Jai Suphavadeeprasit
|
2f01720899
|
more readme changes
|
2026-03-02 11:39:45 -05:00 |
|
Jai Suphavadeeprasit
|
585244559e
|
more readme changes
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
4a7da8049f
|
README changes
|
2026-03-02 11:18:52 -05:00 |
|
pre-commit-ci[bot]
|
91afc9e46e
|
[pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
d2ea8cd612
|
remove KL
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
dbf6026165
|
remove reqs and update community readme
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
fb3228f669
|
add this to our pyproject
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
ce85c7d95e
|
H100 bug fixes
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
624b3cdabe
|
feedback fixes: shared layers + hard coded values + warmup steps
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
e1f9b926bb
|
script test
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
c80481a3cc
|
script test
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
725a5d5502
|
readme fix
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
00e9da6cae
|
sanity_check
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
6e62513a63
|
packageification
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
fa22bf58d1
|
model layer stuff
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
16ac332880
|
readme fixes
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
396491ab72
|
readme fixes
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
e2e8268f2a
|
cleanup 3
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
fe5b13a5da
|
cleanup 2
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
0ebf3552c9
|
cleanup
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
9f6cc64b9e
|
restart issues 3
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
6800c68ea3
|
restart issues 3
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
32cd466592
|
restart issues 2
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
c53febd0a8
|
restart issues 2
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
917193d2ea
|
restart issues
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
2364d9d8f8
|
math zero 32k
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
7d96367516
|
math zero 32k
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
74d46aaa76
|
math zero
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
676593de73
|
kill old
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
f29a3d04fa
|
gradient flow fix
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
344d87562b
|
wandb integration
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
dc9df00570
|
vllm restart 2
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
9dcb362aba
|
vllm restart 1
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
6bd0296bac
|
vllm restart
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
328bdf3f3f
|
enforce eager check 32k context length
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
211f91b528
|
enforce eager check
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
84cee536a3
|
visibility fix
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
90281f5993
|
lora restart saving gradient changes
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
1127083b5f
|
ditching lora nccl 2
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
eb123f9596
|
ditching lora nccl
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
d7e661117d
|
testing lora
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
71f7cc5b27
|
unneccesary gloo
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
a05a7dc276
|
nccl loras 2
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
c33f9170c3
|
nccl loras
|
2026-03-02 11:18:52 -05:00 |
|
pre-commit-ci[bot]
|
5cfd1929f1
|
[pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
d07ab3e3ce
|
math zero work arounds
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
a9ebdc50b8
|
math zero ymls
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
19248ed5b4
|
relative imports
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
1559f59b5d
|
logprobs
|
2026-03-02 11:18:52 -05:00 |
|
Jai Suphavadeeprasit
|
77c592c909
|
logprobs
|
2026-03-02 11:18:52 -05:00 |
|