
|
2644fd02c8
Merge pull request #617 from exo-explore/runners2
|
7 maanden geleden |
Alex Cheema
|
88ac12df6c
install clang test
|
7 maanden geleden |
Alex Cheema
|
dfd9d3eb48
linux install
|
7 maanden geleden |
Alex Cheema
|
200ff4d713
linux install
|
7 maanden geleden |