 Alex Cheema
|
4748bb7dc7
increase file download timeout to 30min
|
7 bulan lalu |
|
Alex Cheema
|
ae770db4f3
increase download chunks to 1MB
|
7 bulan lalu |
|
Alex Cheema
|
82f75d0ccf
increase hf download http timeout 15 mins for large downloads
|
7 bulan lalu |
|
Alex Cheema
|
295f41c5cc
increase bench job timeout to give enough time to download
|
7 bulan lalu |
|
Alex Cheema
|
19a27c5bfd
HF_HOME -> EXO_HOME
|
7 bulan lalu |
|
Alex Cheema
|
d7ca9b7732
show each node id in the tinychat topology viz
|
7 bulan lalu |
|
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 bulan lalu |
|
Alex Cheema
|
21586063f6
use llama-3.2-1b in tinygrad test
|
7 bulan lalu |
|
Alex Cheema
|
277d63d860
special case when a model doesnt have a model index file, then use wildcard for allow_patterns
|
7 bulan lalu |
|
Alex Cheema
|
74379ef671
log download logs with DEBUG>=6 very verbose
|
7 bulan lalu |
|
Alex Cheema
|
3c7bd48aa3
get rid of some more hf bloat
|
7 bulan lalu |
|
Alex Cheema
|
1df023023e
remove a lot of hf bloat
|
7 bulan lalu |
|
Alex Cheema
|
b89495f444
rewrite ShardDownloader, simplify significantly
|
7 bulan lalu |
|
Alex Cheema
|
a3766f538a
add exception for mlx-community/DeepSeek-R1-3bit and mlx-community/DeepSeek-V3-3bit in tokenizers test
|
7 bulan lalu |
|
Alex Cheema
|
82ef086010
add deepseek-v3-3bit and deepseek-r1-3bit
|
7 bulan lalu |
|
Alex Cheema
|
55ea366932
fix post_init deepseek v3
|
7 bulan lalu |
 Alex Cheema
|
63318983de
Merge pull request #631 from sigseg5/main
|
7 bulan lalu |
 sigseg5
|
fb841a1f50
Adjust truncate size in history list for text without any spaces
|
7 bulan lalu |
|
sigseg5
|
4512366580
Fix bubble behavior when user passes long text without any spaces
|
7 bulan lalu |
|
sigseg5
|
9525c0e7a7
Add adaptive padding for user and assistant messages on width <= 1480px
|
7 bulan lalu |
|
Alex Cheema
|
66f73768cc
Merge pull request #627 from exo-explore/deepseek
|
7 bulan lalu |
|
Alex Cheema
|
fdd05baddb
fix tokenizer tests
|
7 bulan lalu |
|
Alex Cheema
|
59174bdc62
we have a lot of models so group them nicely
|
7 bulan lalu |
|
Alex Cheema
|
cfdaaef8e6
handle thinking outputs nicely, format latex beautifully
|
7 bulan lalu |
|
Alex Cheema
|
d8ffa59dba
add deepseek v1, v3 and all the distills
|
7 bulan lalu |
|
Alex Cheema
|
aa1ce21f82
Merge pull request #625 from eltociear/patch-1
|
7 bulan lalu |
 Ikko Eltociear Ashimine
|
4fb01f516d
chore: update manual_discovery.py
|
7 bulan lalu |
|
Alex Cheema
|
a635b23044
Merge pull request #619 from exo-explore/runners2
|
7 bulan lalu |
|
Alex Cheema
|
ad0e0d02d8
fix readme images
|
7 bulan lalu |
|
Alex Cheema
|
2644fd02c8
Merge pull request #617 from exo-explore/runners2
|
7 bulan lalu |
