XllentAI
/

modular_arithmetic

modular-arithmetic

modular-multiplication

carry-aware-tcn

temporal-convolutional-network

algorithmic-reasoning

length-generalization

sair-modular-arithmetic-challenge

Model card Files Files and versions

modular_arithmetic

131 MB

Ctrl+K

Ctrl+K

1 contributor

History: 16 commits

etwk

Use HF default .gitattributes (comprehensive LFS rules)

ba38bb5 5 months ago

.gitattributes
1.52 kB
Use HF default .gitattributes (comprehensive LFS rules) 5 months ago
.gitignore
19 Bytes
Commit all 5 cell weights as git-LFS objects (16/32/64/128/256-bit) 5 months ago
README.md
16.1 kB
Add model-card YAML frontmatter (clears HF 'missing yaml metadata' warning) 5 months ago
manifest.json
10.8 kB
Shrink: 16/32-bit MLPs -> width-matched TCN. Artifact 0.77GB -> 0.13GB 5 months ago
model.py
12.8 kB
Tier 10 = 0.94: highest_tier 9->10 (MAX), overall 0.886->0.978 5 months ago
train.py
9.06 kB
Horner-RNN modular-multiplication model (tiers 1-5, up to 2^64) 5 months ago
weights1024.pt
19 MB
xet

Tier 9 = 0.99: highest_tier 8->9, overall 0.788->0.886 5 months ago
weights128.pt
15.8 MB
xet

Commit all 5 cell weights as git-LFS objects (16/32/64/128/256-bit) 5 months ago
weights16.pt
9.48 MB
xet

Shrink: 16/32-bit MLPs -> width-matched TCN. Artifact 0.77GB -> 0.13GB 5 months ago
weights2048.pt
20.5 MB
xet

Harden tier 10: 0.94 -> 0.98, overall 0.978 -> 0.982 5 months ago
weights256.pt
19 MB
xet

Commit all 5 cell weights as git-LFS objects (16/32/64/128/256-bit) 5 months ago
weights32.pt
12.6 MB
xet

Shrink: 16/32-bit MLPs -> width-matched TCN. Artifact 0.77GB -> 0.13GB 5 months ago
weights512.pt
22.1 MB
xet

Tier 8 re-polish: 0.92 -> 0.98, overall 0.982 -> 0.988 5 months ago
weights64.pt
12.6 MB
xet

64-bit cell: MLP -> carry-aware TCN (fixes tier-0 near-2^64, 944MB->13MB) 5 months ago