Gahow Wang 603c85e1e0 model: silence torch parity warning (read loss before backward) ...

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

2026-06-15 16:09:30 +08:00

..

src

model: tiny RoPE+RMSNorm+SwiGLU transformer + overfit test

2026-06-15 16:05:20 +08:00

tests

model: silence torch parity warning (read loss before backward)

2026-06-15 16:09:30 +08:00

build.rs

model: tiny RoPE+RMSNorm+SwiGLU transformer + overfit test

2026-06-15 16:05:20 +08:00

Cargo.toml

model: tiny RoPE+RMSNorm+SwiGLU transformer + overfit test

2026-06-15 16:05:20 +08:00