OpenTransformer
/

AGILLM4-diffusionblocks

diffusionblocks

memory-efficient-training

block-wise-training

Model card Files Files and versions

AGILLM4-diffusionblocks

Ctrl+K

Ctrl+K

3 contributors

History: 18 commits

Scott/Codex

Tune DBlock backward-math speed line

9c90574 12 days ago

.gitattributes

1.52 kB
initial commit 13 days ago
.gitignore

23 Bytes
Add improved sublinear anchor coverage 13 days ago
README.md

8.82 kB
Tune DBlock backward-math speed line 12 days ago
dblocks_agillm4.py

4.66 kB
AGILLM4-DiffusionBlocks: block-wise AR+SAT+NAT denoising, fused CE, tied heads 13 days ago
dblocks_agillm4_lm.py

6.35 kB
AGILLM4-DiffusionBlocks: block-wise AR+SAT+NAT denoising, fused CE, tied heads 13 days ago
dblocks_train.py

16.9 kB
Tune DBlock backward-math speed line 12 days ago
fused_ce.py

2.44 kB
Upgrade VRAM-first DiffusionBlocks trainer 13 days ago
nB300_agillm4_vram_dblock.py

147 kB
Tune DBlock backward-math speed line 12 days ago
relaunch_agillm4_dblock.sh

3.73 kB
Add stochastic sparse DBlock speed profile 13 days ago
relaunch_agillm4_dblock_sg2.sh

1.93 kB
Tune DBlock backward-math speed line 12 days ago
relaunch_agillm4_dblock_tied.sh

3.5 kB
Add stochastic sparse DBlock speed profile 13 days ago
sublinear_improved.py

3.08 kB
Add sublinear attention v2 improvements 13 days ago
sublinear_improved_snippet.py

1.55 kB
Add sublinear attention v2 improvements 13 days ago